Construction method and device of digital power system based on multifunctional intelligent agent

Abstract

The invention discloses a construction method and device of a digital power system based on a multifunctional agent. Respectively extracting feature production element data and control production element data from the power data of the power plant side and the power grid side; constructing a target data vector based on the power function demand, and determining key control production element data associated with the power function demand; learning by using an artificial intelligence algorithm to obtain a mapping function between the target data vector and the key control production element data, constructing a functional operator taking the mapping function as a kernel, and constructing an intelligent agent based on the functional operator; and adding the intelligent agents corresponding to the different electric power function requirements into the digital electric power system to serve as electric power function implementation units. According to the system, diversified and digital electric power functions based on data driving can be realized, the relation between data can be captured more accurately, and high-value data assets in the electric power system are formed.

Description

Technical Field

[0001] The present application relates to the technical field of power systems, and in particular to a method and device for constructing a digital power system based on a multifunctional intelligent agent. Background Art

[0002] With the advancement of industrialization and the progress and development of science and technology, international cooperation in electric energy is also gradually strengthening. The new global electricity market is emerging: new energy has become the main force, and fossil energy has become a supporting role. In this transformation, new entities such as new energy storage, virtual power plants and smart microgrids have emerged one after another, injecting new impetus into the power system. At the same time, the entire industrial chain of the power system is also facing many challenges.

[0003] The promotion and development of the global power trading market is inseparable from the accurate understanding and keen control of the power system. Therefore, it is urgent to build an intelligent and digital power system. The construction of the current power system faces the challenges of complexity and variability. The complexity is reflected in the complex types of power plants connected to the power grid, which brings great challenges to the grid dispatching. Variability is reflected in the uncertainty of some new energy power generation methods (such as photovoltaics, hydropower, etc.), which also greatly affects the reliability and stability of power supply in the power system. At present, it is urgent to combine emerging fields such as new power and intelligent hydropower business to construct an intelligent and digital power system that helps the domestic power market reform and global power trading. Summary of the invention

[0004] The present application provides a method and device for constructing a digital power system based on a multifunctional intelligent agent. The purpose is to construct an intelligent agent with rich functions by extracting production factor data on the power plant side and the power grid side, and to assist the power system in realizing diversified and digital power functions based on data-driven through the intelligent agent with diversified functions.

[0005] The first aspect of the present application provides a method for constructing a digital power system based on a multifunctional intelligent agent, the method comprising:

[0006] Extracting characteristic production factor data corresponding to the characteristic production factor group from the power data on the power plant side; and extracting control production factor data corresponding to the control production factor group from the power data on the power grid side; the characteristic production factor group includes characteristic production factors of multiple levels; the control production factor group includes control production factors of multiple aspects;

[0007] Based on the power function requirements of the digital power system, the target data vector is constructed using the extracted characteristic production factor data, and key control production factor data associated with the power function requirements are determined from the extracted control production factor data;

[0008] Based on the target data vector and the key control production factor data, an artificial intelligence algorithm is used to learn a mapping function between the target data vector and the key control production factor data, a functional operator with the mapping function as the core is constructed, and an intelligent agent is constructed based on the functional operator;

[0009] Intelligent agents corresponding to various different power function requirements are added to the digital power system, and each intelligent agent is used as a power function realization unit in the digital power system.

[0010] The second aspect of the present application provides a device for constructing a digital power system based on a multifunctional intelligent agent, the device comprising:

[0011] The data extraction module is used to extract characteristic production factor data corresponding to the characteristic production factor group from the power data on the power plant side; and to extract control production factor data corresponding to the control production factor group from the power data on the power grid side; the characteristic production factor group includes characteristic production factors of multiple levels; the control production factor group includes control production factors of multiple aspects;

[0012] A vector construction module, used to construct a target data vector using the extracted characteristic production factor data based on the power function requirements of the digital power system;

[0013] A data determination module, used to determine key control production factor data associated with the power function requirement from the extracted control production factor data;

[0014] An operator construction module is used to use an artificial intelligence algorithm to learn a mapping function between the target data vector and the key control production factor data based on the target data vector and the key control production factor data, construct a functional operator with the mapping function as the core, and construct an intelligent agent based on the functional operator;

[0015] The intelligent agent adding module is used to add intelligent agents corresponding to various different power function requirements to the digital power system, and use each intelligent agent as a power function realization unit in the digital power system.

[0016] Optionally, in an implementation of the first aspect and the second aspect, the characteristic production factor group includes first-level characteristic production factors, second-level characteristic production factors and third-level characteristic production factors corresponding to multiple different power generation types; wherein the first-level characteristic production factors are natural characteristic production factors, the second-level characteristic production factors are single-system characteristic production factors, and the third-level characteristic production factors are plant system characteristic production factors; the natural characteristic production factors are production factors that directly reflect natural characteristics; the single-system characteristic production factors are production factors involving a single system in the power system; and the plant system characteristic production factors are production factors involving the entire system in the power system.

[0017] Optionally, in an implementation of the first aspect and the second aspect, the multiple aspects of the controlled production factors include: electricity price, inertia and frequency, active and reactive power, electricity carbon emission, safety and stability, and grid connection and disconnection;

[0018] The step of extracting the control production factor data corresponding to the control production factor group from the power data on the power grid side includes:

[0019] From the power data on the grid side, extract electricity price data, inertia and frequency data, power data, electricity carbon emission data, safety and stability index data and grid connection and disconnection impact data.

[0020] Optionally, the power function requirement is: the power function requirement for power trading between the grid side and the power plant side, the power function requirement for implementing the grid side's dispatching control over the power plant side, or the power function requirement for the grid's own regulation.

[0021] With respect to the first aspect and the second aspect, in a first possible implementation manner, the power function requirement for power trading between the power grid side and the power plant side is specifically to calculate the electricity price, the functional operator is an electricity price operator, and the electricity price operator is used to calculate the electricity price; the process in which the digital power system uses an intelligent agent constructed based on the electricity price operator includes:

[0022] Calling the intelligent agent to obtain the electricity price calculation result of the power plant side through the electricity price operator;

[0023] The electricity price calculation result is verified by a financial verification model on the grid side; the financial verification model includes: a first verification condition and a second verification condition; the first verification condition is: the actual output of various types of power plants ≥ the grid power; the second verification condition is: the sum of the products of the actual output of various types of power plants, the grid power price at the corresponding time and the power generation time ≤ the product of the grid average price and the grid power;

[0024] If the electricity price calculation result satisfies the first verification condition and the second verification condition, it is determined that the electricity price calculation result has been verified; if the electricity price calculation result does not satisfy any of the first verification condition and the second verification condition, it is determined that the electricity price calculation result has not been verified;

[0025] If the electricity price calculation result is verified, then further selecting an electricity price calculation function that is adapted and feasible on the grid side from the dispatch strategy library, and loading the electricity price calculation function into the electricity price operator to perform function update on the electricity price operator;

[0026] The electricity price calculation result on the grid side is obtained through the updated electricity price operator.

[0027] With respect to the first aspect and the second aspect, in a second possible implementation manner, the power function requirement for power trading between the power grid side and the power plant side is specifically power clearing, the functional operator is a clearing operator, and the clearing operator is used for power clearing; the process in which the digital power system uses an intelligent agent constructed based on the clearing operator includes:

[0028] Perform low-order data abstraction processing according to the power generation element characteristics of each associated power plant of the power grid to obtain a first data vector of each power generation element characteristic;

[0029] Performing long-term transaction electricity price prediction according to a preset long-term electricity price function library and each of the first data vectors to establish a long-term transaction stack;

[0030] Establishing a spot transaction stack based on the spot transaction electricity price of each of the associated power plants, and determining a first clearing function through the long-term transaction stack and the spot transaction stack;

[0031] Determining, according to the first clearing function, a power supply and demand balance state of the power grid when clearing under the first clearing function;

[0032] The first clearing function is adjusted according to the power supply and demand balance state to obtain a second clearing function, and power clearing is performed based on the second clearing function.

[0033] With respect to the first aspect and the second aspect, in a third possible implementation manner, the power function requirement for realizing the dispatching control of the power grid side over the power plant side is specifically peak-shaving dispatching in a high-frequency variable load scenario of thermal power, and the functional operator is a thermal power peak-shaving dispatching operator, which is used to realize peak-shaving dispatching in a high-frequency variable load scenario of thermal power; the process in which the digital power system uses an intelligent agent constructed based on the thermal power peak-shaving dispatching operator includes:

[0034] Calculating the heat storage margin of the energy storage device in the thermal power plant; the heat storage margin includes a heat storage margin characterization value and a heat release capacity characterization value;

[0035] Sending the correlation data between the load, performance and cost of each thermal power unit in the thermal power plant and the heat storage and access margin to the power grid side, so that the power grid side can determine the target unit for expected auxiliary peak load regulation and issue peak load regulation instructions based on the change of thermal power load demand, the correlation data provided by each thermal power plant and the heat storage and access margin;

[0036] receiving a peak-shaving dispatch instruction issued by the power grid side; the peak-shaving dispatch instruction carries the unit identification of the target unit and peak-shaving requirement information for the target unit; the peak-shaving requirement information includes a peak-shaving load curve;

[0037] An auxiliary peak shaving service is performed based on the peak shaving requirement information.

[0038] With respect to the first aspect and the second aspect, in a fourth possible implementation manner, the power function requirement for realizing the dispatching control of the power plant side by the power grid side is specifically water resource dispatching of cascade hydropower stations, the functional operator is a water resource dispatching operator, and the water resource dispatching operator is used to realize water resource dispatching of cascade hydropower stations; the process of the digital power system using an intelligent agent constructed based on the water resource dispatching operator includes:

[0039] Obtain water resource data of each hydropower station in the cascade hydropower station at the current moment;

[0040] For each of the hydropower stations, judging whether the hydropower station is in a safe operating state according to the water resources data of the hydropower station;

[0041] When it is determined that all the hydropower stations are in the safe operation state, judging whether to perform water resource scheduling according to the water resource data of each hydropower station, the preset electricity price scheme and the target historical data; the target historical data includes the average water consumption for power generation and the average power plant revenue corresponding to the month at the current moment;

[0042] If it is determined to carry out water resource scheduling, a water resource scheduling plan is determined based on the water resource data and water resource scheduling model of each hydropower station; the water resource scheduling model is a pre-trained model for outputting a water resource scheduling plan; the water resource scheduling plan includes day-ahead scheduling and seasonal scheduling.

[0043] With respect to the first aspect and the second aspect, in a fifth possible implementation manner, the power function requirement for realizing the dispatching control of the power grid side to the power plant side is specifically the dispatching of the power grid to the power plant in the large-machine small-grid power system, and the functional operator is a large-machine small-grid dispatching operator, and the large-machine small-grid dispatching operator is used to realize the dispatching of the power grid to the power plant in the large-machine small-grid power system; the process of the digital power system using an intelligent agent constructed based on the large-machine small-grid dispatching operator includes:

[0044] Based on the digital feature extraction of the power grid and power supply points of various power generation types in the power system, determine the emergency reserve capacity of various power generation types that should be reserved in the power system and configure the emergency reserve capacity;

[0045] Based on the output of the power source points of the multiple power generation types, judging whether the current power system meets the characteristics of large machine and small grid;

[0046] If it is determined that the current power system meets the characteristics of large machines and small grids, the power grid utilizes the configured emergency reserve capacity of multiple power generation types to dispatch power supply points in the power system for voltage adjustment based on a voltage multi-round adjustment scheme, and / or dispatches power supply points in the power system for frequency adjustment based on a frequency multi-round adjustment scheme; the voltage multi-round adjustment scheme includes: voltage multi-round adjustment methods, voltage multi-round adjustment ranges, and voltage multi-round adjustment priority information for the multiple power generation types; the frequency multi-round adjustment scheme includes: frequency multi-round adjustment methods, frequency multi-round adjustment ranges, and frequency multi-round adjustment priority information for the multiple power generation types;

[0047] Based on the stability control requirements of the frequency dynamic characteristic index of the whole network of the power system, the expected load of the whole network and the characteristics of the units of each power source point, the power grid generates the output curve of the units of each power source point in the future period; the frequency dynamic characteristic index is used to numerically characterize the power change of the whole network required to cause the unit frequency change of the power system;

[0048] The power grid sends a power generation dispatching instruction to each power source point to adjust the power; the power generation dispatching instruction includes an output curve of the unit at the corresponding power source point.

[0049] With respect to the first aspect and the second aspect, in a sixth possible implementation manner, the power function requirement for self-regulation of the power grid is specifically to regulate the grid structure of the power grid, the functional operator is a grid structure regulation operator, and the grid structure regulation operator is used to implement the regulation of the grid structure of the power grid; the process of the digital power system using an intelligent agent constructed based on the grid structure regulation operator includes:

[0050] Get the current system inertia corresponding to the current grid structure;

[0051] Calculating a frequency change rate based on the current system inertia and a difference between a power demand and an actual power supply;

[0052] If the frequency change rate is greater than a preset first threshold, a target grid structure and a target constant value corresponding to the target grid structure are determined based on a pre-established deep learning model; the frequency change rate of the target grid structure is less than or equal to the first threshold;

[0053] The current set values ​​applied in the current grid structure are modified based on the target set values, and the current grid structure of the power grid is adjusted to the target grid structure.

[0054] It can be seen from the above technical solutions that the embodiments of the present application have the following advantages:

[0055] In the technical solution of the present application, characteristic production factor data corresponding to the characteristic production factor group and control production factor data corresponding to the control production factor group are extracted from the power data on the power plant side and the power grid side. Thus, the coordination of characteristic production factors on the power plant side and control production factors on the power grid side is realized. On the basis of the extracted relevant production factor data, in order to construct an intelligent body with specific power functions, artificial intelligence technology is further used, and sufficient preparations are made for the use of this technology: based on the power function requirements of the digital power system, the extracted characteristic production factor data is used to construct the target data vector, and the key control production factor data associated with the power function requirements are determined from the extracted control production factor data. On the basis of the target data vector and the key control production factor data, the mapping function between the target data vector and the key control production factor data is learned by using the artificial intelligence algorithm, a functional operator with the mapping function as the core is constructed, and an intelligent body is constructed based on the functional operator. Intelligent bodies corresponding to various different power function requirements are added to the digital power system, and each intelligent body is used as a power function realization unit in the digital power system. Thus, the digital power system has intelligent bodies with diversified functions, and the system can realize diversified and digital power functions based on data drive.

[0056] In the technical solution of the present application, since the construction of the intelligent body depends on the relevant production factor data on the power plant side and the power grid side, and the characteristic production factor group includes characteristic production factors of multiple levels, and the control production factor group includes control production factors of multiple aspects, it is equivalent to realizing the coordination of characteristic production factors of multiple levels and control production factors of multiple aspects. The intelligent body constructed based on this effectively utilizes the diversified information of power data to realize the power function of coordinating multiple production factors, such as the power function for power trading between the power grid side and the power plant side, the power function for realizing the dispatching control of the power grid side on the power plant side, and the power function for the power grid to regulate itself. The intelligent body can more accurately capture the connection between data and data, and then obtain more accurate and transferable data analysis results or data calculation results. It can also be understood that the digital power system constructed by this solution forms high-value data assets in the power system and enhances the analytical value of power data. The constructed digital power system can effectively contribute to the domestic power market reform and global power trading. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0058] Figure 1A An example flowchart for building an intelligent agent based on data in this application;

[0059] Figure 1B A schematic diagram of constructing an operator through deep learning and reinforcement learning provided in an embodiment of the present application;

[0060] Figure 1C A structural diagram of data in the construction of a digital power system provided in an embodiment of the present application;

[0061] Figure 1D A diagram of an implementation architecture of digital power association provided in an embodiment of the present application;

[0062] Figure 1E A flowchart of a method for constructing a digital power system based on a multifunctional intelligent agent provided in an embodiment of the present application;

[0063] Figure 1F A schematic diagram of a power supply scenario provided in an embodiment of the present application;

[0064] Figure 1G A schematic diagram of a production factor division architecture provided in an embodiment of the present application;

[0065] Figure 1H A schematic diagram of the relationship between an agent, an operator, a function, and production factor data provided in an embodiment of the present application;

[0066] Fig. 1I A flowchart for implementing a power analysis intelligent entity provided in an embodiment of the present application;

[0067] Figure 1J A schematic diagram of the relationship between another agent, operator, function, and production factor data provided in an embodiment of the present application;

[0068] Figure 2A It is the grid side flow chart based on the electricity price operator;

[0069] Figure 2B It is the flow chart of the power plant side based on the electricity price operator;

[0070] Figure 2C It is the signaling diagram between the power plant side, the grid side and the intelligent agent;

[0071] Figure 3A A schematic diagram of a flow chart of a power grid clearing method provided in an embodiment of the present application;

[0072] Figure 3B A signaling interaction diagram of a power grid clearing method provided in an embodiment of the present application;

[0073] Figure 3C A schematic diagram of a flow chart of another power grid clearing method provided in an embodiment of the present application;

[0074] Figure 3D A schematic diagram of a long-term transaction stack provided in an embodiment of the present application;

[0075] Figure 3E A flowchart of another power grid clearing method provided in an embodiment of the present application;

[0076] Figure 3F A parameter diagram showing the thermal performance of a unit under full load conditions provided in an embodiment of the present application;

[0077] Figure 3G A schematic diagram of comprehensive consideration parameters for coal price and long-term transaction electricity price provided in an embodiment of the present application;

[0078] Figure 3H A schematic diagram of a stack structure of a spot transaction stack and a long-term transaction stack provided in an embodiment of the present application;

[0079] Fig. 3I A flowchart of a method for establishing a spot trading stack provided in an embodiment of the present application;

[0080] Figure 4A A schematic diagram of power prediction based on a wind power plant provided in an embodiment of the present application;

[0081] Figure 4B A schematic diagram of a spot transaction stack provided in an embodiment of the present application;

[0082] Figure 4C A schematic diagram of a curve of a power grid clearing function provided in an embodiment of the present application;

[0083] Figure 4D A flowchart of another power grid clearing method provided in an embodiment of the present application;

[0084] Figure 4E A flow chart of a first clearing function adjustment method when a target power grid is in an over-generation state provided in an embodiment of the present application;

[0085] Figure 4F A schematic diagram of calculating a second data vector through a deep learning model provided in an embodiment of the present application;

[0086] Figure 4G A flow chart of a first clearing function adjustment method when a target power grid is in an under-generation state provided in an embodiment of the present application;

[0087] Figure 4H A schematic diagram of a target power grid fitting power generation curve provided in an embodiment of the present application;

[0088] Figure 5A A schematic diagram of a power supply scenario provided in an embodiment of the present application;

[0089] Figure 5B A flow chart of a peak load scheduling method in a thermal power high frequency variable load scenario provided in an embodiment of the present application;

[0090] Figure 5C A signaling interaction diagram of a peak load scheduling method in a thermal power high frequency variable load scenario provided in an embodiment of the present application;

[0091] Figure 5D A flowchart for determining a target unit for expected auxiliary peak load regulation provided in an embodiment of the present application;

[0092] Figure 5E A flowchart of a fault judgment and working condition judgment provided in an embodiment of the present application;

[0093] Fig. 5F A flowchart of another peak load scheduling method in a thermal power high frequency variable load scenario provided in an embodiment of the present application;

[0094] Fig. 6AA flow chart of a water resource scheduling method provided in an embodiment of the present application;

[0095] Figure 6B A schematic diagram of the historical water consumption for power generation in each month of an upstream hydropower station provided in an embodiment of the present application;

[0096] Figure 6C A schematic diagram of the historical water consumption for power generation in each month of a downstream hydropower station provided in an embodiment of the present application;

[0097] Fig.6D A schematic diagram of the historical power plant revenue corresponding to each month of an upstream hydropower station provided in an embodiment of the present application;

[0098] Fig. 6E A schematic diagram of the historical power plant revenue corresponding to each month of a downstream hydropower station provided in an embodiment of the present application;

[0099] Fig. 6F A schematic diagram of water assets corresponding to each month of an upstream hydropower station provided in an embodiment of the present application;

[0100] Figure 6G A schematic diagram of water assets corresponding to each month of a downstream hydropower station provided in an embodiment of the present application;

[0101] Figure 6H A schematic diagram of a water resource regulation scheme for a cascade hydropower station provided in an embodiment of the present application;

[0102] Fig.6I A schematic diagram of the interaction between a power plant and a power grid provided in an embodiment of the present application;

[0103] Figure 6J A flow chart of another water resource scheduling method provided in an embodiment of the present application;

[0104] Fig. 7A A schematic diagram of an application scenario of a power grid dispatching method in a large-machine small-grid power system provided in an embodiment of the present application;

[0105] Figure 7B An exemplary flow chart of a method for dispatching electric power in a large-scale power system with a small grid provided in an embodiment of the present application;

[0106] Figure 7C A schematic diagram of a multi-round voltage adjustment provided in an embodiment of the present application;

[0107] Fig.7D A schematic diagram of a frequency multi-round adjustment provided in an embodiment of the present application;

[0108] Fig. 7E Another exemplary flow chart of the power dispatching method in the large-machine small-grid power system provided in the embodiment of the present application;

[0109] Figure 7F A power dispatch signaling diagram in a large-machine and small-grid power system provided in an embodiment of the present application;

[0110] Fig. 8A A flow chart of a method for adjusting a power grid structure provided in an embodiment of the present application;

[0111] Figure 8B A flow chart of another method for adjusting the grid structure of a power grid provided in an embodiment of the present application;

[0112] Figure 8C A flow chart of a method for determining a target grid structure in the case of a sudden change in power generation provided in an embodiment of the present application;

[0113] Fig.8D A schematic diagram of a binary tree structure provided in an embodiment of the present application;

[0114] Fig. 9 An interactive diagram of a power generation dispatching process of a power system provided in an embodiment of the present application;

[0115] Fig.10 A schematic diagram of the relationship between a function and an operator provided in an embodiment of the present application. DETAILED DESCRIPTION

[0116] At present, international cooperation in electric power and energy is becoming increasingly extensive. It is the key demand facing the current power industry to build digital artificial intelligence technology that drives power intelligent entities with digital technology, promote the unified construction of the global power trading market, and formulate top-level design rules to guide the marketization process. Based on the practical experience in the power industry at home and abroad, the inventor proposed a digital power system construction plan based on multiple intelligent agents. Based on the cost-effectiveness demands of the entire industry chain under the new global power market, and the digital characteristics of the production factor data contained in the power system, these complex factors (coal consumption, light, wind speed, electricity price mechanism, investment cost, etc.) are converted into data or advanced data vectors to promote cross-industry information flow and efficient utilization, and give data new life with the help of AI technology.

[0117] In this application, the inventor integrates forward-looking thinking, faces the technical and industrial challenges of the entire industrial chain, emphasizes the integration of technology and economy, the digitization of the value chain, and the advancement of marketization and intelligence, aiming to provide intelligent and automated solutions to power problems in the energy industry. Combined with emerging fields such as new power and intelligent hydropower business, the construction method and device of a digital power system based on a multifunctional intelligent body provided by the technical solution of this application can serve the global energy Internet and form digital assets. From the essence of artificial intelligence, transforming data into digital assets requires both the data itself and the most profound and essential understanding of the operation mode of the power industry. With the deepening of the reform of the power market, the innovation of various technologies and mechanisms has become the key to promoting reform. Construct an underlying design framework for the deep integration of digitalization and artificial intelligence, based on data-driven digital power, algorithms based on digital power, and intelligent bodies based on power systems, especially in key links such as dispatching, settlement and pricing, from different dimensions, abstract the low-order, mid-order, and high-order features of data to achieve a double leap in efficiency and intelligence. The technical conception of the technical solution of this application can promote the transformation and application of related technologies, thereby accelerating the process of power market reform.

[0118] The following is an introduction to some of the inventive concepts involved in the technical solution of this application:

[0119] Symbiosis: From the data level, after a class of comparable transactions are digitized, they have certain properties of association and connectivity under a certain abstraction. Symbiosis integrates the production factors of nature or the information of production and control of production factors into the data, making it possible to associate and transmit data. Symbiosis also enables data feature abstractions to exist in different operators or agents, different operators and agents can exist at the same time, and characteristics also exist in multiple operators and agents. In essence, different types of transactions may have the characteristics of being scattered in form but similar in spirit. Finding the essence and connotation of symbiosis means finding the same properties. In the technical solution of this application, the inventor uses symbiosis to integrate the concepts in the neural network into the power system based on his own accumulated knowledge of the power system, thereby realizing the ingenious application of artificial intelligence technology in the power field.

[0120] Migration: Transferring the characteristics of one type of transaction to the characteristics of another related type of transaction, so that the relationship is generated and the two types of transactions can be interchanged at the data asset level. The migration function is realized by nesting and calling of intelligent agents, so that multifunctional intelligent agents do not need too many iterations, and operators are used to implement specific functions. Using migration, most functions in the power system can be brought from one intelligent agent to another.

[0121] Emergence: When the data scale is large enough and there are enough logics in the intelligent body, the data and logic can be regenerated and iterated with each other, which is the dividing line between intelligence and wisdom. When artificial intelligence develops to the emergence stage, wisdom will be generated. Recalling that humans use tools to change productivity, tools are means of production. First in ancient times, and then continuously expand the scale of input data, in order to continuously promote the development of productivity, production tools were invented, and then summarized and abstracted laws through mathematics, physics, chemistry and other disciplines, and finally obtained logic and formula theorems; in modern society, the development of informatics has changed the carrier of the third industrial revolution of mankind, and produced electricity, computers, etc., which are also tools for iterative information of informatics, but in the fourth industrial revolution, artificial intelligence is fundamentally upgraded from simple to complex computers, etc., using neural networks and statistical principles to approach the production function again, so that the road is simply driven directly from data. In the next 10 years, the development of intelligent entities and internal logic is equivalent to the development of production tools in the previous society. Human understanding always deepens and deepens step by step. Many phenomena that cannot be explained have internal connections and deeper theorems and concepts, but high-level abstractions of data exist and are easier to obtain. The key is to analyze the relevant logic within the intelligent body, which is a natural process and more like waiting for a certain opportunity.

[0122] Agent: An agent is a unit with certain or multiple functions. It makes the power system and artificial intelligence more closely integrated. The agent protects the power system and the outside world, which is equivalent to a cell, but has smaller kinetic units such as operators inside. The agent has special data characteristics in different scenarios, which has a deeper meaning for generating emergent functions and studying the digital nature of the power system. The agent is a core component of artificial intelligence in the power industry, which is equivalent to the thermal control logic diagram or relay protection involving logic in the power industry in the third industrial revolution. For example, the logic inside the "five protections" of the switch station can be symbolically represented. The logic inside the agent can also be symbolically represented, which is used to more accurately and deterministically represent the key logic and control in the power system based on big data and big models. The general logic of the intelligent agent conforms to the key theorems and common sense in the power system, and conforms to the energy conversion company and related rules. Its research objects are production characteristic factors and control production factors, such as illuminance, wind speed, water level, heat consumption, load rate, system inertia, frequency, etc. The interface of the intelligent agent is directly connected to the input layer or output layer (output function) of deep learning and reinforcement learning, and is also connected to the intermediate layer when necessary. In the technical solution of this application, the first half of the neural network is the data transmitted after the natural production factors are abstracted and calibrated, which enhances the parallel computing and fast capabilities. The operator functions and intelligent agents in the output of the second half reflect the ability of mathematical abstraction and the physical laws in the industry, and can be combined and reconstructed, so that the intelligent agent has the capabilities and functions of thousands of industries.

[0123] In the technical solution of this application, the whole article starts with the data and information flow to build an algorithm. After the data features are extracted, the data needs to be calibrated, that is, to give the data a reasonable data structure. At the same time, the inherent logic of the operator controls the flow of information. The different data structures and information flows corresponding to the digitization of power plants and power grids are also presented through different embodiments. It is better to use different neural networks as algorithms. For the operators involved, there are differences in data structure and information flow methods. For example, the power grid is suitable for using binary trees for power grid decoupling and grid connection, and stacks for clearing electricity prices, while the power plant is suitable for gradually establishing information flow methods and inherent safety logic from the first-level indicators of nature. Combined with the applicable objects, the conditions and direction of information flow are determined, which also determines the selection of convolutional neural networks, recurrent neural networks, graph neural networks, attention networks, etc. The following is a discussion of related issues: I. Digital feature extraction, II. Mathematical tools, III. Binary trees and stacks in data structures, IV. Logical core, V. Reasoning ability and information classification under the underlying logic.

[0124] I. Digital Feature Extraction

[0125] Digital features, digital features are divided into power plant and power grid digital features. Establish power grid characteristic variables, such as the real part of each node voltage, the imaginary part of the voltage, the active power flowing into each node, the reactive power flowing into each node, the system inertia, the system frequency, the ratio of the system power change rate to the system frequency change rate, etc. Establish power plant characteristic variables, such as generator power angle, each generator voltage, each generator electromagnetic power, each generator reactive power, etc. According to the above-mentioned production factor digital features from the primary characteristic production factors in nature, such as illumination, coal type and quality, and water level, first extract the digital features of each layer, such as extracting the digital features of low-order characteristic production factors on the power plant side, such as the seasonal volatility of water level and the efficiency stability of illumination, and extracting the digital features of high-order control production factors on the power grid side, such as extracting the system inertia to frequency change rate characteristics, and the frequency change rate to power change rate characteristics. The means adopted are also different. For the digital features of low-order production factors such as water level, photovoltaic light intensity, etc., clustering or Euclidean distance method can be used to extract digital features, while the digital features of high-order control production factors require modeling or more advanced mathematical tools to extract digital features.

[0126] II. Mathematical Tools

[0127] Mathematical tools can adopt one of the convolutional neural network, recurrent neural network, graph neural network or attention network according to the data and information flow characteristics of the object. The characteristics of the above various neural networks are as follows: 1. Convolutional neural network: regular network data, information flows to local areas; 2. Recurrent neural network: data is input in order, and information flows in sequence; 3. Graph neural network: data is in a fixed graph structure, and information flows along fixed edges; 4. Attention network: data is in an unordered set, and information flow is dynamically controlled by the neural network. These neural networks target the logical core: operators, agents. Corresponding to the process of constructing a digital power system in the multifunctional agent (operator), the typical cases are: grid connection and decoupling operators (Example 6 below), hydropower seasonal scheduling operators (Example 4 below), large machine and small network power supply and grid control operators (Example 5 below), clearing function operators (Example 2 below), etc. The data research and information flow characteristics in these operators all deeply reflect the above-mentioned neural network characteristics. From data feature extraction to the rules of information sequence flow (physical and equipment mechanisms), we analyze data characteristics and information characteristics respectively, and select suitable neural networks for each, so that the artificial intelligence algorithm is highly compatible with the power system.

[0128] When using mathematical tools, we can combine the data scale and sample size to determine the mathematical tools. Figure 1A Introduce the example process of building an intelligent agent based on data in this application. Figure 1A As shown, the process includes:

[0129] (1) Data collection and input.

[0130] (2) Determine the data scale, small sample or large sample. If the sample is large, skip step (3). If the sample is small, execute it directly.

[0131] (3) Data fitting: using mathematical tools or formulas to regress the data to a certain convergence value.

[0132] (4) Data cleaning: delete or process abnormal data based on the fitted data.

[0133] (5) Extract data features to confirm whether they are production factor features or control production factor features.

[0134] (6) Intelligent agent construction: By understanding the internal logic of the power industry, key processes or constraints are written. For the constructed intelligent agent, deep learning and reinforcement learning interfaces are laid out to receive data extracted from data features, and further deep learning or reinforcement learning is performed based on its characteristics and classification.

[0135] (7) Use the results of deep learning or reinforcement learning to create an output layer output function, perform a backpropagation algorithm on the function, and fine-tune and correct the intermediate results of each layer.

[0136] (8) Generalize the output function into control logic, bring it into the intelligent agent, and embed the intelligent agent and its key internal data elements into the actuator control logic to achieve data-driven.

[0137] Deep learning and reinforcement learning make the transmission of information after compression more representative and error-correcting. Deep learning has a specific algorithm or logic for extracting data features, which makes the data features more regular in subsequent extraction, and facilitates the use of data characteristics to establish a super-high-level mechanism or data structure based on data cleaning; in the process of data transmission, the information loss of data is kept low, while ensuring the speed of data calculation and transmission. In reinforcement learning, through mechanisms such as rewards, the correctness of the learned logic is constantly verified, and the priority is determined, so that the logic can be generated in constant comparison and calibration.

[0138] Combined with the process introduced above, in the technical solution of the present application, digitization is not a single digitization method or the use of a single mathematical tool. There are differences under large and small samples. For the digitization of large sample data, it is necessary to adopt deep learning methods (such as the use of convolutional neural networks, etc.), compare the measured data with the sample, form a workflow, and repeatedly deduce and reverse according to the logical flow in the intelligent agent to simulate human reasoning. The convolution algorithm can obtain features through deep learning and give them to the operator function. The convolutional neural network adopts an "end-to-end" approach and can automatically identify data features. It has the functions of power sharing, layered abstract data low-cost, mid-order, and high-order data features. Small samples directly extract data features from the data.

[0139] The concept of intelligent agents is suitable for research objects with small samples. When to use large models (corresponding to large samples) and when to use small samples in power systems depends on the characteristics of the data. At present, weather forecasts involve more data and are suitable for large models. Large models are also suitable for dispatching, grid connection and decoupling. Because the amount of data is large, the research on intelligent agents, especially the innovation of operator logic design in power systems for deep learning and reinforcement learning, is suitable. Because computing power involves advanced processes, GPUs, HBMs, and data transmission rates and network throughput are limited, the logic in uncertain intelligent agents must adapt to GPU high-speed computing very quickly. Therefore, the type of neural network selected by the algorithm must adapt to the characteristics of data and logical information flow, and capture logical and digital certainty in the changes of uncertain natural production factors. In the stage from artificial intelligence to AGI\ASI, the application of intelligent agents makes small sample data more advantageous than large samples.

[0140] For small sample data, binary trees and stacks can currently be used as data structures to encapsulate data features.

[0141] III. Binary tree and stack in data structure

[0142] The encapsulation of data features uses binary trees or stacks so that data features can be more accurately reflected or easily shared.

[0143] In the embodiments described below, Example 2 shows an example of using a stack as a data structure. After the production factors are abstracted, the above data structure is put in to obtain the implementation of its parallel computing and intelligent agent logic. Example 2 shows a stack method that gradually decreases from bottom to top according to priority. The stack's first-in-last-out structure and sequential characteristics conform to the clearing logic of the power grid, and can also achieve dynamic orderliness of data. For operations such as electricity price clearing that target high-order production factors, if high-speed calibration data parallel computing is required, multiple stacks or hierarchical processing are required. It increases the pressure on parallel computing, but reduces the time for logical judgment. It is a typical case of data-driven.

[0144] The sixth embodiment shows an example of using a binary tree as a data structure. With the help of data structures with inherent characteristics, such as a binary tree, grid decoupling and grid connection can be achieved. Practical data tools are not limited to functions, but also include graph theory, etc.

[0145] IV. Logical Core

[0146] The association of three major groups, two major production factors, and four data structures is constructed. Through the above related content of the logical core, the logical core associates the production factors, operators, and intelligent agents, so that after the data is cleaned and calibrated, the data characteristics representing the production factors enter the operator to achieve specific functions, such as electricity price, clearing, frequency, etc., so that the intelligent agent containing its operator also obtains such multiple functions, so that symbiosis and migration can be realized. In addition, the underlying logic of data drive and operators and the subsequent reasoning process of intelligent agents are realized, so that emergence can be realized.

[0147] 1. Structured and systematic logic:

[0148] 1. Construct a characteristic production factor group centered on the power plant side, which includes 1-3 level indicators, namely natural indicators, single system indicators, and plant system indicators. The internal calculation is the parallel calculation of data vectors, because the parallel calculation speed of data vectors is high enough, and only the characteristics of 1-3 level indicators need to be extracted, so that the data reflects the characteristics of each part, transmits the characteristics, and performs simple analysis and statistics. You can refer to Figure 1D The right part of the architecture diagram of a digital power association implementation is shown.

[0149] 2. Construct a control production factor group centered on the power grid, which includes important indicators of the power grid, namely electricity price, inertia and frequency, active and reactive power, carbon, safety and stability, network combination decoupling, etc. Figure 1D The left part of the implementation architecture diagram of a digital power association is shown in the figure. The underlying data logic is a function. Through the data vector, according to the system law in the intelligent body, the function of data vector mapping is summarized through reinforcement learning. The important laws inside the power grid are expressed through function calculation. For example, through the system inertia calculation, the frequency change rate is obtained, so as to call the intelligent body interface for the control production factor of the power grid, and the intelligent body is processed under reinforcement learning to make the power grid balanced and stable. Other things such as electricity prices are also based on the principle of digital power association. Various types of data vectors are mapped to the functions on the power grid side. Through reinforcement learning, the function is continuously iterated to obtain the optimal solution for the control production factor on the power grid side.

[0150] 3. Construct a multifunctional intelligent agent, as shown in Examples 1 to 6. The intelligent agent is a key logic body that combines artificial intelligence and electricity to realize specific functions.

[0151] 2. Data and Functionalization

[0152] 4. The abstract characteristics of the data reflect the primary indicators and indicators in nature. These indicators need to be abstracted with mathematical tools, and then digitized, normalized, and abstracted under the condition that signal loss is allowed. Then, using the characteristics of parallel computing, the data of the transmission layer is iterated, and finally in the output layer, it is functionalized, and the rules and constraints and other relevant rules of nature or industry are reflected by the intelligent agent. The operator is used as a function to implement the characteristic function, and the operator here is nested in the intelligent agent. It has certain functions, and these functions are symbiotic with the intelligent agent. The combination and division of the intelligent agent is equivalent to the combination and division of cells. In this process, the operator is equivalent to protein. Its different combinations and reconstructions make the protein have certain functions, and the data of the transmission layer transmits protein information or nutrients. It is the data that is transformed into operators through functional generalization, and these data come from the characteristic abstraction of production factors. Such as Figure 1B , which is a schematic diagram of constructing an operator through deep learning and reinforcement learning provided in an embodiment of the present application.

[0153] Nature and the second machine revolution have established the above-mentioned connection based on neural networks and data annotation. This structure and interface, under the self-attention mechanism, enables probabilistic methods to improve the hit rate of artificial intelligence. In addition, the emergence of GPU parallel computing power requires mathematical abstraction, namely the design of operators, and the development of intelligent agents in the power industry or thousands of industries. The characteristic production factor is the characteristic carrier of various abstract indicators. The relevant power plant network indicators are digitized into data vectors to represent their characteristics. After heavy feature extraction, the data is sent to the operator.

[0154] 5. The digital vector in the data structure is the key to reflecting the power index quantity on the power plant side. For example, the measurement of the impact of fog on production starts from the data vectors of each power plant (number of foggy days, foggy impact on power, etc.), and then re-automatically extracts features and their associations through deep learning of the intelligent agent interface. Similarly, there are queue sorting priority for thermal power to participate in the scheduling of variable load peak regulation, stack-pointer-electricity price and other data structure applications, which are reflected in the priority and real-time scheduling method of electricity price.

[0155] 6. The concept of operator function: The function in the data structure reflects the electricity price, active and reactive power, inertia and frequency, electric carbon, safety and stability, and network combination decoupling. It is embodied by the operator, and the parallel computing function unit that realizes a specific function in a certain power system in the intelligent body, such as electricity price, system inertia, and frequency. As long as it is a function, it can exist in the form of an operator. For example, the fitting curve function maps and summarizes the function according to the data vector, and then strengthens the learning of the heavy logic function association through the intelligent body interface.

[0156] After extracting data features, the data is packaged with the above tools to form a new logical core as an operator. Multiple operators form an intelligent agent, and multiple intelligent agents constitute a digital power system. In this operator, the rules for the logical formation of information flow caused by the application of logical relationships driven by data features to the physical and equipment mechanisms (plant network control and equipment) in the power system are detailed in the flowcharts, signaling diagrams, etc. involved in the following embodiments.

[0157] According to the three operators' power generation control, clearing, and internal control logic, the association is established. Inspired by the feature extraction article, the high-dimensional data vector comparison is used to realize the data comparison between the power grid and the power plant side, and the optimal feature with large correlation weight is found. The association in the operator and the "source-grid" matching degree are fully reflected as the underlying logic and algorithm for safety considerations.

[0158] The three operators, namely the power generation control operator, the clearing operator and the internal control logic operator, provide functional descriptions from the aspects of power generation mechanism on the power supply side, grid clearing principle and logic, and safety considerations. They describe their respective technical solutions, which conform to the creative characteristics of the invention. At the same time, they also creatively propose the relationship between the three operators, leading to deeper topics on the construction of digital power systems by multiple intelligent agents, such as studying their symbiosis and migration, until more intelligent agents emerge to produce emergence.

[0159] The method of constructing a digital power system with multiple agents essentially provides many operations on data and information flows, including feature extraction, comparison and matching study of data. The information in the information flow controls the flow according to the mechanism and constructs agents to realize the many functions of the digital power system. The key lies in constructing appropriate operators in the agent to enable the construction of indicators such as "matching degree" to measure the various physical mechanisms of the power grid and power plant.

[0160] The operator reflects the production factors of the power grid and belongs to the power grid. For example, in the functional operator, the electricity price operator, such as the electricity price function, the balance point of the power grid electricity price, the internal control operator, and the operator corresponding to the electricity fee in the final function. According to the digital power plant composition of different types of units (including its power plant electricity price balance point), and combined with the actual clearing function of the power grid, the power grid electricity price operator is constructed, and the power grid electricity price balance point is established at the same time. The balance point is the operating point at which the power plant cost and the power grid clearing transaction price are balanced according to the power grid electricity price. Its significance lies in the key reference for the power grid to set electricity prices.

[0161] 3. Digitalization and Functionalization

[0162] The embodiment of digitalization and data-driven, multiple embodiments of the present application deeply involve digitalization, such as embodiment 4, its digitization is not a completely single digitization method, there are differences in large and small sample environments, for the digitization of large samples, it is necessary to adopt a deep learning method to compare the measured data with the sample, form a work flow, and repeatedly deduce and reverse according to the logical flow in the intelligent body to simulate human reasoning.

[0163] The data collected in Example 4 is a small sample. By studying the distribution of water levels, the seasonal cycles and regularities of upstream water levels are found. Only after digitizing them and finding the regularities can the seasonal adjustment scheduling be implemented in the scheduling strategy, so that the higher-order data power generation income, unit power generation water consumption, and water assets can be maximized. Only by finding the association between data and the main factors in the association, and analyzing the internal logic in the market and environment, can the most core key data be found in the data drive to adapt to the relevance and criticality of each item in the data vector selected by the data drive. In addition, other similar low- and medium-order data of water levels can be found, and this abstraction of data features can be used to create a data-driven method.

[0164] Another example is the second embodiment. In this scheme, for units of various power types, their impact on the power and frequency of the power grid is given by the ratio K of the high-order power difference to the frequency difference. The curve is derived from the quotation and power provided by the initial power point and the physical characteristics of its power type. At the same time, the power curve needs to be further fitted by a power source such as photovoltaics. The data fitting involves a large amount of real-time data. According to the degree of fitting, the next step of the process is selected under data drive. If the fitting is not good, it is necessary to adjust the output power of other units, and even adjust the K value of the entire power grid for the safety of the power grid, so that the K value or the power output value of each power source can be dynamically adjusted and find a balance point under the stable frequency regulation. These are all interacting with each other in the intelligent body. The bottom layer is the association of data and the data drive after abstraction. It is the method of parallel operation that enables this coordination to respond quickly and achieve flexibility that human judgment cannot achieve. The abstract data law replaces the back-and-forth process of human beings abstracting with mathematical formulas and then approaching the function result, which simplifies the process of discovering the law of things. Digitally transmitting laws and information directly to subsequent calculations ensures the accuracy and speed of information.

[0165] Figure 1C The structural diagram of data in the construction of the digital power system provided in the embodiment of the present application focuses on the data aspect. Figure 1C As shown in the figure, from data elements, data vectors, data functionalization to electricity prices, and finally to scheduling algorithms, it directly affects the digitization of the entire industry chain. The connotation of the digital power system revolves around data, whether it starts from the data vector of the digitization of production factors, to the normalization of production factors, to the electricity prices and scheduling strategies after the operation, all of which reflect the underlying logic of the data.

[0166] Quantization of safety data is discussed in Example 4, hydropower cascade scheduling; digitization of protection settings is discussed in Example 6, grid structure change; digitization of production factors is discussed below, reflecting the digitization and coordination of multiple production factors; quantization of other data is discussed in Example 3; scheduling algorithms are discussed in Example 2, clearing function, Example 4, hydropower scheduling, and Example 5; artificial intelligence processing of complex scheduling is discussed in Example 6, Example 4, and Example 5; normalization of production factors is discussed in Example 2; digital functionization of production and settlement is discussed in Example 3, Example 2, and Example 4; electricity price and scheduling functionization is discussed in Example 2 and Example 3; digitization of the entire industrial chain is discussed in Example 1.

[0167] V. Reasoning Ability and Classification of Information Underlying Logic

[0168] The production factors on the grid side highlight the internal connection of coordination, and the specific production factors on the power plant side are controlled by incorporating the digital logic of high-level control production factors such as hydropower (inertia control) and photovoltaics (active and reactive power control).

[0169] In the first embodiment, the production factors of the power plant and the power grid are written to highlight the internal connection of coordination. The essence lies in establishing the control of computing power in different functions, such as the computing power group of active and reactive power functions, the operator group of the power grid inertia function, the computing power group of the power grid load and electricity price function, the computing power group of the power grid security and stability, and the computing power group of the power grid carbon footprint. Each computing power cluster has a direct high-speed data connection, and can also be nested and called with each other, so that the blockchain is decentralized and decentralized. These computing power groups are all driven by data in the previous production or control of production factors. This constitutes the digitization of the operator function in the intelligent body, which is the core of digital power.

[0170] Taking computing power cluster as the starting point of digital power means deeply considering and grasping digital power. Professionally, by calculating and measuring the computing power of power and the digital world, we can establish a thinking ability similar to 0PENAIO1. It is the intelligent body that establishes a collaborative relationship of function mapping between the power grid and the power plant side, and establishes an associated data vector relationship in the data. Only in this way can we widely associate vectors with functions, groups (production factors and characteristics) with intelligent bodies (electricity prices, active and reactive power, inertia, safety, and electricity carbon footprint).

[0171] Figure 1D An implementation architecture diagram of a digital power-related system is provided for an embodiment of the present application. The digital power system of the multifunctional intelligent body in this solution is also constructed according to the concept of the implementation architecture diagram.

[0172] The following is a detailed description of the construction method of a digital power system based on a multifunctional intelligent agent and the implementation of related devices in the technical solution of the present application through the accompanying drawings and embodiments. Figure 1E A flowchart of a method for constructing a digital power system based on a multifunctional intelligent agent is provided in an embodiment of the present application. Figure 1E As shown, the method includes:

[0173] S101. Extract characteristic production factor data corresponding to characteristic production factor groups from power data on the power plant side; and extract control production factor data corresponding to control production factor groups from power data on the power grid side.

[0174] At present, the analysis of power data in the power system is generally isolated. For example, when analyzing a certain indicator, only a very small number of data directly related to the indicator are considered, so the influence of some other factors is also ignored, resulting in insufficient accuracy of the power analysis results, or the content is too single and the value of the analysis results is low. In this case, it is easy to cause ineffective waste of power resources. In order to build a digital power system based on multiple agents, this application proposes to coordinate the data characteristics of the power plant side with the data characteristics of the power grid side. Specifically, the characteristic production factor data on the power plant side and the control production factor data on the power grid side are coordinated, and a functional operator of a mapping function containing the relationship between the two is constructed based on this, and an agent is built accordingly, see S102~S103 for details. This concept solves the problem that the existing analysis is not comprehensive and the data considered is too single, and can more accurately and sensitively capture the connection between data and data in the power system, and form data assets to meet the diverse power function requirements. Thereby, it can assist relevant personnel to dispatch and control in the power system more efficiently and maximize the effectiveness of the digital power system.

[0175] Figure 1F A schematic diagram of a power supply scenario provided in an embodiment of the present application. Figure 1F As shown, in actual applications, various types of power plants may communicate with the grid side and transmit power. These different types of power plants can be collectively referred to as the power plant side. In the embodiment of the present application, the power plant side can report its own data to the grid side and give timely feedback; the grid side can dispatch the power plant side, such as peak load regulation, frequency regulation, etc. Based on the influence of various factors such as power generation cost, performance of generator sets, uncertainty of power generation of different types of power plants, and changes in load demand, the power plant side often needs to reach a "consensus" with the grid side and perform corresponding actions according to the instructions of the grid side. Taking a thermal power plant as an example, the thermal power plant can further increase the heat stored in the thermal power plant or further release the heat stored in the thermal power plant according to the instructions of the grid side; or the thermal power plant can adjust the following mode of the motor-machine-furnace according to the requirements of the load. Taking a wind power plant as an example, the fan can add or subtract load according to the instructions of the grid side, adjust the chamfer of the fan, etc. Taking a photovoltaic power plant as an example, the angle of the thyristor can be controlled according to the dispatching instructions of the grid side to the load, thereby changing the power generation. Taking a hydropower plant as an example, the water volume and water cost can be calculated based on the dispatch curve on the grid side, thereby controlling the turbine power generation. Figure 1FIt can be seen that in the actual power production process, the grid side and the power plant side need to be closely dispatched so as to achieve better and more stable power supply and maintain the cost demands of both parties. In combination with the above-mentioned practical needs, this application proposes a digital power system that coordinates multiple production factors to build a multifunctional intelligent body. The system has a relatively broad application prospect and has the potential to be used in power systems for a long time. Through the coordination and digital analysis of multiple production factors, it can improve the accuracy and reliability of power analysis in the current power system. Through the coordination of multiple production factors, the barriers between the power plant side and the grid side data are broken, and the connection between the data of multiple production factors is captured through artificial intelligence technology, so as to realize digital power analysis in the field of power systems in a more intelligent and automated way.

[0176] For ease of understanding, the following Figure 1G Introduce the production factor division structure in the technical solution of this application. Figure 1G A schematic diagram of a production factor division architecture provided for an embodiment of the present application. In the embodiment of the present application, the production factors are divided according to the power plant side and the power grid side. The basis for dividing the production factors on the power plant side is called the characteristic production factor group; the basis for dividing the production factors on the power grid side is called the control production factor group.

[0177] In the embodiment of the present application, the characteristic production factor group includes characteristic production factors of multiple levels. Specifically, these characteristic production factors can be subdivided into: primary characteristic production factors, secondary characteristic production factors and tertiary characteristic production factors. Among them, the primary characteristic production factors are natural characteristic production factors (or called: natural indicators), which are production factors that can directly reflect natural characteristics. The secondary characteristic production factors are single-system characteristic production factors (or called: single-system indicators), which are production factors involving monomer systems in the power system. The tertiary characteristic production factors are plant system characteristic production factors (or called: plant system indicators), which are production factors involving the overall system in the power system.

[0178] Combination Figure 1F As shown, there are various types of power plants, such as thermal power plants, photovoltaic power plants, wind power plants, hydropower plants, etc., which use different power generation methods, and the natural resources used and the internal system structures are also different. In order to more accurately realize digital power analysis, in the technical solution of this application, for various types of power generation, the first-level characteristic production factors, second-level characteristic production factors and tertiary characteristic production factors can be subdivided. Therefore, for each type of power plant, the data of the characteristic production factors of the corresponding level can be subsequently extracted.

[0179] The following is an illustrative introduction to several primary characteristic production factors in combination with different types of power generation. Taking photovoltaic power generation as an example, the primary characteristic production factors may include: photovoltaic light illumination. Taking hydropower generation as an example, the primary characteristic production factors may include: precipitation (water inflow), etc. Taking thermal power generation as an example, the primary characteristic production factors may include: low calorific value of coal, coal consumption, heat consumption, etc. Taking wind power generation as an example, the primary characteristic production factors may include: wind speed, etc.

[0180] For thermal power plants, a single system can be a boiler system, an electrical system, etc. For hydropower plants, a single system can be a turbine system, a speed control system, a butterfly valve layer system, etc. For photovoltaic power plants, a single system can be a photovoltaic panel area, a substation area, etc. In addition, these different power plants also share a transmission and transformation system. Correspondingly, the secondary characteristic production factors can be furnace efficiency, turbine efficiency, and other production factors that reflect a single system. The tertiary characteristic production factors can be photovoltaic efficiency, hydropower efficiency, thermal power unit efficiency, power plant thermal efficiency (specific heat index), and other production factors that reflect the overall situation of multiple systems. From Figure 1G It can be seen that the mining level of data features is gradually deepened from the first-level characteristic production factors, the second-level characteristic production factors, and the third-level characteristic production factors. It can be seen that in the embodiment of the present application, relying on the division structure of the characteristic production factors in the characteristic production factor group, the data of natural characteristics, single system characteristics and plant system characteristics can be collaboratively extracted, and digital power analysis can be realized from the characteristics of multiple levels.

[0181] In the embodiment of the present application, the control production factor group includes multiple aspects of control production factors. Control production factors are production factors that reflect the performance of the power grid, which are composed of some key physical quantities in the power system. Control production factors help to provide an effective theoretical basis for power system control. In the embodiment of the present application, for example, the control production factors of the following six aspects may be included but are not limited to: (1) electricity price; (2) inertia and frequency; (3) active and reactive power; (4) carbon emission; (5) safety and stability; (6) grid connection and disconnection. It should be noted that the six aspects of control production factors in the above examples are only defined from a macro perspective. When implemented specifically, each aspect of the control production factor can be further subdivided or derived into more specific indicators. The control production factors are not limited in quantity and content here. In the embodiment of the present application, relying on the division structure of the control production factors in the control production factor group, data on multiple aspects such as electricity price, inertia and frequency, active and reactive power, carbon emission, safety and stability, and grid connection and disconnection can be extracted collaboratively, and digital power analysis can be realized from multiple aspects of power grid concern.

[0182] As mentioned above, the technical solution of this application pre-plans characteristic production factor groups and control production factor groups. Among them, the characteristic production factor group includes characteristic production factors of multiple levels, such as first-level characteristic production factors, second-level characteristic production factors and third-level characteristic production factors of various different power generation types. The control production factor group includes multiple aspects of control production factors, such as electricity price, inertia and frequency, active and reactive power, electric carbon emissions, safety and stability, and grid connection and disconnection. On the basis of the above-mentioned characteristic production factor group and control production factor group, in this step, the production factor data is extracted in combination with the power data on the power plant side and the grid side.

[0183] In an optional implementation, characteristic production factor data corresponding to the characteristic production factor group are extracted from the power data on the power plant side, including: extracting the first-level characteristic production factor data, the second-level characteristic production factor data and the third-level characteristic production factor data corresponding to thermal power generation from the power data of the thermal power plant; extracting the first-level characteristic production factor data, the second-level characteristic production factor data and the third-level characteristic production factor data corresponding to photovoltaic power generation from the power data of the photovoltaic power plant; extracting the first-level characteristic production factor data, the second-level characteristic production factor data and the third-level characteristic production factor data corresponding to hydropower generation from the power data of the hydropower plant; and extracting the first-level characteristic production factor data, the second-level characteristic production factor data and the third-level characteristic production factor data corresponding to wind power generation from the power data of the wind power plant.

[0184] In an optional implementation, control production factor data corresponding to the production factor group associated with control is extracted from the power data on the grid side to form a data vector to express a specific function, such as power system stability, including: extracting electricity price data, inertia and frequency data, power data, electricity carbon emission data, safety and stability index data and grid connection and disconnection impact data from the power data on the grid side.

[0185] As an example, the electricity price data may include electricity prices at different times and with different load demands.

[0186] Inertia and frequency data can include system inertia and frequency. The relationship between system inertia and frequency is an important aspect in power system stability analysis. System inertia usually refers to the rotational inertia of the generator sets in the power system, which reflects the system's resistance to frequency changes. The following are some key points that outline the connection between system inertia and frequency. Inertia support: When there is a large load change in the power system or the sudden addition or withdrawal of generator sets, the system inertia can slow down the change rate of the system frequency. This inertia support helps maintain the frequency stability of the power system. Frequency change rate: The size of the system inertia directly affects the frequency change rate. The larger the inertia, the smaller the rate of change of the system frequency for a given power imbalance. A smaller frequency change rate helps avoid underfrequency load shedding or other stability control measures triggered by too fast frequency changes.

[0187] Voltage and active and reactive power data can include power at different voltages, for example in the form of (voltage, active power, reactive power). In power systems, voltage and frequency have no direct relationship, but they are related to power (active and reactive, respectively), creating an indirect relationship. When reactive power is insufficient, voltage drops, and when reactive power is excessive, voltage rises; when active power is insufficient, frequency drops, and when active power is excessive, frequency rises.

[0188] Electricity carbon emissions data may include carbon footprint, such as the amount of carbon dioxide emitted per kilowatt-hour of electricity generated.

[0189] Safety and stability index data may include the mean time between failures (MTBF) of the power grid. MTBF is an important indicator for measuring the reliability of products (especially electronic products). It indicates the average working time between two adjacent failures of a product under specified conditions and within a specified time range.

[0190] The grid connection and disconnection image data may include the degree of influence of each network on other networks.

[0191] In specific implementation, after extracting the control production factor data, it can be further converted into a digital vector representation to facilitate network recognition, calculation and processing. The converted digital vector representation can contain data of one aspect of the control production factor, or data of multiple aspects of the control production factor. The dimension and data source of the digital vector representation can be set according to demand and are not limited here.

[0192] S102. Based on the power function requirements of the digital power system, a target data vector is constructed using the extracted characteristic production factor data, and key control production factor data associated with the power function requirements are determined from the extracted control production factor data.

[0193] In the embodiment of the present application, an intelligent body is constructed based on the power function requirements and in combination with the characteristic production factor data and control production factor data extracted in the previous step. It can be understood that multi-level and multi-faceted production factor data are extracted in the previous step, but some of these data may be highly related to the power function requirements, and these data are helpful to build an intelligent body with the ability to meet specific power function requirements. However, some of the extracted data may have a very weak correlation with the power function requirements, such as the power function requirements are related to the electricity price. At this time, the electric carbon emission data in the data is currently of little significance for the calculation and analysis of the electricity price. To this end, in order to avoid the negative and adverse effects of redundant and massive data on the construction of intelligent bodies, this application extracts and refines the massive data obtained, so as to facilitate the accurate capture of the connection between the data. With the future reinforcement learning data feature correlation, and the electric carbon emission data gradually under the data-driven strengthening trend, the convolutional neural network algorithm will automatically extract this data feature and include it in the electricity price operator, which also reflects the mechanism of future deduction and emergence capabilities.

[0194] In the embodiment of the present application, on the basis of the extracted characteristic production factor data, based on the specific demand reflected in the power function demand, and the connection between the specific demand and the characteristic production factor, one or more characteristic production factor data (as the target characteristic production factor) with a high correlation with the specific demand is further extracted from the extracted characteristic production factor data, and then a data vector is constructed. For ease of distinction, the data vector is referred to as the target data vector. When constructing the target data vector, the vector can be constructed based on certain construction rules. For example, the dimension of the vector and the level or name of the characteristic production factor corresponding to each dimension can be set in the construction rule.

[0195] Table 1 shows some characteristic production factor data extracted from the power data of thermal power plants. In Table 1, SHRW represents the weighted specific heat index, in kJ / (kW·h). Ea represents the power supply (or power generation), in kW·h. EP represents the power charge, in US dollars. SHRcc represents the specific heat index, in kJ / (kW·h). U represents the coal price, in USD / t. As an example, U = 69 US dollars / ton. E represents the unit power generation heat consumption rate, that is, the heat consumption of the unit per kilowatt-hour of electricity, in kcal / kWh. N represents the specific heat index, specifically the heat required per kilowatt-hour of electricity, in kcal / kWh, and AUX represents the plant power consumption rate. ECRm is the electricity charge per kilowatt-hour, in USD / (kW·h). ECRm represents the power charge ratio, that is, the coal cost per kilowatt-hour of electricity produced, in USD / (kW·h).

[0196] Table 1

[0197]

[0198] If the specific demand reflected in the power function demand is to calculate the electricity price, multiple target data vectors can be extracted based on the characteristic production factor data shown in Table 1. For example, each row of data in Table 1 is extracted to construct a target data vector with a structure of (operating condition, SHRW, ECRm, Ea, CERm, EP, actual coal consumption per kWh, actual coal cost per kWh, and overall coal cost). For example, the target data vector 1 constructed using the second row of data in Table 1 is (100%, 2138.4, 0.0293, 9267053600 0.0311, 287772056.8, 450.0942, 0.0311, 287802236), and the target data vector 2 constructed using the third row of data in Table 1 is (95%, 2152.69, 0.0295, 8803700920, 0.0311, 273383454, 453.5357, 0.0313, 275502693). And so on.

[0199] In addition, in the specific implementation, the corresponding relationship between the control production factors and the power function requirements can be pre-constructed. Then, according to the specific power function requirements, the corresponding control production factors can be timely and efficiently determined as key control production factors, and based on this, the key control production factor data associated with the power function requirements can be determined from the extracted massive control production factor data. For the extracted key control production factor data, similarly, it can also be converted into a digital vector representation.

[0200] S103. Based on the target data vector and the key control production factor data, use an artificial intelligence algorithm to learn and obtain a mapping function between the target data vector and the key control production factor data, construct a functional operator with the mapping function as the core, and construct an intelligent agent based on the functional operator.

[0201] Figure 1H A schematic diagram of the relationship between an agent, an operator, a function, and production factor data provided in an embodiment of the present application. Figure 1H The implementation process of this step is described below. Figure 1HAs shown in , in the embodiment of the present application, the target data vector is obtained based on the characteristic production factor data, and the key control production factor data is determined based on the control production factor data. Next, it is necessary to rely on the artificial intelligence algorithm to learn based on the target data vector and the key control production factor data, and infer and analyze the potential data connection between the characteristic production factor data and the key control production factor data behind the target data vector. Through the application of the artificial intelligence algorithm, the connection between the two can be expressed through a mapping function.

[0202] In the embodiment of the present application, it is proposed to construct a functional operator with a mapping function as the core. Figure 1H In the example, taking agent 1 as an example, it contains multiple functional operators, namely: operator 1, operator 2 and operator 3. A mapping function is loaded in each functional operator. It can be understood that the mapping functions loaded in different functional operators are different. This is because the power function requirements that drive the construction of each functional operator may be different, and the characteristic production factor data and control production factor data used may also be different. By executing this step, the constructed agent corresponds to the aforementioned power function requirements. For example, according to the power function requirement 1, the intelligent agent 1 is finally constructed; according to the power function requirement 2, the intelligent agent 2 is finally constructed.

[0203] In the embodiments of the present application, the artificial intelligence algorithms used may be diverse. For example, all open source artificial intelligence algorithms currently available on the market can be based on the above technical concepts, and can be used to infer and analyze the intrinsic relationship between the target data vector and the key control production factor data, thereby obtaining an accurate mapping function. The specific type of artificial intelligence algorithm used is not limited here.

[0204] Combination Figure 1H It can be seen that in the embodiment of the present application, an agent can include one or more functional operators. Taking agent 1 as an example, it includes 3 functional operators. Functional operators in the same agent can be independent of each other. In addition, functional operators in the same agent can also have technical or logical connections.

[0205] exist Figure 1H In addition to Agent 1, other agents are also shown, such as Figure 1HThe intelligent agents 2, N, etc. shown in the figure. After these intelligent agents are successively constructed, an automated device that integrates the wisdom of multiple intelligent agents is formed. Therefore, the device can also be regarded as a "robot". It has rich knowledge related to the power system, and by using the functional operators in each intelligent agent, it can solve various power system analysis problems. With the increasing expansion of international cooperation in the power industry, the construction method of the intelligent agent and the architecture of the "robot" proposed in the technical solution of this application are also breakthrough technologies for coping with international power cooperation.

[0206] S104, adding intelligent agents corresponding to various power function requirements to the digital power system, and using each intelligent agent as a power function implementation unit in the digital power system.

[0207] In practical applications, power function requirements can be expressed through power analysis requests. The power analysis request can be initiated by the power plant side, the power grid side, or a third party other than the power plant side and the power grid side. As long as the relevant subject or device that initiates the power analysis request has the authority or qualification to start the power analysis agent for data analysis, the execution device (such as a server or terminal) of the method for creating a digital power system based on a multifunctional agent proposed in this scheme can respond to the power analysis request and analyze the matching of the power function requirements carried in the request with one or more agents that have been constructed. If a matching agent is not found, it is necessary to call the steps in the above method to establish an agent or a corresponding operator for the power function requirement.

[0208] It is understandable that if the analysis determines that the power function requirement carried in the power analysis request matches a certain intelligent agent that has been constructed, the intelligent agent is called and used as a power function implementation unit to implement the response to the power analysis request through the functional operator inside the intelligent agent. For example, if the demand information carried in the power analysis request indicates the calculation of the electricity price, the electricity price operator (whose function is to calculate the electricity price) in the power analysis intelligent agent is called to calculate the electricity price based on the data currently provided to the operator for the relevant calculation.

[0209] In the technical solution of the present application, since the construction of the intelligent body depends on the relevant production factor data on the power plant side and the power grid side, and the characteristic production factor group includes characteristic production factors of multiple levels, and the control production factor group includes control production factors of multiple aspects, it is equivalent to realizing the coordination of characteristic production factors of multiple levels and control production factors of multiple aspects. The intelligent body constructed based on this effectively utilizes the diversified information of power data to realize the power function of coordinating multiple production factors, such as the power function for power trading between the power grid side and the power plant side, the power function for realizing the dispatching control of the power grid side on the power plant side, and the power function for the power grid to regulate itself. The intelligent body can more accurately capture the connection between data and data, and then obtain more accurate and transferable data analysis results or data calculation results. It can also be understood that the digital power system constructed by this solution forms high-value data assets in the power system and enhances the analytical value of power data. The constructed digital power system can effectively contribute to the domestic power market reform and global power trading.

[0210] In practical applications, it is possible that a single operator cannot meet a relatively large analysis goal. In this case, a possible solution is to call multiple operators to meet an analysis goal. This type of situation is introduced below.

[0211] To deal with the above problems, the power analysis demand information can be parsed in the initial stage of constructing the intelligent agent to obtain multiple sub-demand information and the logical dependency relationship or digital conversion relationship between the multiple sub-demand information. By parsing and disassembling the power analysis demand information, functional operators can be built according to the sub-demand information in a targeted manner. Assume that by parsing the power analysis demand information, multiple sub-demand information is obtained, including the first sub-demand information and the second sub-demand information.

[0212] Fig. 1I This is a flowchart for implementing a power analysis intelligent entity provided in an embodiment of the present application. Fig. 1I As shown, in a specific implementation, the method for constructing a digital power system based on a multifunctional intelligent agent provided in an embodiment of the present application further includes:

[0213] A first target data vector is constructed based on the first sub-demand information and a first key control production factor data associated with the first sub-demand information is determined; and a second target data vector is constructed based on the second sub-demand information and a second key control production factor data associated with the second sub-demand information is determined.

[0214] for Fig. 1IIn the specific example shown, based on the target data vector and the key control production factor data, an artificial intelligence algorithm is used to learn the mapping function between the target data vector and the key control production factor data, a functional operator with the mapping function as the core is constructed, and a power analysis intelligent agent is constructed based on multiple functional operators, which may specifically include:

[0215] Based on the first target data vector and the first key control production factor data, an artificial intelligence algorithm is used to learn the first operator; and based on the second target data vector and the second key control production factor data, an artificial intelligence algorithm is used to learn the second operator; based on a logical dependency relationship or a numerical conversion relationship, a transfer function relationship between the first operator and the second operator is constructed; based on the transfer function relationship, the first operator and the second operator, an electric power analysis intelligent entity is constructed.

[0216] So far, a multi-operator power analysis agent including the first operator and the second operator has been constructed. Based on this, when a power analysis request is received, and the demand information carried therein also matches the first sub-demand information and the second sub-demand information, the power analysis agent can be called to trigger the first operator and the second operator based on the transfer function relationship to generate the final analysis response result to the power analysis request. In this way, the collaborative work of multiple functional operators in the power analysis agent is realized. By constructing multiple functional operators with logical dependencies or numerical conversion relationships, and constructing a power analysis agent accordingly, the power analysis agent can handle more complex and diversified power data analysis tasks.

[0217] As mentioned above, the transfer function relationship between the first operator and the second operator is constructed based on the logical dependency relationship or the numerical conversion relationship. Therefore, in the intelligent agent, different operators also have corresponding logical dependencies or numerical conversion relationships. The following are several dependencies that exist in the power system: reactive power and voltage, heat consumption and coal consumption, system inertia and frequency, electricity price and coal price, etc.

[0218] For example, the numerical conversion relationship between different operators may mean that different operators have basically the same functions, but there are differences at the transaction level or pricing level. In order to meet the interoperability requirements of transactions or pricing, it is necessary to call operators to perform digital conversion at the transaction level or pricing level. As an example, operator A calculates the electricity price of the power grid of country A, and operator B calculates the electricity price of the power grid of country B. When it is necessary to convert the electricity prices of countries A and B, it is necessary to operate according to the digital conversion relationship.

[0219] In the embodiment of the present application, each intelligent agent is configured with multiple types of interfaces to complete communication or data exchange with other subjects. As an example, the intelligent agent is configured with a power plant side interface, a grid side interface, and an intelligent agent interface. Among them, the power plant side interface is used for the intelligent agent to connect with the power plant; the grid side interface is used for the intelligent agent to connect with the grid; and the intelligent agent interface is used for the intelligent agent to connect with other intelligent agents.

[0220] In a possible implementation, the agent may be specifically configured with multiple power plant side interfaces, and different power plant side interfaces are used to connect to different types of power plants, or different power plants of the same type. This application does not limit the number of power plant side interfaces configured for an agent.

[0221] In a possible implementation, the agent may be specifically configured with multiple agent interfaces, and different agent interfaces are used for the agent to connect to different other agents. This application does not limit the number of agent interfaces configured for an agent.

[0222] By calling the intelligent agent, an analysis response result for the power analysis request can be generated. Based on the above introduction to the interface configured on the intelligent agent, in the technical solution of this application, the intelligent agent can send the analysis response result to the power plant through the power plant side interface; the intelligent agent can send the analysis response result to the power grid through the power grid side interface; the intelligent agent can send the analysis response result to other intelligent agents through the intelligent agent interface. It can be seen that through the configuration of the above multiple types of interfaces, the intelligent agent has a way to communicate with various external objects through the interface to transmit the analysis results.

[0223] In addition, in an embodiment of the present application, a scenario may arise in which, after the agent obtains the analysis response result, it needs to send a control instruction to the outside world. With the help of the configuration of various types of interfaces, the agent can transmit control instructions. In an example implementation, the agent generates a first control instruction for the power plant, a second control instruction for the power grid, or a third control instruction for other agents based on the analysis response result. It should be noted that the above first control instruction, second control instruction and third control instruction are generated according to specific control requirements. The agent can send the first control instruction to the power plant through the power plant side interface; or, send the second control instruction to the power grid through the power grid side interface; or, send the third control instruction to other agents through the agent interface.

[0224] Figure 1J Another schematic diagram of the relationship between an agent, an operator, a function, and production factor data provided in an embodiment of the present application. Figure 1J On the left side, objects of the same level as the concepts of data, function, operator, agent, etc. in the technical solution of this application are shown from the perspective of organisms; Figure 1J On the right side, the concepts of data, functions, operators, intelligent agents, etc. mentioned in the digital power analysis method for coordinating multiple production factors proposed in this application are displayed. Figure 1J The left and right sides are connected by an arrow marked with the word "symbiosis", which reflects the similarity of the roles or functions of the concepts or objects on the left and right sides.

[0225] Combination Figure 1J As shown on the left, the construction of proteins depends on mitochondria, the construction of cells depends on proteins, and the operation of physiological functions such as human joints (or organs) depends on cells. A complete human body cannot be separated from diverse and multifunctional joints and organs. It is understandable that mitochondria provide key biological characteristics, such as the genetic material deoxyribonucleic acid (DNA) in mitochondria. DNA carries the genetic information necessary for the synthesis of RNA and proteins and is an essential biological macromolecule for the development and normal operation of organisms. The performance of human joints (or organs) is also inseparable from the genetic information carried by DNA. Figure 1J The data, functions, operators, agents and robots shown on the right also have a similar progressive relationship. The formation of the mapping function is inseparable from the extraction of characteristic production factor data and the extraction of control production factor data. The mapping function depends on these data, the operator uses the function as the core, and the agent contains one or more operators to realize the analysis function of the power system data. The robot finally formed has the ability to handle complex and diverse power analysis needs because of its diverse agents. And the foundation of all this depends on Figure 1G The production factor division framework is shown.

[0226] The above text describes in detail the construction process of the construction method of the digital power system based on the multifunctional intelligent agent. In the technical solution of the present application, a plurality of intelligent agents corresponding to different power function requirements are added to the constructed digital power system. In order to facilitate the understanding of the responsiveness of the constructed digital power system to the diversified power function requirements, the present application also combines the following six embodiments to explain the use of operators to realize power functions.

[0227] In the technical solution of this application, the power function requirement can be: the power function requirement for power trading between the power grid and the power plant, the power function requirement for realizing the dispatching control of the power grid on the power plant, or the power function requirement for the power grid to regulate itself. In the technical solution described below in this application:

[0228] In the first embodiment, the power function requirement for power grid side and power plant side to trade power is specifically to calculate the power price, the functional operator is the power price operator, and the power price operator is used to calculate the power price. The first embodiment introduces the process of using the intelligent agent constructed based on the power price operator in the digital power system. By using the intelligent agent constructed by the power price operator, a power price calculation method is implemented, combined with the following first embodiment and FIG. 2A to FIG. 2C illustrate.

[0229] In the second embodiment, the power function requirement for power trading between the power grid side and the power plant side is specifically power clearing, and the functional operator is the clearing operator, which is used for power clearing. The second embodiment introduces the process of a digital power system using an intelligent agent constructed based on the clearing operator. The difference between the electricity price operator and the clearing operator is that the clearing operator has a part for calculating the electricity price, but after calculating the electricity price, the function of the clearing curve is implemented according to the priority or the priority of the stack, making the clearing operator function more complex. By using an intelligent agent constructed by the clearing operator, a power grid clearing method is implemented. Combined with the second embodiment below, FIG. 3A to FIG. 3I and 4A to 4H illustrate.

[0230] In the third embodiment, the power function requirement for realizing the dispatching control of the power plant side by the power grid side is specifically the peak-shaving dispatching in the high-frequency variable load scenario of thermal power. The functional operator is the thermal power peak-shaving dispatching operator. The thermal power peak-shaving dispatching operator is used to realize the peak-shaving dispatching in the high-frequency variable load scenario of thermal power. The third embodiment introduces the process of using the intelligent agent constructed based on the thermal power peak-shaving dispatching operator in the digital power system. By using the intelligent agent constructed by the thermal power peak-shaving dispatching operator, a peak-shaving dispatching method in the high-frequency variable load scenario of thermal power is realized. Combined with the following third embodiment and FIG. 5A to FIG. 5F illustrate.

[0231] In the fourth embodiment, the power function requirement for realizing the dispatching control of the power plant side by the power grid side is specifically the water resource dispatching of the cascade hydropower station, and the functional operator is the water resource dispatching operator, which is used to realize the water resource dispatching of the cascade hydropower station. The fourth embodiment introduces the process of using the intelligent agent constructed based on the water resource dispatching operator in the digital power system. By using the intelligent agent constructed by the water resource dispatching operator, a water resource dispatching method is realized, combined with the fourth embodiment and the following FIG. 6A to FIG. 6J illustrate.

[0232] In the fifth embodiment, the power function requirement for realizing the dispatching control of the power grid side to the power plant side is specifically the dispatching of the power grid to the power plant in the large-machine small-grid power system, and the functional operator is the large-machine small-grid dispatching operator, which is used to realize the dispatching of the power grid to the power plant in the large-machine small-grid power system. The fifth embodiment introduces the process of using the intelligent agent constructed based on the large-machine small-grid dispatching operator in the digital power system. By using the intelligent agent constructed by the large-machine small-grid dispatching operator, a method for power grid dispatching in a large-machine small-grid power system is realized, combined with the fifth embodiment below and 7A to 7F illustrate.

[0233] In Example 6, the power function requirement for the self-regulation of the power grid is specifically to regulate the grid structure of the power grid, and the functional operator is the grid structure regulation operator, which is used to achieve the regulation of the grid structure of the power grid. Example 6 introduces the process of a digital power system using an intelligent agent constructed based on the grid structure regulation operator. By using an intelligent agent constructed by the grid structure regulation operator, a method for regulating the grid structure of the power grid is implemented, combined with Example 6 and FIG. 8A to FIG. 8D illustrate.

[0234] Embodiment 1

[0235] In the first embodiment, the power function requirement for power trading between the power grid and the power plant is specifically to calculate the power price, the functional operator is the power price operator, and the power price operator is used to calculate the power price. The first embodiment introduces the process of a digital power system using an intelligent agent constructed based on the power price operator.

[0236] In actual applications, the power plant needs to calculate the electricity price and then provide it to the power plant. If the power plant and the grid reach an agreement on the electricity price, electricity trading can be carried out.

[0237] Combine the following Figure 2A and Figure 2B From the perspectives of the grid side and the power plant side, the grid side process and the power plant side process based on the electricity price operator are introduced respectively.

[0238] like Figure 2AAs shown in the figure, the grid-side process based on the electricity price operator is shown. First, it is necessary to extract the key control production factor data related to the electricity price calculation from the power data on the grid side. Optionally, these key control production factor data can be represented by digital vectors. Next, the grid side also needs to obtain the target data vector obtained by feature extraction based on the power data on the power plant side. It can be understood that this type of data vector is also related to the electricity price calculation. In one example, the performance efficiency related data vector A of unit A is expressed as (coal consumption 1, heat rate 1, unit efficiency 1), and the performance efficiency related data vector B of unit B is (coal consumption 2, heat rate 2, unit efficiency 2). These data vectors are aligned and statistically obtained to obtain the comprehensive production factor data vector (coal consumption 1+coal consumption 2, heat rate 1+heat rate 2, unit efficiency 1+unit efficiency 2). Next, based on the data vectors extracted from the power plant side and the grid side above, the operator function computing power group is obtained by using the artificial intelligence algorithm. The operator function computing power group contains many functional operators with functions as the core. Having these operator function computing power groups can also be understood as building an intelligent power analysis entity.

[0239] Taking electricity price calculation as an example, the constructed operator function computing power group can be called the power grid load and electricity price function computing power group. In addition, considering other possible power analysis needs, it is also possible to establish a power grid inertia frequency computing power group, an active and reactive function computing power group, a power grid carbon footprint computing power group, a power grid voltage and current function computing power group, a power grid safety and stability computing power group, a power grid connection and decoupling computing power group, etc. Among them, the active and reactive function computing power group includes functions used to reflect the performance of active and reactive power in the power grid; the power grid inertia function computing power group includes functions used to reflect the performance of stable frequency conversion of the power grid; the power grid load and electricity price function computing power group includes functions used to calculate the relationship between the power grid electricity price and the power plant power generation load; the power grid safety and stability computing power group includes functions used to calculate the power grid step and flow; the power grid carbon footprint computing power group includes functions used to calculate the carbon consumption in the production of hydropower, thermal power, photovoltaic, wind power and other equipment in the power grid.

[0240] Taking the power grid load and electricity price function computing power group as an example, the mapping function as the core of the electricity price operator can be expressed as: CERm = U*N / E(1-AUX). CERm is the grid compensation coefficient for 1 kWh of electricity payment. U represents the coal price, which is also the fuel cost subsidy, in US dollars / ton. E represents the unit's power generation heat consumption rate, that is, the unit's heat consumption per kWh of electricity, in kcal / kWh. N represents the specific heat index, in kcal / kWh. AUX represents the plant power consumption rate. This formula reflects the connection between the grid compensation coefficient for 1 kWh of electricity payment and characteristic production factors such as coal price, unit power generation heat consumption, specific heat index, and plant efficiency.

[0241] After obtaining the electricity price operator by using the artificial intelligence algorithm, when calling the intelligent agent containing the operator, the electricity price calculation result on the power plant side is obtained through the electricity price operator. It should be noted that since the construction of this operator depends on the power data on the power plant side, the electricity price calculation result actually reflects more of the power plant's own cost considerations and profit needs. The subsequent power grid side needs to further consider the electricity price calculation result.

[0242] like Figure 2A As shown in , after obtaining the electricity price calculation result on the power plant side through the electricity price operator, the electricity price calculation result is verified through the financial verification model on the power grid side. The main purpose of verifying the electricity price calculation result through the financial verification model on the power grid side is to ensure the balance and stability of the power plant and the power grid. In one example, the financial verification model on the power grid side includes: a first verification condition and a second verification condition; the first verification condition is: the actual output of various types of power plants ≥ the power grid electricity; the second verification condition is: the sum of the products of the actual output of various types of power plants, the power grid electricity price at the corresponding time and the power generation time ≤ the product of the average power grid price and the power grid electricity. If the electricity price calculation result meets the first verification condition and the second verification condition, it is determined that the electricity price calculation result has been verified; if the electricity price calculation result does not meet any of the first verification condition and the second verification condition, it is determined that the electricity price calculation result has not been verified.

[0243] The expression of the first verification condition is:

[0244] Q 火电 +M 风电 +Q 水电 +M 光伏 ≥N 电量

[0245] The expression of the second verification condition is:

[0246] Σ(H*Q 火电 *N 各时刻电网电价 )+ΣM 风电 *N 各时刻电网电价 +Σ(H*Q 水电 *N 各时刻电网电价 )+ΣM 光伏 *N 各时刻电网电价 ≤P 电网均价 *N 电量

[0247] In the above expression, Q 火电 、M 风电 , Q 水电 、M 光伏 are the actual outputs of thermal power plants, wind power plants, hydropower plants and photovoltaic power plants respectively. 电量 is the power of the power grid. H represents the power generation time. 各时刻电网电价is the grid electricity price at the corresponding time. 电网均价 Represents the average grid price.

[0248] For calculation, thermal power and hydropower are both physical power generation with controllable resources, which are deterministic; while photovoltaic and wind power cannot control the wind and light, and their natural elements are highly uncertain. Here, the processing is expressed differently, distinguished by Q and M. This shows the difference in data abstraction between the two types of production factors. The production factors of thermal and hydropower generation are highly deterministic and weakly abstract, represented by Q; while the production factors of wind and photovoltaic generation are highly uncertain and highly abstract, and require a higher-order data operator function M to represent.

[0249] If the electricity price calculation result is verified, the electricity price calculation function that is suitable and feasible on the grid side is further selected from the dispatching strategy library. The dispatching strategy library can be responsible for a special operator that provides a variety of calculation functions. As mentioned above, the construction of the constructed electricity price operator depends on the power data on the power plant side. Therefore, the electricity price calculation result actually reflects more of the power plant's own cost considerations and profit requirements. The subsequent grid side needs to further consider this electricity price calculation result. The specific consideration method is to use the dispatching strategy library. The grid side also needs to select an electricity price calculation function that is suitable for the grid side and technically feasible from the dispatching strategy library, and then load the electricity price calculation function into the electricity price operator to update the function of the electricity price operator; the electricity price calculation result on the grid side is obtained through the updated electricity price operator. In this way, the grid side not only refers to the electricity price calculation result on the power plant side, but also updates the electricity price operator based on its own cost and profit requirements. In this process, the collaborative calculation of electricity prices between the power plant side and the grid side is realized.

[0250] If a grid-adaptive and technically feasible electricity price calculation function cannot be selected from the dispatch strategy library, it is necessary to deeply learn the grid energy consumption average efficiency operator, average electricity price operator and other important production factor operators, return the learning results as samples, and use artificial intelligence algorithms to learn the electricity price operator.

[0251] In an optional implementation, after the electricity price calculation function is loaded into the electricity price operator to perform function update on the electricity price operator, the digital power analysis method for coordinating multiple production factors provided in the embodiment of the present application further includes:

[0252] The grid side collects the transaction volume and electricity price reported by the power plant side to the grid side. Prepare to conduct transactions between the power plant side and the grid side. At this time, the grid side completes the electricity price calculation function for the power plant side. Next, based on the grid side, it determines whether the network is stable to determine whether the virtual power plant function needs to be started. The purpose of starting the virtual power plant function is to call the storage capacity, and then give the power of each power generation and clearing according to the cost optimization principle, and finally issue instructions in advance based on artificial intelligence calculations. The power grid calls the storage capacity of the virtual power plant. When there is a power shortage, the electricity price is high, and the virtual power plant (battery) is called to discharge; when there is a surplus of electricity, the electricity price is low, and the virtual power plant (battery) is charged.

[0253] In the technical solution of the present application, the power grid side can record the respective clearing curves and dispatching curves under different loads or in emergency situations as input data for deep learning, continuously verify, learn and imitate the laws and characteristics of the power grid, and use them as a reference for issuing instructions next time.

[0254] If it is determined that the virtual power plant function does not need to be started, the grid side sends dispatch instructions for clearing electricity prices and electricity to various types of power plants based on the electricity price calculation results on the grid side. If it is determined that the virtual power plant function needs to be started, the virtual power plant function is started to call storage capacity. And the operator of the virtual power plant function is combined and returned again, and the steps of obtaining the electricity price operator are obtained using the artificial intelligence algorithm.

[0255] like Figure 2B As shown in the figure, the power plant side process based on the electricity price operator is demonstrated. First, various characteristic production factor data on the power plant side are collected to form a data vector. Then, the electricity price operator is trained in combination with the key control production factor data on the power grid side. The power plant side receives the clearing electricity price given by the power grid side; combined with the power plant cost and the clearing electricity price, the financial verification model on the power plant side is used for verification. In an optional implementation, the financial verification model on the power plant side includes: a third verification condition; the third verification condition is: the sum of the product of the actual output of the power plant, the power grid electricity price at the corresponding moment and the power generation time> the product of the power plant cost and the actual output of the power plant. Taking a thermal power plant as an example, the expression of the third verification condition is:

[0256] Σ(H*Q 火电 *N 各时刻电网电价 )>Σ(H*Q 火电 *P 电厂成本 )

[0257] In the expression of the third verification condition above, Q 火电 is the actual output of the thermal power plant. H represents the duration of power generation. 各时刻电网电价 is the grid electricity price at the corresponding moment. Artificial intelligence is used to convert the grid electricity price N at each moment 各时刻电网电价 As data input, the power plant cost P under different loads calculated by this power plant system is used. 电厂成本The corresponding formula is substituted into the formula. The expression of this verification condition reflects that the actual output of thermal power generation production factors is accumulated and calculated as the power grid settlement electricity fee, which fluctuates with the power grid, but the cost production factors of a single power plant change with the load rate, and finally map the cost production factors of the power plant.

[0258] The same power plant type may have several different power supply points. Figure 2B As shown in , if the verification result indicates that the verification is passed, it means that the verification conditions are met as a whole. Then, it is necessary to further determine whether different power sources of the same power plant type can be cleared based on the power volume and electricity price; if each power source can be cleared, the clearing power volume is executed. Subsequently, the corresponding action of the load adjustment of the thermal power plant unit. If there is a situation where the power source cannot be cleared, it is also necessary to calculate the production cost of the power plant or adjust the clearing electricity price of the power plant, and after verification, it is determined again whether each power source can be cleared.

[0259] The first verification condition, the second verification condition and the third verification condition mentioned above are mathematical logics, and all express some physical constraints in the power system. These verification conditions make the power system stable.

[0260] Figure 2C It is a signaling diagram between the power plant side, the grid side and the intelligent agent. Figure 2C The significance of peak-shaving in the power system is to find power plants that are suitable for peak-shaving electricity prices within the electricity price range specified by the power grid, so that the revenue and expenditure of the power grid remain balanced and within the budget. At the same time, the clearing electricity and prices of various types of power plants are estimated, and clearing is done from two buses or algorithms. That is, each power plant can provide the technical clearing point of the electricity and clearing curve under the basic electricity price. After the total electricity price of the power grid is distributed to various types of power plants, the minimum value that satisfies the above inequality is the power plant electricity price and electricity clearing point.

[0261] When digital power analysis is required, the measured data is first digitized, and then (based on the power data on the power plant side to be analyzed and / or the power data on the grid side to be analyzed), data cleaning and data composition are performed to facilitate subsequent parallel calculations. The output results of the calculations are generalized into operators (functions) based on the data model. This operator (function) completes a specific function. After the intelligent agent completes the analysis using the above operator, the entire intelligent agent logic process is completed, and the established mapping function output is used to generate the power analysis results, or the operator output is brought into a new intelligent agent nested iteration. The operator is the most important part of the intelligent agent, which realizes specific functions of the power system, such as the frequency operator, the active and reactive operator, and the electricity price operator. The electricity price operator is: the operator is a function. The intelligent agent is a process or logic that contains many operators to realize many functions.

[0262] After the production factor data is digitized, data parallel calculation is performed. Due to the characteristics of GPU, after the data vectors of the same type are aligned, the data can be quickly calculated in parallel. At the same time, the use of neural network algorithms will lose some characteristics of its symbolic artificial intelligence algorithms, but the data tools of graph neural networks are sufficient to retain and calculate the data features at the input and transmission layers under the self-attention mechanism under the probabilistic method, reflecting the data-driven characteristics. In order to make up for the loss of symbolic artificial intelligence and to make it easier to perform functional calculations and control of intelligent agents, the concept of operators is introduced at the output, and multiple operators are placed in the logic of the intelligent agent, so that the intelligent agent obtains the corresponding functions. The capabilities of digital power analysis also revolve around the specific capabilities of these operators, making the intelligent agent the basic unit for power data analysis in the power system.

[0263] Embodiment 2

[0264] In the second embodiment, the power function requirement for power trading between the power grid and the power plant is specifically power clearing, and the functional operator is a clearing operator, which is used for power clearing. The second embodiment introduces the process of a digital power system using an intelligent agent constructed based on the clearing operator.

[0265] In the current power grid clearing process, it is often necessary to involve the electricity price forecast for different power plants and the power distribution process. However, in actual application scenarios, the prediction of power plant electricity prices and the power distribution process are often affected by many factors, resulting in poor accuracy of power grid clearing. In order to solve the above problems, the embodiment of the present application realizes power clearing through a clearing function, which can also be understood as realizing power grid clearing. First, low-order data abstraction processing is performed according to the power generation element characteristics of each associated power plant, and the various factors affecting the power grid clearing are quantified into a first data vector, thereby reducing the data complexity of the power generation element characteristics. Subsequently, a long-term transaction electricity price prediction is performed according to the first data vector and a preset long-term electricity price function library, so as to predict the corresponding long-term transaction electricity price according to the actual power generation element characteristics of each associated power plant, and establish a corresponding long-term transaction stack, so as to improve the accuracy of power grid clearing by ensuring the accuracy of the long-term transaction electricity price. Further, a spot transaction stack is established based on the spot transaction electricity price of each associated power plant, and the first clearing function is determined by the long-term transaction stack and the spot transaction stack. Correspondingly, according to the determined first clearing function, the power supply and demand balance state of the target power grid when clearing under the first clearing function is determined, and the first clearing function is adjusted in real time according to the actual power supply and demand balance state of the target power grid to obtain the second clearing function. In this way, the clearing function of the target power grid can be dynamically adjusted according to the supply and demand state of the target power grid, and a specific clearing function can be established through a transaction stack constructed in real time by long-term transaction electricity prices and spot transaction electricity prices, so that the clearing of the power grid can effectively consider the impact of the characteristics of power generation factors on the power generation of related power plants, as well as the changes in the spot transaction electricity prices of each related power plant, and then determine a more accurate clearing function, thereby achieving the effect of improving the accuracy of power grid clearing.

[0266] Next, a power grid clearing method provided in an embodiment of the present application will be introduced in conjunction with specific embodiment drawings.

[0267] See also Figure 3A and Figure 3B , Figure 3A A schematic diagram of a flow chart of a power grid clearing method provided in an embodiment of the present application, Figure 3B A signaling interaction diagram of a power grid clearing method provided in an embodiment of the present application. Figure 3A In the example, the grid clearing method is implemented on the target grid side, while Figure 3B In the embodiment, the overall implementation of the solution is introduced by associating the interactive signaling between the power plant side and the target grid side.

[0268] like Figure 3A As shown, the power grid clearing method specifically includes the following steps:

[0269] S301: Perform low-order data abstraction processing according to the power generation element characteristics of each of the associated power plants to obtain a first data vector of the power generation element characteristics.

[0270] The power generation factor characteristics of the associated power plant are the data of various natural factors and production factors that affect the power generation performance of the power plant, such as weather conditions (illuminance, temperature, wind speed, etc.), hydrological water flow, coal type and coal consumption, etc. In actual power generation scenarios, the power generation performance of the associated power plant is often affected by many factors such as weather environment, unit equipment, coal type and coal consumption.

[0271] Therefore, in order to determine the power generation performance of the associated power plants as accurately as possible, in the power grid clearing method provided in this application, it is first necessary to perform low-level data abstraction processing on the power generation factor characteristics of each associated power plant, so as to abstract the power generation factor characteristics that have a greater impact on the power plant's power generation performance from the complex power generation factor characteristics, and integrate these power generation factor characteristics into a first data vector. At the same time, the quantization of the first data vector for the power generation factor characteristics can provide a data basis for the subsequent adjustment of the preset long-term electricity price function library. By presetting the long-term electricity price function library and the first data vector, the long-term transaction electricity price of the associated power plant can be more accurately predicted in the subsequent process, thereby improving the accuracy of power grid clearing.

[0272] Specifically, taking a thermal power plant as an example of an associated power plant, after low-level data abstraction processing, the first data vector of the thermal power plant can be the data characteristics of its corresponding thermal performance, such as (heat consumption rate of the unit, coal consumption, and power consumption rate of the plant). Correspondingly, when the associated power plant is a photovoltaic power plant, its corresponding first data vector can also be a photoelectric conversion efficiency characteristic, such as (illuminance, power generation, and photoelectric conversion efficiency).

[0273] Next, the process of performing low-level data abstraction processing on the characteristics of power generation elements in this step will be introduced in conjunction with the drawings of specific embodiments.

[0274] See also Figure 3C , which is a flow chart of another power grid clearing method provided in an embodiment of the present application, specifically comprising the following steps:

[0275] S1101: establishing an energy consumption data model for each of the associated power plants according to the characteristics of each of the power generation elements; the energy consumption data model is used to evaluate the power generation performance of the associated power plants.

[0276] Specifically, in the process of low-level data abstraction based on the power generation factor characteristics of each related power plant, it is necessary to convert the collected various power generation factor characteristics into primary indicators (natural indicators), and establish energy consumption data models of secondary and tertiary indicators related to the related power plants based on the primary indicators. Among them, these indicators include parameter indicators such as energy consumption and power generation efficiency. By constructing energy consumption data models of each related power plant, it can reflect the power generation performance of the related power plant under different conditions, so as to comprehensively evaluate the impact of various power generation factor characteristics on the power generation performance of its related power plant.

[0277] At the same time, by constructing an energy consumption data model based on the power generation element characteristics of each related power plant, a mapping of the corresponding data of each power generation element characteristic to the specific function in the preset long-term electricity price function library can be established, so that the association between data and function can be preliminarily constructed.

[0278] S1102: Perform low-order data abstraction processing on the characteristics of each power generation element through the energy consumption data model to obtain the first data vector of the characteristics of each power generation element.

[0279] After constructing the energy consumption data model of each associated power plant, low-level data abstraction processing is performed on the characteristics of each power generation element through the energy consumption data model, so as to extract the power generation element characteristics that can accurately characterize the power generation performance of the associated power plant from the complex power generation element characteristics, and integrate these power generation element characteristics into the first data vector corresponding to the associated power plant alone.

[0280] The first data vector thus generated can accurately describe the key characteristics of the associated power plant in the power generation process. At the same time, it will also be used to adjust the preset long-term electricity price function library and be applied in long-term electricity price forecasting, thereby realizing dynamic and rapid long-term electricity price forecasting, so as to quickly adjust the clearing function of the target power grid.

[0281] In one possible implementation, after constructing the energy consumption data model of each related power plant, the weight of each indicator is set in the energy consumption data model to highlight the importance of different power generation elements in the power output, thereby effectively improving the accuracy of subsequent function adjustments to the preset electricity price function library.

[0282] The above is the specific process of performing low-level data abstraction processing on the power generation element characteristics in step S301. Figure 3A The grid clearing method shown is introduced.

[0283] S302: performing long-term transaction electricity price prediction according to a preset long-term electricity price function library and each of the first data vectors to establish a long-term transaction stack.

[0284] In the preset long-term electricity price function library, a plurality of operator functions for calculating the long-term transaction electricity prices of associated power plants are stored. By presetting the electricity price operator functions for different power plants in the long-term electricity price function library and combining the first data vector determined by the characteristics of each power generation element, the index parameters represented by the first data vector can be imported into the corresponding operator function, thereby calculating the long-term transaction electricity prices of each associated power plant, thereby completing the long-term transaction electricity price prediction for the associated power plants.

[0285] For example, taking the associated power plant as a hydropower plant as an example, the corresponding long-term electricity price operator function is:

[0286] PTOPE (long-term transaction electricity price) = A + B + C + D + E = Am + Bm + Cm + Dm + Em = (TOPEm-PCm) * CCRm + (TOPEm-PCm) * FOMRm + (TOPEm-PCm) * HFCm + NEOm * VOMRm + (TOPEm-PCm) * CCRTm = (TOPEm-PCm) * (CCRm + FOMRm + HFCm + CCRTm) + NEOm * VOMRm

[0287] Where A represents the capital cost recovery factor, B represents the fixed operation and maintenance cost factor, C represents the hydropower facility factor, D represents the variable operation and maintenance cost factor, E represents the special facility factor, Am, Bm, Cm, Dm, Em represent the factors of the annual billing period (in rupees);

[0288] TOPEm represents the amount of electricity (kWh) taken or paid during the billing period, which is obtained through annual TOPE. TOPE needs to be confirmed by the target grid and the associated booking site.

[0289] CCRm represents the capital cost recovery charge rate applicable to the billing period (Rp / kWh);

[0290] PCm = Payment credit for the billing period (kWh). Payment credit PCm exists only at the end of each billing period and when the net output during the billing period is less than TOPEm;

[0291] Here: PCm = TOPEm - NEOm - DCm - WLCm;

[0292] Among them, NEOm represents the net output during the billing period; NEOm during the billing period should not exceed TOPEm;

[0293] DCm represents the transmission credit for the billing period, which should be equal to the amount of electricity (kWh) produced by non-power plants according to the dispatch instructions of the target grid plus the amount of electricity delivered or generated that is considered; if the power supply system of the target grid cannot accept all the electricity produced by the associated power plant, the target grid should issue appropriate dispatch instructions to the power plant;

[0294] FOMRm = Fixed Operation and Maintenance Cost Recovery Charge Rate (Rp / kWh) applicable during the billing period, expressed in rupees, HFCm represents the allowance for (i) a portion of the operation and maintenance cost of the hydropower facility, (ii) the contribution to river basin coordination, and (iii) water charges, all expressed in Rp / kWh.

[0295] VOMRm represents the variable operation and maintenance cost recovery charge rate (Rp / kWh) for the billing period, namely:

[0296] VOMRm=VOMRFm+VOMRLm;

[0297] Where VOMRFm represents the variable operation and maintenance cost (expressed in non-rupees) recovery charge rate applicable during the billing period (Rp / kWh), and VOMRLm represents the variable operation and maintenance cost (expressed in rupees) recovery charge rate applicable during the billing period (Rp / kWh);

[0298] CCRTm represents the capital cost recovery charge rate (Rp / kWh) for a particular facility applicable during the billing period.

[0299] As can be seen from the above formula, by importing the first data vector containing the characteristics of the power generation elements of the hydropower plant into its corresponding long-term electricity price operator function, the long-term transaction electricity price of the hydropower plant in a certain period of time in the future can be predicted. By presetting the long-term transaction electricity price operator function corresponding to each associated power plant in the long-term electricity price function library, the first data vector of each power plant is imported into it, and the long-term transaction electricity price of each power plant can be predicted.

[0300] It is understandable that in actual long-term transaction electricity price forecasting scenarios, there are differences in the characteristics of power generation factors of related power plants in different regions and countries, and their corresponding electricity price calculation formulas will also be different, which will not be elaborated in this embodiment.

[0301] Furthermore, by sorting the long-term transaction electricity prices of each power plant, the stack priority in the long-term transaction stack can be determined, thereby establishing a long-term transaction stack. For example, the long-term transaction stack can be found in Figure 3D A schematic diagram of a long-term transaction stack is shown. As can be seen from the figure, the long-term transaction stack is sorted based on the long-term transaction electricity prices predicted by each associated power plant.

[0302] It can be understood that in actual application scenarios, the long-term trading electricity between the power grid and its associated power plants is determined by the long-term trading contract signed in advance between the two parties. In the process of constructing a long-term trading stack, the long-term trading electricity indicated in the long-term trading contract can also be used as the weight of the stack. The more trading electricity, the lower the long-term trading electricity price, and the higher the priority of the stack. When the long-term trading electricity price is the same, in order to ensure the clearing stability of the power grid, the long-term trading electricity needs to have more weight than the long-term trading electricity price. The amount of trading electricity is used as the key factor in the construction of the long-term trading stack, which is not elaborated in this embodiment.

[0303] In this way, through the first data vector corresponding to each associated power plant and the preset long-term electricity price function library, the specific long-term transaction price of each associated power plant under the influence of the current power generation factor characteristics can be predicted, so as to establish a long-term transaction stack through the long-term transaction electricity prices of each associated power plant.

[0304] Next, the process of establishing a long-term transaction stack in step S302 will be introduced in conjunction with the specific embodiment drawings. Figure 3E , which is a flow chart of another grid clearing method provided in an embodiment of the present application, specifically comprising the following steps:

[0305] S2201: Using the first data vector, perform data-driven adjustment on the function indicators of the preset long-term electricity price function library to obtain a dynamic electricity price function library.

[0306] As can be seen from the foregoing, operator functions for calculating the long-term transaction electricity prices of each associated power plant are pre-stored in the preset electricity price function library. In actual application scenarios, the long-term transaction electricity prices of associated power plants are determined by their own power generation costs, and in different regions, different time periods, and even different seasons, the power generation costs of different associated power plants vary greatly. Therefore, in order to accurately predict the long-term transaction electricity prices of associated power plants, it is necessary to perform data-driven adjustments to the function indicators in the preset electricity price function library through the first data vector generated by the characteristics of the power generation elements, so as to adjust the function indicators in each operator function, thereby improving the prediction accuracy of the long-term transaction electricity price.

[0307] Here, a thermal power plant is taken as an example of an associated power plant. The first data vector of the thermal power plant is (unit heat rate, coal consumption, plant power rate, electricity price). Its first data vector is: (Pm, SHRW, GCVs, AUX, CERm), and its corresponding long-term transaction electricity price operator function is:

[0308] CERm=Pm*SHRW / GCVs(1-AUX)=0.031053242USD / KWh(1)

[0309] Wherein, Pm represents the coal price USD, SHRW represents the unit specific heat index Kcal / KWh, GCVs represents the coal high calorific value Kcal / Kg, AUX represents the plant power consumption rate, unit %, CERm represents the electricity price, unit USD / KWh, and in formula *(1), SHRW=2138.4Kcal / KWh is set;

[0310] The electricity price operator function is adjusted by the first data vector, and the adjusted electricity price operator function is:

[0311] CERm=Pm*SHRW(1+AGE) / GCVs(1-AUX)=0.031947846USD / KWh(2)

[0312] Wherein, AGE represents the unit loss, unit %, and the others are the same as above. When AGE is set to 5.4%, SHRW = 2210.14Kcal / KWh;

[0313] For details, see Figure 3F and Figure 3G ,in, Figure 3F A parameter indicating the thermal performance of a unit under full load conditions provided in an embodiment of the present application is shown. Figure 3G for Figure 3F Based on the data shown, a schematic diagram of comprehensive consideration parameters for coal prices and long-term trading electricity prices is shown. It can be seen that after the unit performance decay changes the specific heat index, the loss needs to be considered in the unit electricity price change formula, so that (2) replaces formula (1), so that the electricity price changes from 0.031USD / KWh to 0.032USD / KWh.

[0314] It can be seen that, through the first data vector determined in real time by each associated power plant, the long-term electricity price operator function for each associated power plant in the preset long-term electricity price function library can be adaptively adjusted, thereby ensuring the accuracy of the prediction of the long-term trading electricity price.

[0315] S2202: Perform long-term transaction electricity price forecasting based on the dynamic electricity price function library and the characteristics of each of the power generation elements to obtain the long-term transaction forecast electricity price of each of the associated power plants.

[0316] Correspondingly, after dynamically adjusting the preset long-term electricity price function library, the characteristics of each power generation factor are used as input data in the adjusted dynamic electricity price function library to calculate the long-term transaction forecast electricity price of each related power plant.

[0317] S2203: Establishing the long-term transaction stack through the long-term transaction predicted electricity price of each of the associated power plants.

[0318] It can be seen from this that the first data vector generated by the actual power generation element characteristics of each associated power plant can effectively adjust the function operator in the preset electricity price function library, so as to predict the actual long-term trading electricity price for the associated power plant through the adjusted dynamic electricity price function library, so as to ensure the prediction accuracy of the long-term trading electricity price and obtain the long-term trading stack.

[0319] S303: establishing a spot transaction stack based on the spot transaction electricity price of each of the associated power plants, and determining a first clearing function through the long-term transaction stack and the spot transaction stack.

[0320] In the process of establishing the long-term transaction stack, the target power grid will synchronously receive the spot transaction electricity prices sent by the associated power plants. The target power grid can establish the corresponding spot transaction stack according to the size of the spot transaction electricity prices of each associated power plant. In this way, the first clearing function of the target power grid can be determined through the spot transaction stack and the long-term transaction stack.

[0321] For spot trading stack and long-term trading stack, please refer to Figure 3H , Figure 3H A schematic diagram of the stack structure of a spot trading stack and a long-term trading stack provided for an embodiment of the present application, as shown in the figure, the stack is divided into three levels according to the electricity price, and is gradually increased and divided into different levels of top, middle and bottom according to the electricity price. Among them, each layer considers different energy types (such as photovoltaic, wind power) and market types (spot trading, long-term trading). The adjustment mechanism for the stack is represented on the side of the stack, which optimizes the overall electricity price and electricity distribution by reducing or increasing the transaction volume and balancing between spot trading and long-term trading.

[0322] In actual application scenarios, the spot trading electricity prices of various related power plants often have various types, such as hourly quotations, block quotations, etc. The spot trading electricity price is calculated by the spot trading electricity price calculation formula set by the power plant itself. Taking the calculation of hourly quotations by hydropower plants as an example, the calculation formulas for hourly quotations are as follows:

[0323] Hydropower Plant:

[0324]

[0325] Q m3 =PR 实 ×P m (1.2)

[0326] In the formula, m is the mth hydropower station in the cascade hydropower station, i is the i-th unit in the mth hydropower station; m and i are both integers not less than 1; Q in formula (1.1) m2 represents the actual income corresponding to the potential electricity of the hydropower station at the current moment; Q in (1.2) in the target formulam3 represents the actual power generation income corresponding to the actual power generation of the hydropower station at the current moment, G i额 represents the rated power of the i-th unit, H im represents the water level duration of the i-th unit, F iJm represents the derated power of the i-th unit, H iZm represents the duration of interruption during the water level period of the i-th unit, P im The power generation during the water level period of the i-th unit, PR 实 represents the actual transaction price of all units, P m The power generation of all units during the water level period.

[0327] As can be seen from the foregoing, operator functions for calculating the spot trading electricity prices of each associated power plant are pre-stored in the preset electricity price function library. In actual application scenarios, the spot trading electricity prices of associated power plants are determined by their own power generation costs, and in different regions, different time periods (unit performance decays with age), and even different seasons, there are large differences in the power generation costs of different associated power plants. Therefore, in order to accurately predict the long-term trading electricity prices of associated power plants, it is necessary to perform data-driven adjustments to the function indicators in the preset electricity price function library through the first data vector generated by the characteristics of the power generation elements, so as to adjust the function indicators in each operator function, thereby improving the prediction accuracy of the long-term trading electricity price.

[0328] In addition, in the process of establishing a spot transaction stack, it is necessary to construct it through the two dimensions of the spot transaction electricity price and the power generation of the associated power plant. Next, the process of establishing the spot transaction stack will be introduced in conjunction with the specific embodiment drawings. Fig. 3I , which is a flow chart of a method for establishing a spot transaction stack provided in an embodiment of the present application, and specifically includes the following steps:

[0329] S3031: Perform power forecasting according to the first data vector of each of the associated power plants to obtain the predicted power of each of the associated power plants.

[0330] As can be seen from the foregoing, in the first data vector corresponding to the associated power plant, multiple power generation factor characteristics that affect the power generation efficiency of the associated power plant are collected. By performing power forecasting based on the first data vector, the power generation of the associated power plant within a certain period of time can be predicted.

[0331] Specifically, in the process of predicting the power generation based on the first data vector, the neural network model can be used to predict the power generation of the associated power plant within a certain period of time. Here, a wind power plant is used as an example. For details, please refer to Figure 4A , Figure 4A A schematic diagram of power prediction based on a wind power plant provided in an embodiment of the present application.

[0332] As can be seen from the figure, the global forecast data, regional actual data and station observation data of the wind power plant in the historical time period are used as the training data of the model, so as to predict the power generation of the wind power plant through the trained neural network model. Correspondingly, the model can output the meteorological forecast results and the corresponding power forecast results of the wind power plant. Through the meteorological data and power forecast data within a certain period of time, the power generation of the wind power plant can be effectively predicted according to the main characteristics that affect the power generation performance of the wind power plant.

[0333] In addition, for the power forecast of the associated power plant, a time series forecasting model (ARIMA) or a machine learning method (such as random forest, XGBoost) can be used. For the first data vector with a complex data structure in this application, a deep learning model such as LSTM (Long Short-Term Memory) can be used to analyze the temporal relationship in the step sequence data.

[0334] LSTM (Long Short-Term Memory) is a special recurrent neural network (RNN) architecture that aims to solve the gradient vanishing and gradient exploding problems faced by ordinary RNNs when processing long sequence data. LSTM can effectively capture long-term dependencies in sequences by introducing memory units and gating mechanisms.

[0335] S3032: Establishing a preliminary spot transaction stack according to the predicted power volume of each of the associated power plants.

[0336] After obtaining the predicted power for each associated power plant, the call priority of each associated power plant when calling for power can be determined through the size of the predicted power of each associated power plant, so as to establish a preliminary spot trading stack. For example, taking the associated power plants as wind power, photovoltaic power, hydropower, thermal power and nuclear power as an example, the predicted power of each power plant is (100, 50, 30, 60, 20) respectively. Through the predicted power of each associated power plant, a preliminary spot trading stack can be established based on the size of the predicted power, that is, (wind power, thermal power, photovoltaic power, hydropower, nuclear power).

[0337] S3033: Based on the spot transaction electricity price of the associated power plant, the preliminary spot transaction stack is adjusted to obtain the spot transaction stack.

[0338] On the basis of establishing a preliminary spot trading stack based on the predicted power of each associated power plant, the preliminary spot trading stack is further adjusted through the spot trading electricity price calculated by the spot electricity price calculation formula inside each associated power plant, so that the two-dimensional preliminary spot trading stack is transformed into a three-dimensional spot trading stack containing spot trading electricity prices. In this way, when there is insufficient power generation or excessive power generation of an associated power plant, the method of taking out the upper stack of the stack and rebuilding the stack is followed, starting from the power generation of the associated power plant and the actual spot trading electricity price, the spot trading stack is dynamically adjusted, thereby improving the accuracy of power grid clearing.

[0339] For example, the spot trading stack can be found at Figure 4B Schematic diagram of the spot trading stack shown.

[0340] It should be noted that in the scenario of establishing a spot trading stack, the weight of the predicted power in establishing the stack is greater than the weight of the spot trading electricity price. That is, when the spot trading electricity prices of two associated power plants are the same, the associated power plant with a larger predicted power will be placed in a relatively higher priority position in the spot trading stack to ensure the power supply stability of the target power grid.

[0341] S104: Determine, according to the first clearing function, a power supply and demand balance state of the target power grid when clearing under the first clearing function.

[0342] Correspondingly, the target power grid is controlled to clear electricity based on the determined first clearing function, and the power supply and demand balance state of the target power grid can be determined according to the total power generation and total load of the target power grid when clearing based on the first clearing function. When the total power generation of the target power grid is greater than the total load, it indicates that the target power grid is in an over-power generation state, which means that the current power generation of the target power grid exceeds the actual power demand and there is a problem of excess power. When the total power generation of the target power grid is less than the total load, it indicates that the target power grid is in an under-power generation state, which means that the current power generation of the target power grid cannot meet the actual power demand and the power supply needs to be supplemented in time.

[0343] For details, please refer to Figure 4C The graph shows a curve diagram of a power grid clearing function, in which the horizontal axis represents the change in power supply, and the vertical axis represents the change in electricity price. The power dispatch priority shown in the figure is: wind power / photovoltaic power>hydropower with storage capacity>nuclear power>coal power>gas power.

[0344] When the power supply curve is higher than the power demand curve, it means that the power supply of the power grid exceeds the demand, which may lead to a rise in electricity prices. Correspondingly, when the power supply curve is lower than the power demand curve, the power demand exceeds the supply, which may lead to an increase in electricity prices.

[0345] By determining the power supply and demand balance state of the target power grid under the first clearing function, the undergeneration state or overgeneration state of the target power grid under the current first clearing function can be characterized, so as to control the long-term transaction stack and the spot transaction stack according to the actual power supply and demand balance state of the target power grid in the future, thereby realizing the clearing adjustment for the power grid and ensuring the clearing accuracy of the power grid.

[0346] S305: Adjusting the first clearing function according to the power supply and demand balance state to obtain a second clearing function, and clearing power based on the second clearing function.

[0347] Finally, according to the overgeneration state or undergeneration state of the target power grid under the first clearing function, the first clearing function is adjusted, that is, the clearing function of the target power grid can be adjusted according to the actual power generation situation of the target power grid, thereby improving the accuracy of power grid clearing.

[0348] Next, the adjustment method for the first clearing function in different power supply and demand balance states will be introduced in conjunction with the specific embodiment drawings. Figure 4D and Figure 4E , Figure 4D A flowchart of another power grid clearing method provided in an embodiment of the present application is provided. Figure 4E The flowchart of the first clearing function adjustment method when the target power grid is in an over-generation state is shown in FIG. 1 , which specifically includes the following steps:

[0349] S3051: When the power supply and demand balance state is the over-power generation state, a high-level abstract processing is performed on the characteristics of each power generation element through a preset deep learning model to obtain a second data vector of each associated power plant.

[0350] In actual application scenarios, long-term transaction electricity prices are often determined by long-term contracts between the target power grid and the associated power plants, while spot transaction electricity prices are often affected by the immediate supply and demand conditions. Therefore, long-term transaction electricity prices are often lower than spot transaction electricity prices. When the power supply and demand balance state of the target power grid is in an over-generation state, the total power generation of the target power grid is greater than the total load demand of the target power grid.

[0351] In order to reduce the cost of power dispatch as much as possible and improve the accuracy of power grid clearing, when the target power grid is in an overgeneration state, since the total power generation of the target power grid is greater than the total charge at this time, by increasing the first long-term transaction volume in the first clearing function, the proportion of long-term transaction volume in the clearing function can be increased, thereby effectively reducing the cost of power clearing and improving the accuracy of power clearing.

[0352] Therefore, in order to ensure the accuracy of adjustments for long-term trading volume, it is necessary to use a pre-set deep learning model to perform high-order data abstraction processing on the power generation factor characteristics of the associated power plants to obtain the second data vector that affects the power generation efficiency of each associated power plant.

[0353] Different from the low-order data abstraction processing of the characteristics of power generation factors through the energy consumption data model, which only involves the feature screening and combination of the characteristics of power generation factors, the high-order data abstraction processing involves the combination calculation between the characteristics of each power generation factor, so as to calculate the data vector that has a core influence on the power generation performance of the associated power plant.

[0354] For details, please refer to Figure 4F A schematic diagram of calculating a second data vector through a deep learning model is shown, in which a hydropower plant is used as an example of an associated power plant. Among them, parameters such as power generation and water consumption for power generation are the power generation factor characteristics of the hydropower plant, and the Top, Qm' and average power plant revenue of the hydropower plant are parameters calculated by power generation and water consumption for power generation. These need to be calculated through the power generation factor characteristics to obtain the relevant parameters, which is the above-mentioned process of performing high-level abstract processing on the power generation factor characteristics based on the preset reinforcement learning model to obtain the second data vector. In the preset reinforcement learning model provided in the embodiment of the present application, a plurality of different types of parameter calculation formulas are pre-set. When the power generation factor characteristics are subjected to high-level data abstract processing through the preset reinforcement learning model, the parameters are calculated through the preset calculation formula and the power generation factor characteristics, and the calculated results are integrated to obtain the second data vector.

[0355] Compared with linear models, deep learning has stronger nonlinear modeling capabilities, which can simulate the complex nonlinear relationship between the characteristics of various power generation elements in the associated power plant. Therefore, by presetting the high-order data abstraction processing of the deep learning model for the characteristics of the power generation elements, complex features can be further extracted from the original data to obtain a second data vector that can accurately characterize the power generation performance of the associated power plant.

[0356] S3052: Determine the long-term transaction volume increase value according to each of the second data vectors and the preset long-term electricity price function library.

[0357] S3053: Adjust the first long-term transaction volume according to the long-term transaction volume increase value to obtain the second clearing function.

[0358] Furthermore, after determining the second data vector of each associated power plant, the function index in the preset long-term electricity price function library is adjusted based on the second data vector, and the specific index value of the long-term electricity price function can be changed, thereby determining the new long-term transaction volume of the target power grid. By comparing this new long-term transaction volume with the long-term transaction volume in the first clearing function, the increase in the long-term transaction volume can be determined, and the corresponding second clearing function can be obtained.

[0359] Depend on Figure 4D It can be seen that when the target power grid is in an overgeneration state, the high-order data abstraction processing of the power generation element characteristics of the associated power plants is performed through the preset deep learning model, which can determine the added value of the long-term transaction volume, and then adjust the subsequent long-term transaction stack, thereby realizing the adjustment of the first clearing function and obtaining the second clearing function.

[0360] Next, the process of adjusting the first clearing function when the target power grid is in an under-generation state will be described in conjunction with the accompanying drawings of the specific embodiment. Figure 4G , which is a flow chart of a first clearing function adjustment method when a target power grid is in an under-generation state provided by an embodiment of the present application, specifically comprising the following steps:

[0361] S3054: When the power supply and demand balance state is the under-generation state, with respect to the first power generation curve of the target power grid when clearing based on the first clearing function, the first power generation curve is fitted by a preset fitting function to obtain a fitted power generation curve.

[0362] When the target power grid is in a state of under-generation, it indicates that the total power generation of the target power grid is lower than its total load. It is understandable that in the dual trading stack composed of the long-term trading stack and the spot trading stack, since the long-term trading electricity price in the long-term trading stack is often slightly lower than the spot trading electricity price in the spot trading stack, the long-term trading electricity in the long-term trading stack can be dispatched first. In this case, if the target power grid is still in a state of under-generation, it indicates that the target power grid still cannot meet the load demand when fully calling the long-term trading electricity in the long-term trading stack.

[0363] Therefore, in this case, it is necessary to meet the demand for power load by increasing the spot trading volume. In order to ensure the accuracy of the added value of the spot trading volume, before calculating the added value of the spot trading volume, it is first necessary to fit the first power generation curve of the target power grid based on the first clearing function based on the preset fitting function, so as to convert the complex and discrete power generation data into a continuous function model, thereby simplifying the data storage and analysis process and improving data processing efficiency. At the same time, through the fitted power generation curve obtained after fitting, the trends and patterns in the power generation data can be more clearly identified, so as to facilitate the subsequent optimization of the clearing function.

[0364] Specifically, the formula of the preset fitting function is as follows:

[0365] PR*S=P;

[0366] PR=A+BH T -CH T 2 ;

[0367] In the formula, PR represents the power conversion efficiency of the power plant, H T represents the power generation efficiency adjustment factor, S represents the primary indicator affecting the power generation efficiency of the associated power plant, P represents the fitting coefficient, A, B, C represent the characteristic constants calculated by the deep learning model, which are used to characterize the performance characteristics corresponding to different power plants.

[0368] In the above formula, H T The power of represents the influence of this feature on the power generation performance of the associated power plant. Correspondingly, the formula for H T The positive and negative signs of the preceding influences represent the positive or negative influence of the corresponding features on the power generation efficiency of the power plant. Thus, through the above formula, the fitting accuracy of the first power generation curve can be effectively improved, thereby ensuring the accuracy of the power grid clearing.

[0369] It is understandable that for different associated power plants, the data type corresponding to S will also be different. For example, when PR represents the power conversion efficiency of a photovoltaic power plant, S is related to the illuminance of the photovoltaic power plant. Similarly, when PR represents the power conversion efficiency of a thermal power plant, S is related to the coal quality of the thermal power plant.

[0370] By calculating the fitting coefficients P of the target power grid corresponding to all associated power plants, the first power generation curve of the target power grid can be effectively fitted, thereby improving the accuracy of the first power generation curve.

[0371] For details, please refer to Figure 4H , Figure 4H A schematic diagram of a target power grid fitting power generation curve provided for an embodiment of the present application, as shown in the figure, the top-most power generation curve in the figure is a preset power generation curve, and the curve that closely fits the preset power generation curve is the fitted power generation curve when the target power grid is cleared based on the first clearing function and after fitting processing. It can be seen that after fitting the first power generation curve with the preset fitting function, the fitted power generation curve is closer to the preset power generation curve, and by comparing the preset power generation curve with the fitted power generation curve, the spot transaction volume that needs to be supplemented can be accurately determined, thereby ensuring the stability of power grid clearing.

[0372] S3055: Based on the fitted power generation curve and the preset planned power generation curve, determine whether the first spot transaction volume satisfies the preset planned power generation curve.

[0373] Subsequently, the fitted power generation curve is compared with the preset planned power generation curve to determine whether the first spot transaction volume in the first clearing function can meet the preset planned power generation curve. The preset planned power generation curve is used to represent the power generation curve expected by the target power grid for the current power load. By comparing the two, it can be determined whether the first spot transaction volume of the target power grid in the first clearing function is sufficient.

[0374] See also Figure 4H As shown in the figure, the fitted power generation curve in the figure is lower than the preset power generation curve, that is, the power generation of the fitted power generation curve is lower than the power generation of the preset power generation curve. At this time, there is a certain gap between the fitted power generation curve and the preset power generation curve. It can be determined that the power generation curve of the target power grid under the first clearing function cannot meet the requirements of the preset power generation curve. Therefore, it can be determined that the first spot trading volume in the first clearing function cannot meet the preset planned power generation curve, and additional spot trading volume is needed.

[0375] S3056: When the first spot trading volume does not satisfy the preset planned power generation curve, the preset long-term electricity price function library is modified by a preset reinforcement learning model to determine a long-term trading volume reduction value.

[0376] Correspondingly, when the first spot trading volume does not meet the preset planned power generation curve, it indicates that the first spot trading volume of the target power grid at this time cannot meet the current power load. Therefore, in order to meet the current power load by increasing the spot trading volume, it is necessary to correct the preset long-term electricity price function based on the preset reinforcement learning model to obtain the long-term trading volume reduction value. In this way, the spot trading volume increase value can be determined by reducing the proportion of long-term trading volume, so as to ensure the smooth clearing of the power grid.

[0377] Among them, the preset reinforcement learning model can adopt MARL (Multi-agent Reinforcement Learning). MARL is a method for dealing with reinforcement learning problems in a multi-agent environment. Each participant (such as different associated power plants) can be regarded as an agent, and these agents need to adjust their bidding strategies based on real-time market data and the behavior of other agents. MARL can help these agents learn and adapt under complex and dynamically changing market conditions to improve the clearing accuracy of the power grid.

[0378] Specifically, in the process of modifying the preset long-term electricity price function library, the first long-term trading electricity price function with the greatest impact on the overall long-term trading electricity price can be screened out from the preset long-term electricity price function library through the screening mechanism of the reinforcement learning model.

[0379] Subsequently, the function index in the first long-term transaction electricity price function is adjusted and increased to increase the long-term transaction electricity price, thereby achieving the effect of reducing the long-term transaction volume and obtaining the long-term transaction volume reduction value.

[0380] Here we take a thermal power plant as an example. As we can see from the previous article, the long-term transaction electricity price calculation function of a thermal power plant is:

[0381] By adjusting the function index in the long-term transaction electricity price calculation function and increasing the long-term transaction electricity price, the effect of reducing the long-term transaction volume can be achieved, and the long-term transaction volume reduction value can be obtained.

[0382] S3057: Adjust the proportion of the spot trading volume in the first clearing function according to the long-term trading volume reduction value to obtain the spot trading volume increase value.

[0383] S3058: Adjust the first spot trading volume according to the spot trading volume increase value to obtain the second clearing function.

[0384] On the basis of determining the long-term trading volume reduction value, the proportion of the spot trading volume in the first clearing function is increased to obtain the spot trading volume value. In this way, the first spot trading volume in the first clearing function can be adjusted by the spot trading volume increase value to obtain the second clearing function.

[0385] The embodiment of the present application provides a method for clearing a power grid, in which, first, low-order data abstraction processing is performed according to the power generation element characteristics of each associated power plant, and multiple factors affecting the clearing of the power grid are quantified into a first data vector, thereby reducing the data complexity of the power generation element characteristics. Subsequently, a long-term transaction electricity price forecast is performed according to the first data vector and a preset long-term electricity price function library, so as to predict the corresponding long-term transaction electricity price according to the actual power generation element characteristics of each associated power plant, and establish a corresponding long-term transaction stack, so as to improve the accuracy of the clearing of the power grid by ensuring the accuracy of the long-term transaction electricity price. Further, a spot transaction stack is established based on the spot transaction electricity price of each associated power plant, and a first clearing function is determined by the long-term transaction stack and the spot transaction stack. Accordingly, according to the determined first clearing function, the power supply and demand balance state of the target power grid when clearing under the first clearing function is determined, and the first clearing function is adjusted in real time according to the actual power supply and demand balance state of the target power grid to obtain a second clearing function. In this way, the clearing function of the target power grid can be dynamically adjusted according to the supply and demand status of the target power grid. Through the transaction stack constructed in real time by the long-term transaction electricity price and the spot transaction electricity price, a specific clearing function can be established, so that the clearing of the power grid can effectively consider the impact of the characteristics of the power generation factors on the power generation of the associated power plants, as well as the changes in the spot transaction electricity prices of the associated power plants, and then determine a more accurate clearing function, thereby achieving the effect of improving the accuracy of the power grid clearing. In this scheme, in order to better illustrate its data-driven, measured data is used to fit the power forecast curve of the dispatch. The clearing agent quantifies the electricity price and electricity volume, as well as the long-term and short-term electricity prices, so that the algorithms in the data and information flow can be clarified. This intelligent agent needs to be constructed to realize the determination and clearing of electricity prices. The algorithm, that is, the neural network, needs to be selected according to the characteristics of the data and information flow.

[0386] Embodiment 3

[0387] In the third embodiment, the power function requirement for realizing the dispatching control of the power plant side by the power grid side is specifically the peak-shaving dispatching in the high-frequency variable load scenario of thermal power, and the functional operator is the thermal power peak-shaving dispatching operator, which is used to realize the peak-shaving dispatching in the high-frequency variable load scenario of thermal power. The third embodiment introduces the process of using the intelligent agent constructed based on the thermal power peak-shaving dispatching operator in the digital power system.

[0388] In the scenario where thermal power generation and renewable energy generation are carried out in parallel, the load of thermal power generation changes frequently due to the instability of renewable energy generation. Under the condition of high-frequency load changes in thermal power scenarios, there is currently a lack of supporting peak-shaving scheduling solutions with digital calculation costs, making it difficult to implement peak-shaving scheduling safely and stably, which can easily affect the life of the power system. How to ensure the life of the power system is a key issue. In view of this, the inventor proposes that a digital power system based on a multifunctional intelligent body uses a thermal power peak-shaving scheduling operator to implement a peak-shaving scheduling method in a thermal power high-frequency load change scenario. Based on a variety of data fed back by thermal power plants, the load capacity, performance, cost and thermal power load demand changes of thermal power units can be taken into account. By using digital technology, the relationship between the cost of the power plant and the thermal power load changes can be analyzed, thereby ensuring the safety and stability of peak-shaving scheduling.

[0389] Figure 5A A power supply scenario is shown. Figure 5A As shown in the figure, this power supply scenario involves multiple power generation methods, including thermal power generation and photovoltaic power generation. Among them, photovoltaic power generation, as a new energy power generation method, has gradually increased its share in the energy consumption structure due to its zero emission, zero pollution, and sustainability. However, compared with thermal power generation, photovoltaic power generation has more prominent instability. For this reason, Figure 5A In the power supply scenario shown, the thermal power plant that generates electricity through thermal power needs to change the load frequently. In the specific implementation, the thermal power plant needs to cooperate with the peak load regulation on the grid side. Figure 5A For example, Figure 5A The left side shows three thermal power plants, each of which can store and release electricity. The thermal power plants transmit the released electricity through their own electrical connection with the power grid, and this electricity ultimately serves thousands of households that purchase electricity from the power grid.

[0390] Each thermal power plant generally has multiple thermal power units, and the equipment performance, supporting completeness, maintenance costs, etc. of each thermal power plant are often different. Furthermore, the equipment durability, safety attributes, climbing ability to cooperate with peak-shaving scheduling, power generation costs, etc. of each thermal power unit are often different. For thermal power plants, when cooperating with peak-shaving scheduling, it is necessary to pay attention to whether the thermal power units will cause operating losses due to cooperating with peak-shaving scheduling; in addition, it is necessary to determine whether they can cooperate with peak-shaving conditions. For the power grid side, it is necessary not only to combine the quotations of each unit in the thermal power plant and the unit's own capabilities and performance, but also to consider many aspects in scheduling, so as to ensure the safe and stable implementation of peak-shaving scheduling.

[0391] Figure 5B A flowchart of a peak load scheduling method for a thermal power plant with a high frequency variable load is provided in an embodiment of the present application. Figure 5C This is a signaling interaction diagram of a peak load scheduling method in a thermal power plant with high frequency load variation scenario. Figure 5B In this paper, the implementation of the scheme is mainly introduced from the perspective of thermal power plants. Figure 5C In the demonstration, the solution is implemented through interactive introduction on both sides (power plant side and grid side).

[0392] like Figure 5B As shown, the embodiment of the present application provides a peak load scheduling method in a thermal power high frequency variable load scenario, including:

[0393] S501. Calculate the heat storage margin of the energy storage device in the thermal power plant.

[0394] Each thermal power plant is equipped with energy storage devices. The energy storage devices store the heat generated by the coal combustion of the thermal power units and release it when needed. The heat is converted into electrical energy and transmitted to the power grid. In a possible implementation, the energy storage devices in the thermal power plant include but are not limited to: boilers, steam turbine systems, heaters, deaerators, etc.

[0395] The heat storage and access margin of each energy storage device is divided into two different types, one is the heat storage margin characterization value, and the other is the heat release capacity characterization value. The heat storage margin characterization value is used to indicate the ability of the energy storage device to further store heat. The heat release capacity characterization value is used to indicate the ability of the energy storage device to further release heat. The heat storage margin characterization value can be expressed by a specific heat value or by a percentage compared to the rated storage heat. Similarly, the heat release capacity characterization value can be expressed by a specific heat value or by a percentage compared to the pre-rated storage heat. Both the heat storage margin and the heat release capacity are related to the size and performance of the unit.

[0396] The heat storage and access margin of the energy storage devices in the thermal power plant reflects the current output capacity of the thermal power plant from the two aspects of "storage" and "access". In the specific implementation, according to the actual needs of the power grid, the heat storage margin can be counted according to two different dimensions. For example, statistics can be made according to the dimensions of "day before" and "day". The thermal power plant provides the heat storage and access margin of the energy storage device the day before, so that the power grid can prepare in advance according to the heat storage and access margin the day before and carry out orderly peak-shaving scheduling. The thermal power plant provides the heat storage and access margin of the energy storage device within the day, so that the power grid can realize accurate, flexible and reliable peak-shaving scheduling based on high real-time data according to the heat storage and access margin within the day.

[0397] In a possible implementation, the heat storage margin sent by the thermal power plant to the power grid side can be specifically refined to the heat storage margin corresponding to each thermal power unit of the thermal power plant. It should be noted that the heat storage margin can be calculated by the thermal power plant based on the coal type parameters of the selected target coal type and the thermal system design. The choice of coal type affects heat consumption and coal consumption. Table 2 is a data table of a digital selection model for coal types. In Table 2, test items for various types of coal such as GEB 5200, GEB 4800, GEB4700, etc. are shown. Here, the test items can also be regarded as the coal type parameters mentioned above. These coal type parameters include but are not limited to total moisture, air dried basis moisture, received basis ash, dry ash-free basis powdering, received basis carbon, received basis hydrogen, total sulfur, low calorific value, etc. In Table 2, LHV represents the low calorific value of the coal type, and HHV represents the high calorific value of the coal type.

[0398] Table 2

[0399]

[0400] The digital selection model of coal types can realize the selection of coal types by extracting features from the data shown in Table 2. Because the H (hydrogen) part of carbon combines with oxygen to produce water in the physical combustion of the boiler, this part of water absorbs a large amount of heat called "latent heat of vaporization", so it is a relatively important factor in coal selection. This hydrogen content is measured by the percentage difference between HHV and LHV associated with it, as shown in the last row of data in Table 2. The smaller the value, the smaller the heat loss of latent heat of vaporization, the more heat generated by unit coal for power generation, and the better the economic benefits. In practical applications, by using the digital selection model of coal types, according to the high calorific value and low calorific value corresponding to each of the multiple coal types to be selected, the percentage difference between the high and low calorific value of each coal type to be selected is obtained (this value can be understood as a low-order abstract feature); the coal type with the smallest percentage difference between the high and low calorific value among the multiple coal types to be selected is determined as the target coal type. Taking Table 2 as an example, the coal type GEB 5200 has the smallest percentage difference between high and low calorific values, which is 5.90%. Therefore, the coal type GEB 5200 can be selected as the target coal type. By selecting the coal type with the smallest percentage difference between high and low calorific values ​​as the target coal type, the heat generated by unit coal can be maximized.

[0401] The calculation formulas for the higher calorific value HHV and lower calorific value LHV of coal are as follows:

[0402] HHV=LHV+25*M+25*9*H

[0403] M is the total water content of coal, and H is the basic hydrogen content of coal. In the above formula, the units of HHV and LHV are both kcal / kg. In one example, M=23, H=4.21. It should be noted that in the above formula, when it is necessary to convert between the heat unit kcal and kJ, the values ​​of M and H need to be converted according to the conversion coefficients of different heat units.

[0404] S502, sending the correlation data between the load, performance and cost of each thermal power unit in the thermal power plant and the heat storage and access margin to the power grid side, so that the power grid side can determine the target units for expected auxiliary peak load regulation and issue peak load regulation scheduling instructions based on the changes in thermal power load demand, the correlation data provided by each thermal power plant and the heat storage and access margin.

[0405] In order to facilitate the data acquisition, data analysis and peak-shaving scheduling of each thermal power plant and each thermal power unit on the power grid side, in this application, each thermal power plant needs to provide its own data to the power grid side. In specific implementation, the thermal power plant sends the associated data between the load, performance and cost of each thermal power unit to the power grid side, and sends the heat storage and access margin calculated in step S501. It should be noted that in the embodiment of the present application, the associated data sent by the thermal power plant to the power grid side is also calculated based on the coal type parameters of the selected target coal type.

[0406] Table 3 is a parameter table of heat consumption, coal consumption and electricity price under different loads. As shown in the first column of Table 3, a variety of different power plant loads are displayed (for example, 100% load, 95% load, 65% load, 45% load, etc.). As shown in columns 2 to 24 of Table 3, various heat consumption, coal consumption and system parameters under different loads are displayed. Combined with what is shown in Table 3, under the high-frequency variable load scheduling, the actual power consumption rate of the thermal power plant (column 7 of Table 3) and the like are constantly changing. For example, under 100% power plant load, the actual value of the power consumption rate is 5.71%, and under 45% power plant load, the actual value of the power consumption rate is 7.37%.

[0407] By reporting the data shown in Table 3 to the power grid, the power grid has the load conditions and thermal energy conditions of each thermal power plant, and can better classify and aggregate the data, so that different weights and priority calls can be given to the units according to the unit conditions and heat storage and access margins. Since the calculation in this process is affected by multiple variables, the features extracted from the data shown in Table 3 can be called mid-order data abstract features (abbreviated as mid-order features). The mid-order data abstract features are transmitted by the chain rule, reflecting the energy consumption level and thermal energy reserve level of the power plant, and assisting in the peak-shaving scheduling under the high-frequency variable load scenario of thermal power.

[0408] Table 3

[0409]

[0410] Table 4 shows the electricity price and cost data of a selected target coal type under different working conditions (power plant load). The grid compensation coefficient for 1 kWh of electricity payment is the grid electricity price (excluding limestone cost), which is the fuel part of the capacity price, which generally accounts for more than 50% of the entire electricity price.

[0411] The example calculation formula for the grid compensation coefficient for 1 kWh of electricity payment is as follows:

[0412] CERm=U*N / E(1-AUX)

[0413] Among them, U represents the coal price, which is also the fuel cost subsidy, in US dollars per ton (expressed as USD / t). As an example, U = 69USD / t. E represents the unit power generation heat consumption rate, that is, the heat consumption of the unit per kilowatt-hour of electricity, in kcal / kWh. N represents the specific heat index, specifically the heat required per kilowatt-hour of electricity, in kcal / kWh, and AUX represents the plant power consumption rate, in %.

[0414] In Table 4, SHRW represents the weighted specific heat index, in kJ / (kW·h). Ea represents the power supply (or power generation), in kW·h. Ep represents the power consumption and electricity fee, in USD.

[0415] SHRcc is the specific heat index, in kJ / (kW·h). U is the coal price, in USD / t. ECRm is the electricity cost per kilowatt-hour, in USD / (kW·h). ECRm represents the electricity charge ratio, that is, the coal cost per kilowatt-hour of electricity produced, in USD / (kW·h). It should be noted that if the load is evenly distributed every day in a month, the weighted specific heat index is equal to the weighted index, that is, SHRW=SHRcc.

[0416] The calculation formula of ECRm is:

[0417] ECRm=SHRcc×(1 / HHV)×U / 1000

[0418] The calculation formula of Ep is:

[0419] Ep=NEOm*CERx

[0420] In the above formula, NEOm represents net electricity generation, in kW·h. CERx represents electricity price, in USD / (kW·h).

[0421] As shown in Table 4, through the correlation between different values ​​of electricity prices and loads, the cost reflected by the fuel of each thermal power plant in the power grid can be given, so that the power grid can extract the unit performance, environmental protection and fuel cost of the power plant under different load conditions based on these data. The extracted features affected by multiple variables (including coal cost price) are called high-order abstract features. The linear high-order features generated by integrating coal price cost on the basis of mid-order features include the correlation between fuel, electricity and electricity price.

[0422] That is to say, in the technical solution of the present application, the grid side determines the target unit for expected auxiliary peak-shaving and issues peak-shaving scheduling instructions based on the changes in thermal power load demand, the related data provided by each thermal power plant, and the heat storage and access margin, including: the grid side extracts intermediate-order features based on the related data provided by each thermal power plant and the heat storage and access margin, and the intermediate-order features include features reflecting the energy consumption level and thermal energy reserve level of the power plant; the grid side integrates the coal price cost in the related data and the intermediate-order features to obtain high-order features, and the high-order features include the relationship between fuel, electricity and electricity price; the grid side determines the target unit for expected auxiliary peak-shaving and issues peak-shaving scheduling instructions based on the changes in thermal power load demand, the intermediate-order features and the high-order features.

[0423] It can be seen from Table 4 that the higher the load, the smaller the number of the grid compensation coefficient for 1 kWh of electricity payment, which means the lower the fuel cost. The lower the fuel cost under the same operating conditions, the better the unit performance and the lower the coal consumption. To this end, the grid side can know the performance of different thermal power units by comparing the fuel costs of different thermal power units under the same operating conditions (such as the grid compensation coefficient for 1 kWh of electricity payment shown in Table 4). For example, when thermal power unit A is at 100% load, the grid compensation coefficient for 1 kWh of electricity payment is 0.0311USD / (Kw·h); when thermal power unit B is at 100% load, the grid compensation coefficient for 1 kWh of electricity payment is 0.0319USD / (Kw·h), and the coal types selected by the two units are the same. By comparing this coefficient, it can be known that the performance of thermal power unit A is better than that of thermal power unit B.

[0424] Table 4

[0425]

[0426] Based on the data reported by each thermal power plant (including the correlation data between the load, performance and cost of each thermal power unit in the thermal power plant, as well as the heat storage and access margin, etc., where the correlation data can be combined with the examples in Table 3 and Table 4), the power grid side can have a full understanding of the thermal power units of each thermal power plant. Based on this, the power grid side can exercise the peak-shaving scheduling function. In specific implementation, the power grid side can determine the target unit for expected auxiliary peak-shaving based on the changes in thermal power load demand, the correlation data provided by each thermal power plant, and the heat storage and access margin, and then issue peak-shaving scheduling instructions to the target unit.

[0427] Before the grid side determines the target unit for the expected auxiliary peak-shaving dispatch, the grid side can send the peak-shaving load curve for each thermal power unit to each thermal power plant. In an example implementation, the peak-shaving load curve is in a two-dimensional form, with the horizontal axis representing time and the vertical axis representing power. The peak-shaving load curves for different thermal power units may be different. The peak-shaving load curve essentially expresses the load requirements for the thermal power units.

[0428] The thermal power plant can determine the thermal power units that meet the requirements of the corresponding peak load curve according to the peak load curve of each thermal power unit, and calculate the quotation information of the auxiliary peak load service provided by such thermal power units. Since the peak load dispatch is an additional auxiliary work provided by the thermal power unit, a certain fee needs to be charged to the power grid. The amount of the charge is presented in the form of a quotation. The thermal power plant calculates the quotation information of providing auxiliary peak load service in combination with the performance of the thermal power unit, the requirements of the peak load curve, the type of coal burned, the coal consumption, heat consumption and other fuel information, fuel cost, equipment cost, etc. The quotation information is sent to the power grid side, so that the power grid side can compare and determine the expected auxiliary peak load units based on the quotation information, and call such units target units. The number of target units in a thermal power plant is uncertain. For example, thermal power plant A may have 3 thermal power units determined as target units; thermal power plant B may have 1 thermal power unit determined as target unit; thermal power plant C may have no target units determined. Combining Table 3 and Table 4, the grid side can use data-driven and deep learning functions to weigh costs and indicators based on changes in thermal power load demand, related data provided by each thermal power plant, heat storage and access margin, and quotation information reported by each thermal power plant, and determine the target units for the expected auxiliary peak-shaving services through data-driven and deep learning functions.

[0429] For example, each thermal power plant provides its own Table 3 data to the power grid, and the power grid makes a comparison and selection based on Table 3 uploaded by each thermal power plant. For example, the power grid knows that there is a plant A with a load of 95% and a plant B with a load of 60%, and the corresponding heat release capacity characterization values ​​of plant A and plant B are 70% and 80% respectively. In this case, it is necessary to issue a dispatch instruction based on the power grid's deep learning under this condition, focusing on whether the heat release capacity characterization value is prioritized or the load margin is prioritized, and select the unit to go online for power generation. This selection strategy is based on data-driven and deep learning historical data-driven, in order to avoid system safety hazards.

[0430] In a possible implementation, the power grid side can establish a typical load curve set after analysis and research based on the load rise and fall variation data of the thermal power units under various different working conditions, as well as the correlation data between the load, performance and cost of each thermal power unit. The peak load curve of the thermal power unit on the power grid side is selected from a pre-established typical load curve set. The thermal power plant calculates the quotation information of the auxiliary peak-shaving service provided by the thermal power units that meet the requirements of the corresponding peak load curve based on the peak load curve of each thermal power unit. More specifically, it can be based on the peak load curve of each thermal power unit and the power supply quality to generate the quotation information of the auxiliary peak-shaving service provided by the thermal power units that meet the requirements of the corresponding peak load curve. Considering the power supply quality while referring to the peak load curve can match the quotation with the power supply quality and avoid the problem of inflated quotation and poor power supply quality.

[0431] Figure 5D A flowchart for determining a target unit for expected auxiliary peak load regulation is provided in an embodiment of the present application. Figure 5D In order to determine the target unit for expected auxiliary peak load regulation, the technical solution of this application can combine the climbing coefficient and quotation information of each thermal power unit, and through data-driven weighing of costs and indicators, select the thermal power unit with suitable quotation as the target unit from multiple thermal power units expected to assist in peak load regulation. Figure 5D As shown, the process includes:

[0432] S5021. Based on the changes in thermal power load demand, the associated data provided by each thermal power plant and the heat storage and access margin, the grid side generates a peak load curve for each thermal power unit and calculates the climbing coefficient of each thermal power unit.

[0433] It is understandable that during the period of thermal power generation, since thermal power generation and renewable energy generation are carried out in parallel, the demand for thermal power load may fluctuate frequently. For example, the demand for thermal power load is low at noon and high at night; the demand for thermal power load is high during rainy periods and low during sunny days. Combined with the correlation data on load, performance and cost provided by each thermal power plant, it is possible to generate a peak load curve for each thermal power unit through feature extraction and other methods using artificial intelligence algorithm analysis. The peak load curve relies on the extraction and analysis of multi-level and multi-step data to realize a data-driven peak load scheduling scheme, the specific presentation of which includes the generated peak load curve.

[0434] Furthermore, in the technical solution of the present application, in order to select the target unit, the grid side can first calculate the climbing coefficient of each thermal power unit.

[0435] In the technical solution of this application, the climbing coefficient is a parameter used to measure the performance of a thermal power unit. The higher the climbing coefficient, the better the performance (climbing ability) of the thermal power unit, and the better it can perform the auxiliary peak load regulation work. The following is an exemplary method for calculating the climbing coefficient of a thermal power unit.

[0436] For a certain thermal power unit, in order to calculate its climbing coefficient, the grid side can extract the climbing speed, steam pressure and rated power generation capacity from the correlation data between the load, performance and cost of the thermal power unit. Then, according to the climbing speed, steam pressure, rated power generation capacity, heat storage and access margin of the thermal power unit and the climbing time required by the power plant side for the thermal power unit, the climbing coefficient of the thermal power unit is calculated. The following is an exemplary formula for calculating the climbing coefficient of a thermal power unit.

[0437] P=S*T*Q*C / R

[0438] In the formula, P is the climbing coefficient, S is the climbing speed, T is the climbing time required by the power grid, Q is the steam pressure, C is the heat storage margin, and R is the rated power generation capacity. Table 5 shows the operating conditions, climbing speeds, climbing time required by the power grid, steam pressure, heat storage margin, and calculated climbing coefficients of three different thermal power units (W1, W2, and W3). Among them, the steam pressure Q is expressed as a percentage of the rated pressure. Combined with the above formula, the calculation method of the climbing coefficient of the thermal power unit shown in the formula is: calculate the product of the climbing speed, climbing time, steam pressure, and heat storage margin of the thermal power unit; calculate the ratio of the product to the rated power generation capacity of the thermal power unit, and use the ratio as the climbing coefficient of the thermal power unit. The calculation of the climbing coefficient enables the capacity level of each thermal power unit to be quantitatively measured and compared horizontally with each other. The data-driven quantitative comparison of thermal power units enriches the theoretical basis of peak-shaving scheduling from a data level, and helps to achieve more reliable and orderly high-frequency peak-shaving scheduling.

[0439] Taking Table 5 as an example, in Table 5, the heat storage margin is represented by C. As one of the parameters for calculating the climbing coefficient of the thermal power unit, the C value can be specifically used to represent the heat release capacity characterization value in the heat storage margin. Taking Table 5 as an example, the C values ​​of unit W1, unit W2 and unit W3 are 90%, 50% and 20% respectively, which means: the heat release capacity characterization value of unit W1 is 90%, and the heat storage margin characterization value is 10%; the heat release capacity characterization value of unit W2 is 50%, and the heat storage margin characterization value is 50%; the heat release capacity characterization value of unit W3 is 20%, and the heat storage margin characterization value is 80%. In other words, for the same unit, the sum of its heat release capacity characterization value and heat storage margin characterization value is 100%.

[0440] Table 5

[0441]

[0442] S5022. Preliminarily determine a number of thermal power units that are expected to assist in peak load regulation based on the ramp coefficient of each thermal power unit.

[0443] In the embodiment of the present application, the power grid side can preliminarily determine multiple units based on the relative size of the climbing coefficient of the thermal power units, and expects these units to assist in peak load regulation. As shown in the last column of Table 5, thermal power units with different climbing coefficients can be rated (peak load scheduling level) according to the size of the climbing coefficient. For example, thermal power units with a climbing coefficient greater than or equal to 0.8 are classified as Class A; thermal power units with a climbing coefficient less than 0.8 but greater than or equal to 0.5 are classified as Class B; thermal power units with a climbing coefficient less than 0.5 are classified as Class C. In this way, a correspondence between thermal power units with different climbing coefficients and peak load scheduling levels is established.

[0444] In specific implementation, multiple thermal power units expected to assist in peak load regulation are preliminarily determined according to the peak load regulation dispatching level corresponding to each thermal power unit. For example, the power grid side can give priority to the thermal power units of grade A. If the thermal power units of grade A are still not enough for dispatching, the thermal power units of grade B can be further selected as the thermal power units expected to assist in peak load regulation.

[0445] S5023. Determine whether there is a thermal power unit among the multiple thermal power units expected to assist in peak load regulation whose quotation information is less than or equal to K times the threshold quotation. If yes, proceed to S5024; if not, proceed to S5025.

[0446] S5024. The thermal power unit is determined as the target unit for expected auxiliary peak regulation.

[0447] S5025. This thermal power unit is not selected as the target unit for expected auxiliary peak regulation.

[0448] It is understandable that if each thermal power unit needs to cooperate with the auxiliary peak-shaving service, it may generate heat consumption and energy consumption beyond the expected power generation task, which will bring certain cost expenditures. To this end, the thermal power unit can calculate the quotation and report it to the power grid. The power grid compares the quotation information reported by each thermal power unit with K times the threshold quotation. If the quotation is less than or equal to K times the threshold quotation, the power grid side believes that the quotation is relatively reasonable and can be tolerated. As shown in step S5024, such units can be designated as target units to assist in peak-shaving. On the contrary, if the quotation is higher than K times the threshold quotation, the power grid side believes that the quotation is too high and no longer prefers such units as target units.

[0449] Among them, the threshold quotation is the quotation reference value obtained by deep learning historical quotation information on the power grid side. In practical applications, the power grid side can comprehensively learn the historical quotation information of thermal power in high-frequency variable load scenarios, combine the historical quotation information and the performance and cost of the thermal power unit itself, and use data-driven to weigh the cost and indicators to analyze a reasonable quotation reference value. K is a coefficient greater than 1. In one example, K takes a value in the range of 1.1 to 1.3. For example, K takes a value of 1.3, that is, if the quotation information of the thermal power unit overflows by more than 30% compared to the threshold quotation, it is considered that it cannot be selected as the target unit. On the contrary, if the quotation information of the thermal power unit overflows by no more than 30% compared to the threshold quotation, it is considered that it can be selected as the target unit.

[0450] For the target unit, the grid side can send peak-shaving dispatch instructions to the thermal power unit to which the unit belongs.

[0451] S503: Receive a peak load dispatching instruction issued by the power grid side.

[0452] The peak-shaving dispatch instruction carries the unit identification of the target unit and the peak-shaving requirement information for the target unit. For example, the peak-shaving dispatch instruction carries the unit identification W1. After the thermal power plant receives the peak-shaving dispatch instruction, it can be known that the instruction is issued to the thermal power unit with the unit identification W1. If a thermal power plant contains multiple target units, the power grid side can send peak-shaving dispatch instructions to each thermal power unit in parallel. This group dispatch improves the peak-shaving efficiency. The peak-shaving dispatch instruction carries the unit identification, so the thermal power plant can accurately forward the peak-shaving requirement information.

[0453] S504: Execute auxiliary peak-shaving service based on the peak-shaving requirement information.

[0454] As mentioned above, the peak-shaving dispatch instruction carries the peak-shaving requirement information for the target unit. Specifically, the peak-shaving requirement information includes the peak-shaving load curve. In one possible implementation, the peak-shaving requirement information also includes climbing speed requirement information. The peak-shaving load curve makes requirements for the target unit from the perspective of load, while the climbing speed requirement information makes requirements for the target unit from the perspective of climbing speed. When the target unit receives the peak-shaving requirement information, it needs to make a judgment based on its own actual situation to confirm whether it can meet the above requirements.

[0455] Figure 5E A flowchart of a fault judgment and working condition judgment provided in the embodiment of the present application. Figure 5E , an implementation method of this step is introduced exemplarily.

[0456] like Figure 5E As shown, after identifying the peak load requirement information in the peak load scheduling instruction, first, the target unit of the thermal power plant determines whether it has equipment failure and communication failure, and determines whether the target unit meets the ramp speed requirement information. Specifically, it can be as follows Figure 5E As shown, first determine whether there is an equipment failure and a communication failure. After the determination is completed, based on the premise that there is no equipment failure and no communication failure, further determine whether the climbing speed requirement information is met. If there is no equipment failure and communication failure in the target unit (that is, there is neither equipment failure nor communication failure), and the target unit meets the climbing speed requirement information, then the auxiliary peak-shaving service is performed according to the peak-shaving load curve and the climbing speed requirement information in the peak-shaving requirement information. If there is an equipment failure or a communication failure in the target unit, it means that the target unit cannot cooperate to complete the auxiliary peak-shaving service in terms of hardware conditions or communication conditions, then the thermal power plant needs to report the fault message of the thermal power unit to the power grid side, so that the power grid side can be informed of the fault status of the target unit in a timely manner. If the target unit does not meet the climbing speed requirement information, a prompt message that the working condition is not met is reported to the power grid side.

[0457] It should be noted that in an embodiment of the present application, the grid side can adjust the peak-shaving scheduling instructions in response to the prompt information of the operating conditions not being met fed back by the thermal power plant. For example, according to the prompt information of the operating conditions not being met, the peak-shaving load curve in the peak-shaving requirement information is adjusted, and / or the value in the climbing speed requirement information is adjusted. By adjusting the peak-shaving load curve (for example, lowering the vertical coordinate value of the load curve) or lowering the value in the climbing speed requirement information, the threshold for the requirements of the target unit can be lowered, so that more units can become target units serving the peak-shaving scheduling.

[0458] In addition, in the embodiment of the present application, the grid side can also relearn to improve the threshold quotation according to the prompt information of the operating conditions not being met fed back by each thermal power plant, so that more units can be used as target units for expected auxiliary peak regulation. More units are included in the queue of target units for expected auxiliary peak regulation, which expands the range of selected units and avoids the problem of insufficient ability to provide auxiliary peak regulation services in units with suitable quotations. Including more units in the queue of target units can give more units the opportunity to participate in the auxiliary peak regulation work, and also avoid the problem of limited output of thermal power units with better performance in the auxiliary peak regulation work due to constraints on transaction prices. Continuous in-depth learning of threshold quotations can always update the threshold quotations in a timely manner according to the status and quotations of thermal power units, making peak regulation scheduling dynamic and flexible.

[0459] As mentioned above, in this application, the thermal power units, especially the selected target units, should cooperate with the dispatching of the power grid to assist in peak load regulation. The peak load regulation dispatching method for thermal power in the high frequency variable load scenario provided in this application, after the power grid preliminarily determines multiple thermal power units expected to assist in peak load regulation, the method also includes:

[0460] The power grid side sends a heat pre-dispatch instruction to the multiple thermal power units expected to assist in peak load regulation. The purpose of issuing the heat pre-dispatch instruction is to enable each thermal power unit expected to assist in peak load regulation to make thermal preparations for the upcoming load adjustment work. Specifically, heat pre-dispatch may require the energy storage device to further store more heat, or it may require the energy storage device to further release some heat. The heat pre-dispatch instruction may be issued to the thermal power unit by the power grid side after knowing the heat storage and access margin of the thermal power unit. On the premise of knowing the heat storage and access margin, when the power grid side performs peak load regulation and issues the heat pre-dispatch instruction, it can make the instruction content and heat adjustment range of the issued heat pre-dispatch instruction more match the performance and capacity of the thermal power unit.

[0461] As mentioned earlier, the grid side will determine the target unit for the expected auxiliary peak load regulation based on the quotation information. For the target unit, it is considered that the thermal power plant and the grid side have reached an agreement on the quotation. The target unit selected by the grid side will cooperate with the heat storage device in the thermal power plant to which it belongs to to perform heat pre-dispatch after receiving the heat pre-dispatch instruction. For example, the heat pre-dispatch instruction requires the target unit to further store 12% of heat, and the target unit further stores 12% of heat according to the heat pre-dispatch instruction. Therefore, when auxiliary peak load regulation service is required, the corresponding load adjustment can be completed through the pre-stored heat.

[0462] Figure 5C The peak load dispatching method process under the high-frequency load variation scenario of thermal power is presented, showing the interaction content and interaction sequence from both the thermal power plant and the power grid side. Figure 5C As shown, the thermal power plant selects the type of coal and calculates the heat storage and access margin. The calculated heat storage and access margin and the associated data (specifically, the associated data between the load, performance and cost of each thermal power unit in the thermal power plant) are sent to the power grid side. The specific types of associated data can be referred to Table 3, Table 4, etc. The power grid side digitally processes the data received from each thermal power plant, performs multi-level abstract extraction and analysis on the data, and uses artificial intelligence technology to capture the connection between the data. Then, based on the above extraction and analysis, the power grid side generates a peak load curve for each thermal power unit and sends the curve to the corresponding thermal power plant. In addition, heat pre-dispatch instructions can also be issued. Based on the actual situation of each thermal power unit, the thermal power plant calculates the quotation information that meets the requirements of the peak load curve to assist in peak regulation, and reports the quotation information to the power grid side. At this point, the power grid side can obtain the corresponding quotation information of each thermal power unit in each thermal power plant, and compares it horizontally in combination with the quotation information and the calculated climbing coefficient of the thermal power unit, and selects the target unit by weighing the cost and indicators through data drive. The power grid issues peak-shaving dispatch instructions to the thermal power plants, and the target units cooperate to execute heat pre-dispatching and perform auxiliary peak-shaving services based on the peak-shaving requirement information in the peak-shaving dispatch instructions.

[0463] The technical solution of this application has the following outstanding advantages:

[0464] As the proportion of renewable energy generation in the power system increases, thermal power plants, from design to operation, must pay attention to the storage of heat to meet the needs of auxiliary peak-shaving services for the power grid. The quotation of auxiliary peak-shaving services needs to be market-oriented and coordinated. To this end, the technical solution of this application can meet the needs of market-oriented coordination through the above-mentioned method.

[0465] In addition, in the technical solution of the present application, data analysis is introduced in the market-oriented dispatch of high-frequency variable loads of thermal power. Through the quantified Tables 2 to 4, the grid side (combined with Tables 3 to 4) can be digitally dispatched, and the power plant side (combined with Table 2) can be digitally coal selected. The key lies in feature extraction based on data. The data-driven dispatching process makes the execution of peak-shaving dispatch more standardized and digitalized, with better synergy and clearer costs. The power grid can sort and set priorities according to the performance reflected by the costs and indicators, so as to better select the units suitable for cooperating with peak-shaving based on the data, making the peak-shaving effect more stable, safe and ideal.

[0466] In addition, the technical solution of this application also takes into account the safety of the power grid, such as the ramp coefficient and the peak load curve. Such key data can guide the pricing of power quality and is economical. The pricing of high-frequency peak-shaving dispatching and auxiliary peak-shaving services takes into account the cost of power plants in the market.

[0467] By collecting and processing the natural production factors of thermal power with digital tools in this embodiment, its data features are abstracted, and then according to the thermal power price formula, the heat consumption, coal consumption and electricity fee measurement model of thermal power under full load conditions is obtained. Through the digital research of the model, data-driven digital logic can be involved, which can be applied to the power industry to digitize thermal power dispatch and operation. At the same time, by studying the control production factors on the power grid side, such as electricity prices, thermal power production factors are associated with electricity prices and complex production factors. By setting low-order, medium-order, and high-order data abstract production factors, the intermediate results or production factors may not have physical meanings in reality, such as sub-frequency and low-voltage overexcitation. Then these data abstract production factors are the key to unlocking artificial intelligence (digital) electricity.

[0468] Fig. 5F This is a flow chart of another peak load scheduling method in a thermal power high frequency variable load scenario provided by the embodiment of the present application. Fig. 5F Provide a brief description.

[0469] like Fig. 5F In the process shown, the thermal power plant first selects the coal type based on the hydrogen content of each type of coal, then calculates the thermal storage margin of the thermal power plant, and digitizes the correlation data between the load, performance and cost of each thermal power unit in the thermal power plant. The thermal power plant sends this data to the power grid, which uses data to weigh costs and indicators and determine the target unit for expected auxiliary peak regulation.

[0470] In specific implementation, the grid side generates the peak load curve for each thermal power unit based on the changes in thermal power load demand and the corresponding data provided by each thermal power plant, and sends it to the thermal power unit. In addition, the climbing coefficient of each thermal power unit is calculated, and multiple thermal power units expected to assist in peak load regulation are preliminarily determined, and heat pre-dispatch instructions are sent to them. The thermal power plant calculates the quotation for the auxiliary peak load regulation service based on the peak load curve and sends it to the grid side. The grid side continues to combine cost factors and the performance data of the thermal power plant, and weighs the quotation information with the K-fold threshold quotation to select the target unit. If the quotations all exceed the K-fold threshold quotation, it means that the threshold quotation is too low, which means that the threshold quotation needs to be deeply learned again to improve the pass rate of the thermal power units with the load quotation threshold.

[0471] The target unit cooperates with the heat pre-scheduling, and after the pre-scheduling is completed, the heat storage is reported to the power grid again. The power grid determines whether there is equipment failure and communication failure in the target unit, and determines whether the climbing speed requirement information is met. If there is equipment failure or communication failure, it needs to be reported to the power grid; if there is a situation where the target unit does not meet the climbing speed requirement information, it also needs to be reported to the power grid. Fig. 5F As shown by the middle dotted line, if the operating conditions are not met, measures such as re-learning the threshold quotation can be taken, or the peak-shaving requirement information in the peak-shaving dispatch instruction issued to the target unit can be adjusted.

[0472] Embodiment 4

[0473] In the fourth embodiment, the power function requirement for realizing the dispatching control of the power plant side by the power grid side is specifically the water resource dispatching of the cascade hydropower station, and the functional operator is the water resource dispatching operator, which is used to realize the water resource dispatching of the cascade hydropower station. The fourth embodiment introduces the process of the digital power system using the intelligent agent constructed based on the water resource dispatching operator.

[0474] There are a series of issues that need to be considered in the water resource dispatch of cascade hydropower stations. For example, cascade hydropower stations are generally composed of multiple single-stage power stations in series. The upper and lower hydropower stations are connected through storage return water. The control range can be extended from the confluence to the entire basin. The risk of some out-of-control in the upstream power station is transmitted through water flow fluctuations, superimposed and accumulated in the downstream hydropower station, which may cause serious risk events; for example, during the operation of each hydropower station in the cascade hydropower station, it is necessary to consider the reservoir safety (water level should be appropriate) and unit safety of each hydropower station; for example, during the operation of each hydropower station in the cascade hydropower station, it is necessary to consider the unit operation safety caused by sudden accidents in the power grid (such as failure to receive electricity from the interconnection point, sudden load shedding); for example, under the premise of reservoir safety and hydropower generation equipment safety, how to improve the power supply quality, promote the safe operation of the power grid, increase the power supply income, and realize the full utilization of water resources.

[0475] Based on the above problems, this application proposes a water resource scheduling method for cascade hydropower stations using a water resource scheduling operator in a digital power system based on a multifunctional intelligent body. The implementation of this method includes: obtaining the water resource data of each hydropower station in the cascade hydropower station at the current moment; for each hydropower station, judging whether the hydropower station is in a safe operation state according to the water resource data of the hydropower station; when it is determined that each hydropower station is in a safe operation state, judging whether to perform water resource scheduling according to the water resource data of each hydropower station, the preset electricity price scheme and the target historical data; if it is determined to perform water resource scheduling, then determine the water resource scheduling scheme based on the water resource data of each hydropower station and the water resource scheduling model. Through the scheme in this application, when it is determined that each hydropower station is in a safe operation state, based on the water resource scheduling model trained by historical data and the water resource data of each hydropower station at the current moment, a water resource scheduling scheme that can obtain as high a power generation benefit as possible can be directly generated, thereby realizing the reasonable scheduling of water resources.

[0476] Fig. 6A A flow chart of a water resource scheduling method provided in an embodiment of the present application. Fig. 6A As shown, the water resource scheduling method disclosed in this application includes:

[0477] S601, obtaining water resource data of each hydropower station in the cascade hydropower station at the current moment.

[0478] The water resource data of the hydropower station in this application include but are not limited to: the measured water level of the reservoir where the hydropower station is located (referred to as "measured water level"), the measured velocity increase rate of the water flow velocity in the reservoir where the hydropower station is located (referred to as "measured velocity increase rate"), the measured turbine static pressure (also called "measured turbine static water pressure"), the rated speed of the turbine generator, the working power of the turbine generator, the installed capacity of the power station, the maximum / rated / minimum head, the maximum runaway speed, the rated output of the turbine and the wheel tube diameter, etc.

[0479] Table 6 is a table of water inflow to the upstream hydropower station provided by this application. Table 6 shows the water inflow to the upstream hydropower station in different years from January to December. The unit of water volume is 10,000 m 3 .

[0480] For example, the following data can be read from Table 6: The water inflow into the upstream hydropower station in January 2016 was 7.75 million m 3 ; In February 2023, the water inflow from the upstream hydropower station was 12.57 million m 3 .

[0481] It should be noted that the upstream hydropower station refers to the hydropower station located upstream among the cascade hydropower stations.

[0482] Table 6

[0483] month 2016 2017 2018 2019 2020 2023 2024 January 775 3227 3263 3136 1750 2894 1274 February 210 1114 2476 2305 746 1257 3128 March 106 1650 3324 736 1939 2478 798 April 2047 13740 6802 3011 1410 3692 1784 May 8280 23682 35177 3642 5481 5304 2478 June 11174 22343 52766 14295 8700 16633 10618 July 35240 19435 90578 25659 16089 43929 83502 August 30913 22702 115595 73712 33239 49479 25684 September 23290 18653 38499 84177 46228 56418 34185 October 40846 26580 35633 21007 54775 37106 26915 November 16734 11114 10911 7187 12512 18177 none December 6348 5774 4833 2386 2870 4250 none

[0484] Table 7

[0485]

[0486] Table 7 is a table of water volume changes of an upstream hydropower station provided by this application. Table 7 shows the daily water volume changes of the upstream hydropower station from January 23 to January 30. Specifically including: Current water storage capacity (m 3 ), current reservoir energy storage (billion kWh), current water level (m), yesterday's average inflow (m 3 / s), yesterday's average outbound flow (m 3 / s) and yesterday's power generation water consumption rate (m 3 / kWh).

[0487] S602: For each of the hydropower stations, determine whether the hydropower station is in a safe operating state based on the water resource data of the hydropower station.

[0488] The safe operation status in this application mainly refers to the water conservation safety status and the vibration safety status.

[0489] In this application, when judging whether a hydropower station is in a water conservation safety state, two indicators, namely the measured turbine static water pressure and the measured speed rise rate, are mainly considered.

[0490] The measured turbine hydrostatic pressure, also known as volute pressure, refers to the actual net water pressure at the turbine volute inlet; it is usually affected by water velocity, water flow direction, turbine structure and reservoir water level. The measured turbine hydrostatic pressure is of great significance for evaluating the operating efficiency of turbines, predicting the wear of turbines and formulating turbine maintenance plans.

[0491] The measured rate of increase refers to the actual rate of increase of the reservoir water level within a certain period of time, expressed as the amount of water level change per unit time; it is usually affected by the amount of water entering the reservoir, the amount of water leaving the reservoir, rainfall conditions and the reservoir regulation capacity. The measured rate of increase is of great significance for evaluating the water storage capacity of the reservoir, predicting future water level changes and formulating reservoir scheduling plans.

[0492] Usually, the measured speed rise rate and the measured turbine static pressure can be obtained through corresponding sensors; the theoretical speed rise rate and the theoretical turbine static pressure can be obtained from the technical documentation of the hydropower station.

[0493] It should be emphasized that the theoretical speed rise rate in this application is the maximum actual rise rate of the reservoir water level allowed within a certain period of time during the safe operation of the hydropower station; the theoretical turbine hydrostatic pressure in this application is the maximum actual net water pressure at the turbine volute inlet allowed during the safe operation of the hydropower station.

[0494] Table 8

[0495]

[0496]

[0497] Table 8 is a table of volute pressures measured on different dates provided by the present application. Table 8 gives the unit output (MW), upstream water level (m), downstream water level (m), volute pressure (Mpa) and guide vane opening values ​​of different units detected at 09:04 am, 15:00 pm and 18:25 pm on August 18, 2018, and 09:25 am and 13:50 pm on August 19, 2018.

[0498] In an optional implementation, whether each hydropower station in the cascade hydropower station is in a water conservation safety state can be determined by the following steps, specifically:

[0499] For each hydropower station, the measured speed rise rate and the measured turbine hydrostatic pressure are obtained from the water resource data of the hydropower station; then, the measured speed rise rate of the hydropower station is compared with the theoretical speed rise rate, and the measured turbine hydrostatic pressure of the hydropower station is compared with the theoretical turbine hydrostatic pressure.

[0500] If the measured speed rise rate is less than the theoretical speed rise rate, and the measured turbine hydrostatic pressure is less than the theoretical turbine hydrostatic pressure, it is determined that the hydropower station is in a water conservation safety state; if the measured speed rise rate is greater than or equal to the theoretical speed rise rate, or the measured turbine hydrostatic pressure is greater than or equal to the theoretical turbine hydrostatic pressure, it is determined that the hydropower station is not in a water conservation safety state.

[0501] It is understandable that equipment in a hydropower station, such as a turbine generator, will generate vibrations during operation. The amplitude and frequency of these vibrations are important indicators for evaluating the operating status of the equipment. Excessive vibration may mean that the equipment is worn, loose, unbalanced or has other potential problems. In this application, the determination of whether a hydropower station is in a vibration-safe state mainly takes into account the actual working power of the turbine engine and the vibration conditions of the various components of the turbine engine.

[0502] In an optional implementation, whether each hydropower station in the cascade hydropower station is in a vibration safe state can be determined by the following method, specifically:

[0503] Step 1: For each hydropower station, the power (actual working power) of the turbine engine is obtained from the water resource data of the hydropower station, which is recorded as the first power.

[0504] It should be noted that, in the process of the power of the water turbine engine rising from 0 to the maximum power (full load power), in certain power intervals (referred to as the preset power interval in this application), due to various reasons such as frequency resonance, there will be a situation where the vibration of various components of the water turbine engine is very large. In order to avoid the water turbine engine being damaged due to excessive vibration or the vibration triggering the protection trip, this application will focus on the actual working power of the water turbine engine at the current moment (i.e., the first power in this application).

[0505] The second step is to determine whether the first power is within a preset power range.

[0506] It should be noted that the preset power range can be obtained according to a variable power vibration test.

[0507] The third step is to quickly adjust the first power to the second power if the first power is within the preset power range; wherein the second power is outside the preset power range.

[0508] If it is determined that the first power is within the preset power range, it means that the vibration of various parts of the current hydro-generator is large, which may easily cause damage to the hydro-generator. At this time, the working power of the hydro-generator is quickly adjusted, for example, the first power can be quickly adjusted to the second power outside the preset power range to avoid excessive vibration of the hydro-generator due to frequency resonance and other reasons.

[0509] The fourth step is to determine whether the hydropower station is in a vibration safety state if the first power is outside the preset power range.

[0510] If it is determined that the first power is outside the preset power range, it can be determined that the hydro-generator will not vibrate excessively at the first power due to frequency resonance, etc. At this time, it is necessary to further determine whether the hydropower station is in a vibration safety state.

[0511] In an optional implementation, the process of determining whether the hydropower station is in a vibration-safe state is as follows:

[0512] Firstly, for each hydropower station, the rotation speed of the turbine engine of the hydropower station and the actual vibration values ​​of different parts of the turbine engine are obtained from the water resource data of the hydropower station.

[0513] Then, after the actual water turbine engine speed is determined, the actual vibration values ​​of different parts of the water turbine engine measured at the speed are compared with the vibration allowable values ​​corresponding to the parts.

[0514] For each hydropower station, if at the current speed of the turbine engine, the actual vibration values ​​of different parts of the turbine engine are all less than the corresponding allowable vibration values, then the hydropower station is determined to be in a vibration safe state; if the actual vibration value of a certain part of the turbine engine is greater than or equal to the corresponding allowable vibration value of that part, then the hydropower station is determined to be not in a vibration safe state and there is a vibration risk.

[0515] Table 9

[0516]

[0517] Table 9 is a table of the allowable vibration values ​​of various parts of a hydro-turbine generator provided by the present application. As shown in Table 9, the hydro-turbine engine has different allowable vibration values ​​at different rotation speeds. For example, when the rotation speed is less than 100r / min, the allowable vibration value of the vertical vibration of the thrust bearing bracket of the vertical unit of the hydro-turbine generator is 0.1mm. When the actual vibration value of the vertical vibration of the thrust bearing bracket is greater than 0.1mm when the rotation speed is less than 100r / min, it is considered that the vertical unit of the hydro-turbine generator has an equipment vibration risk.

[0518] When it is determined that each hydropower station in the cascade hydropower station is in a water conservation safety state and a vibration safety state, that is, when it is determined that each hydropower station is in a safe operation state, the steps of the subsequent embodiments of the present application can be continued.

[0519] It is understandable that if it is determined that each hydropower station in the cascade hydropower station is not in a safe operating state and there are water conservation safety issues or vibration safety risks, it is necessary to shut down for maintenance until the problem is fixed, and then restart the power generation facilities in each hydropower station; after restarting, verify that each hydropower station is in a safe operating state, and then execute the steps of the subsequent embodiments of this application.

[0520] S603, when it is determined that all the hydropower stations are in the safe operation state, judging whether to perform water resource scheduling according to the water resource data of each hydropower station, the preset electricity price scheme and the target historical data.

[0521] It is understandable that for hydropower generators, while being able to safely operate the power plant's power generation equipment, it is necessary to accurately adjust the water level of the reservoir corresponding to the power station. In this way, higher power generation revenue can be obtained while meeting the power demand of the power grid.

[0522] Specifically, first, the actual water consumption and actual power plant revenue of each hydropower station should be determined based on the water resource data of each hydropower station and the preset electricity price plan as the current actual data of the hydropower station. Then, based on the difference between the current actual data and the target historical data, it is determined whether water resource scheduling is needed. Among them, the target historical data includes the average water consumption and average power plant revenue of the current month.

[0523] If the difference between the current actual data and the target historical data is too large and exceeds the preset difference threshold, it is determined that water resource scheduling is required; otherwise, it is determined that water resource scheduling is not required. The specific value of the preset difference threshold is not limited in this application, and those skilled in the art can set the preset difference threshold according to actual needs.

[0524] In the subsequent embodiments of this application, the process of obtaining the current actual data and the process of obtaining the target historical data will be described in detail.

[0525] In an optional implementation, the following method can be used to determine the actual power generation water consumption and actual power plant revenue of each hydropower station based on the water resource data of each hydropower station and the preset electricity price plan as the current actual data of the hydropower station. Specifically:

[0526] The first step is to obtain the actual power generation and actual water consumption in the target time period from the water resource data of each hydropower station, where the target time period is a period of time in the past with the current moment as the end point.

[0527] For example, the actual power generation and actual water consumption in the past hour can be obtained from the water resource data of hydropower station A obtained at the current moment, where the past hour is the target time period.

[0528] The actual power generation and the actual water consumption can be obtained through corresponding detection equipment. For example, the actual water consumption within the target time can be measured by an ultrasonic flow tester.

[0529] In the second step, for each hydropower station, the actual power generation and water consumption in the target time period are obtained based on the actual power generation and actual water consumption in the target time period.

[0530] Exemplarily, after obtaining the actual water consumption and actual power generation of hydropower station A in the last hour, the actual water consumption is divided by the actual power generation, and then divided by the target time period to obtain the actual water consumption for power generation.

[0531] The actual water consumption for power generation in this application reflects the capacity characteristics of water resources required per unit time and per unit power generation of the hydropower station. The actual water consumption for power generation is a high-level abstract data, which can be compared with the specific heat index of thermal power stations and the wind resource utilization coefficient of wind power stations to determine the degree and performance of resource utilization by power nodes; it reflects the specific function of power stations on resource energy consumption.

[0532] The third step is to determine the actual power plant revenue in the target time period for each hydropower station based on the corresponding segmented electricity price plan in the target time period and the actual water level of the hydropower station.

[0533] The segmented electricity price plan (hereinafter referred to as the electricity price plan) in this application is an electricity fee plan related to the month and the water volume of the reservoir.

[0534] For ease of understanding, the specific form of the segmented electricity price scheme is introduced by taking the segmented electricity price scheme corresponding to the cascade hydropower station including the upstream power station (also called the upstream reservoir power station) and the downstream power station (also called the downstream reservoir power station) as an example:

[0535] (a) Upstream reservoir power station:

[0536] The upstream reservoir power station implements quarterly regulation and calculates prices according to different water levels in different seasons.

[0537] From January to March, the water level is between 250-260m above sea level. If the water level of the upstream reservoir is above 255m, the on-grid electricity price is J-0.001 / m; if the water level of the upstream reservoir is below 255m, the on-grid electricity price is J+0.001 / m; the electricity price for other water levels in the interval is: if the water level is higher than the upper limit, the upper limit is calculated, and if the water level is lower than the lower limit, the lower limit is calculated; where J in this application is the preset basic value of the on-grid electricity price.

[0538] From April to June, the water level is between 210-250 m above sea level. If the water level of the upstream reservoir is above 230 m, the on-grid electricity price is J-0.001 / m; if the water level of the upstream reservoir is below 230 m, the on-grid electricity price is J+0.001 / m; the electricity price for other water levels within the interval is calculated as follows: if the water level is above the upper limit, the upper limit is calculated; if the water level is below the lower limit, the lower limit is calculated.

[0539] From July to September, the water level is between 250-260 m above sea level. If the water level of the upstream reservoir is above 255 m, the on-grid electricity price is J-0.001 / m; if the water level of the upstream reservoir is below 255 m, the on-grid electricity price is J+0.001 / m; the electricity price for other water levels within the interval is calculated as follows: if the water level is above the upper limit, the upper limit is calculated; if the water level is below the lower limit, the lower limit is calculated.

[0540] From October to December, the water level is between 258 and 262 m above sea level. If the water level of the upstream reservoir is above 260 m, the on-grid electricity price is J-0.001 / m; if the water level of the upstream reservoir is below 260 m, the on-grid electricity price is J+0.001 / m; the electricity price for other water levels within the interval is calculated as follows: if the water level is above the upper limit, the upper limit is calculated; if the water level is below the lower limit, the lower limit is calculated.

[0541] The water levels of the upstream and downstream reservoirs are between 262-265 m and 115-120 m, and the electricity price is the full electricity price of US$0.073 per kilowatt-hour. The water levels of the upstream and downstream reservoirs are safe water levels below 235 m and 100 m, and they cannot generate electricity if shut down.

[0542] Table 10

[0543]

[0544] Table 10 is a table of the relationship between the reservoir water level and electricity price of an upstream hydropower station provided by this application. The upstream reservoir power station can directly give an increase or decrease price according to the water level in each quarter according to the content shown in Table 10 to obtain the actual electricity price PR real corresponding to the current month.

[0545] In Table 10, the water level is represented by the letter L; the unit of the water level and the median water level is meter; the unit of the actual electricity price PR is (US dollars / kWh). When the month is January-March, the water level is in the range of 250-260 meters, and the median water level is 255 meters; within this month range, if the water level L is less than the median water level of 255 meters, the value of PR is generated based on the full electricity price of 0.073 (US dollars / kWh) and the floating electricity price of 0.001. In each month in Table 10, when the water level L is greater than the median water level, PR is (0.073+0.001) (US dollars / kWh); when the water level L is less than the median water level, PR is (0.073-0.001) (US dollars / kWh).

[0546] In this application, by analyzing the water resource data, it is found that the data of each quarter has the characteristics of clustering, that is, the quarterly water levels in Table 10 show segmented characteristics, which reflects the characteristics of hydrology and water levels of hydropower stations. Only by better using the production factors of nature (referred to as primary indicators in this application) can the benefits of water resource utilization be maximized and the cost of hydropower water use be market-oriented. Therefore, this application adopts the method of targeting the median water level, comparing it with the median value of the historical water level (the historical water level is one of the data samples for deep learning), judging the measured water inflow and the amount of water entering the reservoir, so as to determine a reasonable power generation price.

[0547] It is understandable that if other patterns are discovered during the analysis of historical water resource data or other data, this may further guide the water level scheduling strategy adopted in this application, further improve the underlying logic of data-based scheduling agents emphasized in this application, and avoid errors caused by artificially abstracting data and specifying water resource scheduling plans.

[0548] (b) Downstream reservoir power station:

[0549] The downstream reservoirs implement day-ahead scheduling, regardless of the season.

[0550] The water level is between 105-110 m above sea level. If the water level of the downstream reservoir is above 107 m, the on-grid electricity price is J-0.001 / m; if the water level of the downstream reservoir is below 107 m; the electricity price for other water levels in the interval is: if the water level is higher than the upper limit, the upper limit will be charged; if the water level is lower than the lower limit, the lower limit will be charged.

[0551] Table 11 is a table of the relationship between the reservoir water level and electricity price of a downstream hydropower station provided by this application. The downstream reservoir power station can directly give the increase or decrease price according to the water level in each quarter as shown in Table 11, and obtain the actual electricity price PR real corresponding to the current month. In Table 11, the water level is represented by the letter L, the units of the water level and the median water level are both meters, and the unit of the actual electricity price PR real is (US dollars / degree). In Table 11, when the water level L is greater than the median water level, PR real is (0.073+0.001) (US dollars / degree); when the water level L is less than the median water level, PR real is (0.073-0.001) (US dollars / degree).

[0552] Table 11

[0553]

[0554] For each hydropower station in the cascade hydropower station, after obtaining the corresponding segmented electricity price plan for the target time period and the actual water level of the hydropower station, the actual power plant revenue for the target time period can be determined based on the following formula. The target formula is:

[0555]

[0556]

[0557] Q3=PR 实 ×P 实 (2.3)

[0558] The meanings of the letters in formula (2.1), formula (2.2) and formula (2.3) are as follows:

[0559] Q1 represents the fee that the power grid should pay to the hydropower station when the power grid fails and the hydropower station cannot generate electricity normally (pay without negotiation); Q2 represents the actual income corresponding to the potential electricity at the current moment; Q3 represents the actual power generation income corresponding to the actual generated electricity at the current moment. The sum of formula (2.1) and formula (2.3) represents the actual power plant income of the hydropower station; the sum of formula (2.1), formula (2.2) and formula (2.3) represents the water assets of the hydropower station.

[0560] D represents the number of turbine generators included in the hydropower station, and D is a positive integer greater than 1; PR is the actual electricity price corresponding to the current month; PR represents the average electricity price within the target time period (i.e., the target pricing time period); i is a turbine generator in the hydropower station, i = 1, 2...D; PR is the power generation (actual electric energy) within the target time period; Gi is the rated power of the i-th turbine generator in the hydropower station; Hi is the continuous power generation time of the i-th turbine generator in the hydropower station at the rated power within the target pricing time period; Fi is the derating power of the i-th turbine generator in the hydropower station; Hiz is the interruption duration of the i-th turbine generator in the hydropower station during the high water level period.

[0561] The high water level is the water level at which the hydropower station can generate electricity. If the contract stipulates that the hydropower station can generate electricity when the water level is within the range of 240-265m, then 240-265m is the high water level in this application.

[0562] Through deep learning of water level data, seasonal water level changes can be discovered and extended research can be conducted; general rules can be obtained through the data features of water level (or other quantities); through the target formula or generalized electricity price scheme in the aforementioned embodiment, based on basic data such as electricity charges and water consumption for power generation, finally associated data such as power plant power generation revenue can be obtained; then the characteristics and associations of data such as water level, electricity charges, power plant power generation revenue, power plant power generation cost, and power generation water consumption can be extracted to establish a model of the median of water level and electricity price; through deep learning and association research, a reasonable scheduling strategy for hydropower station revenue and water resource assets can be obtained. Among them, the scheduling strategy is not limited to upstream quarterly power generation.

[0563] Table 12 is a data calculation table for the cascade hydropower stations provided in this application. The cascade hydropower stations in Table 12 include an upstream hydropower station and a downstream hydropower station, a total of two hydropower stations. The data in Table 12 are calculated based on the water resource data of each hydropower station in the cascade hydropower station at the current moment, formula (2.1), formula (2.2) and formula (2.3).

[0564] Those skilled in the art can calculate the power generation income for other months in 2023 by referring to the electricity prices for different quarters and water levels provided in the above embodiments, formula (2.1), formula (2.2) and formula (2.3).

[0565] It should be noted that the upper dam in Table 12 refers to the upstream reservoir; the lower dam refers to the downstream reservoir; the upper plant refers to the plant of the hydropower station corresponding to the upstream reservoir; and the lower plant refers to the plant of the hydropower station corresponding to the downstream reservoir.

[0566] The unit of water volume in Table 12 is 10,000 m 3 ; The unit of water level is m; The unit of flow is m 3 / s; the unit of rainfall is mm; the unit of electricity is 10,000 kw.h. The meanings of the letters in Table 6 refer to the introduction of the above embodiment and will not be repeated here.

[0567] Table 12

[0568]

[0569]

[0570] In an optional implementation, the target historical data of each hydropower station is obtained as follows:

[0571] First, the historical water consumption for power generation and historical power plant revenue for each month in the past N years are counted, where N is an integer greater than or equal to 1.

[0572] For example, the amount of water entering the reservoir of hydropower station A in a specific month, such as January 2024, can be obtained; the reservoir capacity of hydropower station A in January 2024 can be obtained; the amount of water entering the reservoir minus the reservoir capacity can be used to obtain the water consumption of hydropower station A in January 2024. The power generation and power generation duration of hydropower station A in January 2024 are counted; the water consumption of hydropower station A in January 2024 is divided by the power generation of hydropower station A in January 2024, and then divided by the power generation duration of hydropower station A in January 2024, to obtain the historical power generation water consumption of hydropower station A in January 2024.

[0573] Figure 6B A schematic diagram of the historical water consumption for power generation of an upstream hydropower station corresponding to each month provided in an embodiment of the present application. Figure 6B The unit of the horizontal axis is cubic meter / kilowatt-hour; the unit of the vertical axis is month. Figure 6B The historical water consumption for power generation of the upstream hydropower stations from January to December 2023 and from January to December 2024 is given in the table. The data for November 2024 and December 2024 are the historical water consumption for power generation calculated based on historical data.

[0574] Figure 6C A schematic diagram of the historical water consumption for power generation in a downstream hydropower station corresponding to each month provided in an embodiment of the present application. Figure 6C The unit of the horizontal axis is cubic meter / kilowatt-hour; the unit of the vertical axis is month. Figure 6C The historical water consumption for power generation of downstream hydropower stations from January to December 2023 and from January to December 2024 is given in the table. The data for November 2024 and December 2024 are the historical water consumption for power generation calculated based on historical data.

[0575] based on Figure 6B and Figure 6C By comparing the water consumption for power generation, it can be clearly seen that it is more appropriate to implement quarterly regulation upstream, while it is more appropriate to implement day-ahead regulation (also known as day-ahead scheduling) downstream.

[0576] As described in the above embodiment, the sum of formula (2.1) and formula (2.3) represents the actual power plant revenue of the hydropower station. Therefore, by substituting historical relevant data into formula (2.1) and formula (2.3), the historical power plant revenue can be obtained.

[0577] Fig.6D A schematic diagram of the historical power plant revenue corresponding to each month of an upstream hydropower station provided in an embodiment of the present application. Fig.6D The horizontal axis is in dollars; the vertical axis is in months. Fig.6D The historical power plant revenues of the upstream hydropower stations for each month from January 2023 to December 2023 and from January 2024 to December 2024 are given in the table. The data for November 2024 and December 2024 are the historical power plant revenues calculated based on historical data.

[0578] Fig. 6E A schematic diagram of the historical power plant revenue corresponding to each month of a downstream hydropower station provided in an embodiment of the present application. Fig. 6E The horizontal axis is in dollars; the vertical axis is in months. Fig. 6E The historical power plant revenues of downstream hydropower stations from January 2023 to December 2023 and from January 2024 to December 2024 are given in the table. The data for November 2024 and December 2024 are the historical power plant revenues calculated based on historical data.

[0579] Furthermore, the water asset data of each power plant in each month can also be calculated. The water asset of each power plant in this application refers to the sum of formula (2.1), formula (2.2) and formula (2.3).

[0580] Fig. 6F A schematic diagram of the water assets corresponding to each month of an upstream hydropower station provided in an embodiment of the present application. Fig. 6F The horizontal axis represents the amount of water assets in US dollars, and the vertical axis is in months. Fig. 6F The historical water assets of the upstream hydropower stations for each month from January 2023 to December 2023 and from January 2024 to December 2024 are given in the table. The data for November 2024 and December 2024 are historical water assets calculated based on historical data.

[0581] Figure 6G A schematic diagram of the water assets corresponding to each month of a downstream hydropower station provided in an embodiment of the present application. Figure 6G The horizontal axis represents the amount of water assets in US dollars, and the vertical axis is in months. Figure 6G The historical water assets of the downstream hydropower stations for each month from January 2023 to December 2023 and from January 2024 to December 2024 are given in the table. The data for November 2024 and December 2024 are historical water assets calculated based on historical data.

[0582] For ease of understanding, this application Figure 6B , Figure 6C , Fig.6D , Fig. 6E , Fig. 6F and Figure 6G The historical water consumption for power generation, historical power plant income and historical water assets (income) of each hydropower station in the cascade hydropower station including two hydropower stations in total, the upstream hydropower station and the downstream hydropower station, are given. Those skilled in the art can refer to the method described in the above embodiment to obtain the historical water consumption for power generation, historical power plant income and historical water assets (income) of each hydropower station in other cascade hydropower stations in each month.

[0583] Then, for each month, a graph is drawn based on the N historical power generation water consumption corresponding to the month to obtain a historical power generation water consumption graph corresponding to the month.

[0584] For example, for January, the historical water consumption for power generation in January 2010, January 2011, January 2012, and even January 2024 can be obtained; a graph with the year as the horizontal axis and the historical water consumption for power generation as the historical water consumption map for power generation corresponding to January is generated.

[0585] Similarly, for February, we can get the historical water consumption for power generation in February 2010, February 2011, February 2012, and even February 2024; generate a graph with the year as the horizontal axis and the historical water consumption for power generation as the corresponding historical water consumption map for power generation in February.

[0586] For each month, based on the N historical power plant revenues corresponding to the month, a historical power plant revenue map corresponding to the month is obtained.

[0587] For example, for January, the historical power plant revenues of January 2010, January 2011, January 2012, and even January 2024 can be obtained; a graph with the horizontal axis being the year and the vertical axis being the historical power plant revenue is generated as the historical power plant revenue map for January.

[0588] Among them, the historical power generation water consumption map represents the relationship between historical power generation water consumption and time; the historical power plant revenue map represents the relationship between historical power plant revenue and time.

[0589] Finally, the average power generation water consumption corresponding to the historical power generation water consumption map corresponding to the current month and the average power plant revenue corresponding to the historical power plant revenue map corresponding to the current month are taken as target historical data.

[0590] The average water consumption for power generation is the average of the historical water consumption for power generation included in the historical water consumption map for power generation. The average power plant revenue is the average of the historical power plant revenue included in the historical power plant revenue map.

[0591] After obtaining the current actual data and the target historical data, it is determined whether to perform water resource scheduling based on the difference between the current actual data and the target historical data. Specifically:

[0592] Determine whether the difference between the actual power generation water consumption and the average power generation water consumption is within the preset allowable value of the power generation water difference (first judgment condition), and determine whether the difference between the actual power plant profit and the average power plant profit is within the preset allowable value of the power plant profit difference (second judgment condition).

[0593] If the first judgment condition and the second judgment condition are met at the same time, water resource scheduling is not required and the process directly returns to S601 ; if the above two judgment conditions are not met at the same time, it is considered that water resource scheduling is required and the process proceeds to S604 .

[0594] Furthermore, the actual water assets of the hydropower station corresponding to the current month of the hydropower station can also be calculated (the sum of formula (2.1), formula (2.2) and formula (2.3)); the average water assets of the hydropower station corresponding to the current month can be obtained; it can be determined whether the difference between the actual water assets corresponding to the current month and the average water assets is within the preset allowable value of the water asset difference (the third judgment condition), and whether water resources scheduling is required.

[0595] That is, when the first judgment condition, the second judgment condition and the third judgment condition are met, it is determined that water resource scheduling is not required, and the process directly returns to S601; otherwise, it is considered that water resource scheduling is required, and the process proceeds to S604.

[0596] It should be noted that the present application does not limit the values ​​of the preset allowable difference value of water used for power generation, the preset allowable difference value of power plant revenue and the preset allowable difference value of water assets, and those skilled in the art may limit the above values ​​as needed.

[0597] S604: If it is determined to perform water resource scheduling, a water resource scheduling plan is determined based on the water resource data and water resource scheduling model of each of the hydropower stations.

[0598] Among them, the water resources scheduling model is a model that is trained in advance and used to output water resources scheduling plans.

[0599] In an optional implementation, the training steps of the water resource scheduling model include:

[0600] The first step is to obtain training data.

[0601] The training data in this application includes sample water resource data obtained by each hydropower station in the cascade hydropower stations at a sample time point, an electricity price plan at the sample time point, and a sample water resource scheduling plan at the sample time point.

[0602] It should be noted that the sample time point in this application is any one of the multiple time points of the operation of the hydropower station under all working conditions. In other words, the sample time point can be a time point when the hydropower station is in normal operation, and the data corresponding to the sample time point is the data corresponding to the normal operation of the hydropower station; the sample time point can also be a time point when the hydropower station conducts a load shedding test, a water conservation test, or a vibration test, and the data corresponding to the sample time point is the data corresponding to the hydropower station under the above experimental conditions.

[0603] Sample water resource data include historical water consumption for power generation, historical power plant revenue and historical average water assets; sample water resource scheduling plans include day-ahead scheduling and seasonal scheduling.

[0604] It is understandable that the water resource dispatching of each hydropower station in the cascade is a very complex process. At different points in time, the water level of the reservoir where each hydropower station is located, the actual operating parameters of the power generation facilities and the amount of precipitation are different, and the water resource dispatching scheme adopted is different.

[0605] It is understandable that the storage capacity of the upstream hydropower station in the cascade hydropower station is greater than the storage capacity of the downstream hydropower station; the water regulation space of the upstream hydropower station is greater than the water regulation space of the downstream hydropower station. Based on the above reasons, in the water resource scheduling scheme included in the training data given in this application, the upstream hydropower station adopts the quarterly regulation method (also called quarterly scheduling and quarterly regulation), and the downstream hydropower station adopts the day-ahead regulation method (also called day-ahead scheduling and day-ahead regulation).

[0606] Among them, seasonal regulation refers to adjusting the reservoir capacity of the hydropower station to store a part of the runoff during the flood season of the year for use during the dry season. This regulation method enables the hydropower station to achieve effective redistribution of water resources within a year, especially between seasons with uneven water resources distribution. Seasonal regulation can store excess water in the season of sufficient water and release the stored water in the season of scarce water to ensure the stable operation and continuous power generation of the hydropower station.

[0607] Day-ahead dispatch refers to the redistribution of runoff within a day and night. This regulation method is mainly used to deal with short-term (such as within a day) changes in water resources and fluctuations in electricity demand. Through day-ahead dispatch, hydropower stations can flexibly adjust their power generation plans and water resource allocation according to real-time water resource conditions and electricity demand to ensure the stability and reliability of power supply.

[0608] Seasonal dispatch focuses on the balanced allocation of water resources between seasons to achieve long-term stable operation and power generation efficiency, while day-ahead regulation focuses more on the dynamic balance of water resources and power demand in the short term to ensure the stability and reliability of power supply. Hydropower stations adopt these two regulation methods in combination according to their own reservoir conditions, water resources conditions, and power market demand to achieve efficient use of water resources and optimization of power supply.

[0609] It is precisely because of the day-ahead scheduling of the downstream and the seasonal scheduling of the upstream that the calculation of water assets is meaningful. The two pursue the balance between cost and economy. The downstream is mainly for power generation, while the upstream is mainly for controlling the water volume and water level of the entire basin. Figure 6B and Figure 6C In the comparison between the day-ahead dispatch and the quarterly dispatch of the upstream and downstream, the water consumption per kWh is 0.018m 3 / kWh and 0.026m 3 / kWh, because more emphasis is placed on monthly profits these days, indicating that downstream power generation is more efficient, while upstream quarterly scheduling focuses more on the overall basin, taking power generation into account, and by comparing the monthly accumulation of upstream and downstream water assets, it is possible to clearly see that there are more details of water assets upstream than downstream, which further illustrates the importance of adopting quarterly conditions upstream.

[0610] By abstracting and analyzing high-order features of the data, especially the research on water consumption for power generation and water assets, the two scheduling methods are able to implement different scheduling strategies for the upstream and downstream of the hydropower station through data-driven intelligent entities with two scheduling functions, under the premise of ensuring the safety of the smart hydropower station, that is, when all operating conditions meet the requirements of load shedding, variable power vibration measurement and water conservation safety.

[0611] Figure 6H A schematic diagram of a water resource regulation scheme for a cascade hydropower station provided in an embodiment of the present application. The cascade hydropower station includes an upstream hydropower station and a downstream hydropower station. Figure 6H The meanings of the letters are as follows: J1 represents the cost electricity price; S1 represents the actual water level of the upstream hydropower station; S2 represents the actual water level of the downstream hydropower station; R represents the minimum water level allowed for power generation at the downstream hydropower station; Q represents the minimum water level allowed for power generation at the upstream hydropower station; J represents the current on-grid transaction electricity price, which is also the basic value of the preset on-grid electricity price mentioned in the aforementioned embodiment.

[0612] Combination Figure 6H As shown in the figure, the water resource regulation scheme of the cascade hydropower station is as follows:

[0613] S401, determine the cost electricity price J1, the measured water level S1 of the upstream hydropower station and the measured water level S2 of the downstream hydropower station.

[0614] S402, determine whether S2<R.

[0615] Determine whether the measured water level of the downstream hydropower station is less than the minimum water level allowed for power generation at the downstream hydropower station. If S2 is less than R, proceed to S403; otherwise, proceed to S406.

[0616] S403, determine whether S1>Q and the cost electricity price<on-grid electricity price.

[0617] That is, it is determined whether the measured water level of the upstream hydropower station is greater than the minimum water level allowed for power generation by the upstream hydropower station, and whether the cost electricity price is less than the grid-connected electricity price (the grid-connected electricity price at the current moment). If yes, it proceeds to S404; otherwise, it proceeds to S407.

[0618] S404, conduct quarterly regulation of upstream hydropower stations.

[0619] S405, to make day-ahead adjustments for downstream hydropower stations.

[0620] S406, waiting for a shutdown instruction due to a power grid failure or water shortage in the power plant.

[0621] S407, determine whether the on-grid electricity price change J=J±0.001, and the cost electricity price J1<J.

[0622] If yes, go to step S404; otherwise, go to S408.

[0623] S408, high frequency adjustment of water level, changing water level.

[0624] It should be emphasized that Figure 6H The water resource regulation scheme shown in the figure is only for the convenience of understanding, and is a water resource scheduling scheme that may be used in the actual working process. Different targeted water resource regulation schemes will be adopted for different cascade hydropower stations, at different times, and when the water resource data of each hydropower station is different.

[0625] The second step is to input the training data into a deep learning model to obtain a predicted water resources debugging plan corresponding to the training data.

[0626] Exemplarily, convolutional neural networks, long short-term memory networks, gated recurrent units, etc. can be used as deep learning models in this application.

[0627] The sample water resource data obtained at the sample time point for each hydropower station in the cascade hydropower stations in the training data and the electricity price plan at the sample time point are input into the deep learning model, and the deep learning model inputs the predicted water resource debugging plan.

[0628] In the third step, taking the sample water resources scheduling plan as the true value, the back propagation error of the sample water resources deep debugging plan and the predicted water resources debugging plan is determined through the loss function, and the network parameters of the deep learning model are updated based on the back propagation error until the back propagation error reaches the set value to obtain the trained water resources scheduling model.

[0629] In this application, the sample water resource scheduling plan at the sample time point in the training data is taken as the true value, and the difference between the sample water resource deep debugging plan and the predicted water resource debugging plan, that is, the back propagation error, is calculated through the loss function. The back propagation error is used as the loss value, and the network parameters in the deep learning model, such as weights and biases, are updated through the loss value to reduce future back propagation errors. When the latest back propagation error reaches the set value, the training is stopped to obtain a trained water resource debugging model.

[0630] The loss function is the basis for guiding the model to learn effectively. Different loss functions can be selected or designed based on different tasks so that the model can mine valuable information from the data. Below we introduce several common loss functions. Common loss functions include: square loss function, cross entropy loss, mean square error and mean absolute error, etc. The specific form of the loss function is not limited in this application. Loss function and optimization algorithm are two important components of machine learning. Based on the loss function, the selected optimization algorithm can also be selected according to actual needs. For example, a gradient descent algorithm is used. This algorithm uses gradient information to find a suitable solution by continuously iterating and adjusting parameters.

[0631] In summary, the present application provides a method for water resource scheduling of cascade hydropower stations, including: obtaining water resource data of each hydropower station in the cascade hydropower station at the current moment; for each hydropower station, judging whether the hydropower station is in a safe operating state according to the water resource data of the hydropower station; when it is determined that each hydropower station is in a safe operating state, judging whether to perform water resource scheduling according to the water resource data of each hydropower station, a preset electricity price plan and target historical data; if it is determined to perform water resource scheduling, then determining a water resource scheduling plan based on the water resource data of each hydropower station and a water resource scheduling model. In this way, by replacing the method of manual experience with a water resource scheduling model, the most excellent water resource debugging plan can be determined based on the water resource data of each hydropower station at different times, under the premise of ensuring the safe operating state of the hydropower station, so as to obtain as high a power generation income as possible.

[0632] It should be noted that in addition to the method for determining whether each hydropower station in a cascade hydropower station is in a safe operating state mentioned in the aforementioned embodiment of the present application, it is also necessary to conduct a load shedding test on each reservoir in the cascade hydropower station before the cascade hydropower station is officially put into operation to determine whether the operating parameters of each hydropower station in the cascade hydropower station meet the preset load shedding test index requirements under emergency conditions; that is, to determine whether the power generation equipment of each hydropower station in the cascade hydropower station can work normally under emergency conditions, thereby verifying the dynamic per...

Claims

1. A method for constructing a digital power system based on a multifunctional intelligent agent, characterized in that: include: Extract characteristic production factor data corresponding to the characteristic production factor group from the power plant side's power data; and, extracting control production factor data corresponding to the control production factor group from the power data on the grid side; The characteristic production factor group includes characteristic production factors of multiple levels; the control production factor group includes control production factors of multiple aspects; Based on the power function requirements of the digital power system, the target data vector is constructed using the extracted characteristic production factor data, and key control production factor data associated with the power function requirements are determined from the extracted control production factor data; Based on the target data vector and the key control production factor data, an artificial intelligence algorithm is used to learn a mapping function between the target data vector and the key control production factor data, a functional operator with the mapping function as the core is constructed, and an intelligent agent is constructed based on the functional operator; Intelligent agents corresponding to various different power function requirements are added to the digital power system, and each intelligent agent is used as a power function realization unit in the digital power system.

2. The method according to claim 1, characterized in that The characteristic production factor group includes first-level characteristic production factors, second-level characteristic production factors and third-level characteristic production factors corresponding to various different power generation types; among them, the first-level characteristic production factors are natural characteristic production factors, the second-level characteristic production factors are single-system characteristic production factors, and the third-level characteristic production factors are plant system characteristic production factors; the natural characteristic production factors are production factors that directly reflect natural characteristics; the single-system characteristic production factors are production factors involving individual systems in the power system; and the plant system characteristic production factors are production factors involving the entire system in the power system.

3. The method according to claim 1, characterized in that: The multiple aspects of controlled production factors include: electricity price, inertia and frequency, active and reactive power, carbon emission, safety and stability, and grid connection and disconnection; The step of extracting the control production factor data corresponding to the control production factor group from the power data on the power grid side includes: From the power data on the grid side, extract electricity price data, inertia and frequency data, power data, electricity carbon emission data, safety and stability index data and grid connection and disconnection impact data.

4. The method according to claim 1, characterized in that: The method further comprises: Configuring a power plant side interface, a grid side interface and an intelligent agent interface for the intelligent agent; The intelligent agent communicates with the power plant through the power plant side interface; The intelligent agent communicates with the power grid via the power grid side interface; The agent communicates with other agents via the agent interface.

5. The method according to any one of claims 1 to 4, characterized in that The power function requirements are: The power function requirements are used for power trading between the grid and the power plant, the power function requirements are used to implement the grid's dispatching and control over the power plant, or the power function requirements are used for the grid's own regulation.

6. The method according to claim 5, characterized in that The power function requirement for power trading between the power grid side and the power plant side is specifically to calculate the power price, the functional operator is the power price operator, and the power price operator is used to calculate the power price; the process of the digital power system using the intelligent agent constructed based on the power price operator includes: Calling the intelligent agent to obtain the electricity price calculation result of the power plant side through the electricity price operator; The electricity price calculation result is verified by a financial verification model on the grid side; the financial verification model includes: a first verification condition and a second verification condition; the first verification condition is: the actual output of various types of power plants ≥ the grid power; the second verification condition is: the sum of the products of the actual output of various types of power plants, the grid power price at the corresponding time and the power generation time ≤ the product of the grid average price and the grid power; If the electricity price calculation result satisfies the first verification condition and the second verification condition, it is determined that the electricity price calculation result has been verified; if the electricity price calculation result does not satisfy any of the first verification condition and the second verification condition, it is determined that the electricity price calculation result has not been verified; If the electricity price calculation result is verified, then further selecting an electricity price calculation function that is adapted and feasible on the grid side from the dispatch strategy library, and loading the electricity price calculation function into the electricity price operator to perform function update on the electricity price operator; The electricity price calculation result on the grid side is obtained through the updated electricity price operator.

7. The method according to claim 6, characterized in that After the electricity price calculation function is loaded into the electricity price operator to perform function update on the electricity price operator, the process of using the intelligent agent constructed based on the electricity price operator also includes: The grid side records the applied transaction power and power price reported by the power plant side to the grid side; Based on the power grid side, judging whether the grid is stable, so as to determine whether it is necessary to start the virtual power plant function; If it is determined that the virtual power plant function does not need to be activated, the grid side sends a dispatch instruction of clearing electricity prices and electricity quantities to various types of power plants based on the electricity price calculation result of the grid side; If it is determined that the virtual power plant function needs to be started, starting the virtual power plant function to call its storage capacity; The power plant receives the clearing electricity price given by the grid; Combining the power plant cost and the clearing electricity price, verification is performed using the financial verification model on the power plant side; the financial verification model on the power plant side includes: a third verification condition; the third verification condition is: the sum of the product of the actual output of the power plant, the grid electricity price at the corresponding moment and the power generation time > the product of the power plant cost and the actual output of the power plant. If the verification result indicates that the verification is passed, the different power supply points of the same power plant type will be further judged based on the power consumption and electricity price to determine whether they can be cleared; If all power supply points can be cleared, the power will be cleared.

8. The method according to claim 5, characterized in that The power function requirement for power trading between the power grid side and the power plant side is specifically power clearing, the functional operator is a clearing operator, and the clearing operator is used for power clearing; the process of the digital power system using an intelligent agent constructed based on the clearing operator includes: Perform low-order data abstraction processing according to the power generation element characteristics of each associated power plant of the power grid to obtain a first data vector of each power generation element characteristic; Performing long-term transaction electricity price prediction according to a preset long-term electricity price function library and each of the first data vectors to establish a long-term transaction stack; Establishing a spot transaction stack based on the spot transaction electricity price of each of the associated power plants, and determining a first clearing function through the long-term transaction stack and the spot transaction stack; Determining, according to the first clearing function, a power supply and demand balance state of the power grid when clearing under the first clearing function; The first clearing function is adjusted according to the power supply and demand balance state to obtain a second clearing function, and power clearing is performed based on the second clearing function.

9. The method according to claim 8, characterized in that The power supply and demand balance state includes: over-generation state; the first clearing function includes: first long-term transaction volume; The step of adjusting the first clearing function according to the power supply and demand balance state to obtain a second clearing function includes: When the power supply and demand balance state is the over-power generation state, high-order data abstract processing is performed on the characteristics of each power generation element through a preset deep learning model to obtain a second data vector of each associated power plant; Determining a long-term transaction volume increase value according to each of the second data vectors and the preset long-term electricity price function library; The first long-term transaction volume is adjusted according to the long-term transaction volume increase value to obtain the second clearing function.

10. The method according to claim 9, characterized in that The power supply and demand balance state includes: under-generation state; the first clearing function includes: first spot transaction volume; The step of adjusting the first clearing function according to the power supply and demand balance state to obtain a second clearing function includes: When the power supply and demand balance state is the under-generation state, for a first power generation curve when the power grid is cleared based on the first clearing function, fitting the first power generation curve by using a preset fitting function to obtain a fitting power generation curve; Based on the fitted power generation curve and the preset planned power generation curve, determining whether the first spot transaction volume satisfies the preset planned power generation curve; When the first spot transaction volume does not satisfy the preset planned power generation curve, the preset long-term electricity price function library is modified by a preset reinforcement learning model to determine a long-term transaction volume reduction value; Adjusting the proportion of the spot trading volume in the first clearing function according to the long-term trading volume reduction value to obtain a spot trading volume increase value; The first spot trading volume is adjusted according to the spot trading volume increase value to obtain the second clearing function.

11. The method according to claim 10, characterized in that When the first spot transaction volume does not satisfy the preset planned power generation curve, the preset long-term electricity price function library is modified by a preset reinforcement learning model to determine a long-term transaction volume reduction value, including: Performing function screening on the preset long-term electricity price function library through a preset reinforcement learning model to obtain a first long-term transaction electricity price function; An index adjustment is performed on the function index of the first long-term transaction electricity price function to determine the long-term transaction volume reduction value.

12. The method according to claim 8, characterized in that The long-term transaction electricity price prediction is performed according to the preset long-term electricity price function library and each of the first data vectors to establish a long-term transaction stack, including: By using the first data vector, a data-driven adjustment is performed on the function index of the preset electricity price function library to obtain a dynamic electricity price function library; Performing a long-term transaction electricity price forecast based on the dynamic electricity price function library and the characteristics of each of the power generation elements to obtain a long-term transaction forecast electricity price for each of the associated power plants; The long-term transaction stack is established by using the long-term transaction predicted electricity price of each of the associated power plants.

13. The method according to claim 8, characterized in that The step of establishing a spot transaction stack based on the spot transaction electricity price of each of the associated power plants includes: Performing power forecasting according to the first data vector of each of the associated power plants to obtain the forecasted power of each of the associated power plants; Establishing a preliminary spot transaction stack according to the predicted power output of each of the associated power plants; Based on the spot transaction electricity price of the associated power plant, the preliminary spot transaction stack is adjusted to obtain the spot transaction stack.

14. The method according to claim 8, characterized in that The step of performing low-order data abstraction processing according to the power generation element characteristics of each of the associated power plants to obtain a first data vector of the power generation element characteristics includes: According to the characteristics of each power generation element, an energy consumption data model of each associated power plant is established; the energy consumption data model is used to evaluate the power generation performance of the associated power plant; The energy consumption data model is used to perform low-order data abstraction processing on the characteristics of each power generation element to obtain the first data vector of the characteristics of each power generation element.

15. The method according to claim 5, characterized in that The power function requirement for realizing the dispatching control of the power plant side by the power grid side is specifically peak-shaving dispatching in the high-frequency variable load scenario of thermal power, and the functional operator is a thermal power peak-shaving dispatching operator, which is used to realize peak-shaving dispatching in the high-frequency variable load scenario of thermal power; the process of the digital power system using an intelligent agent constructed based on the thermal power peak-shaving dispatching operator includes: Calculating the heat storage margin of the energy storage device in the thermal power plant; the heat storage margin includes a heat storage margin characterization value and a heat release capacity characterization value; Sending the correlation data between the load, performance and cost of each thermal power unit in the thermal power plant and the heat storage and access margin to the power grid side, so that the power grid side can determine the target unit for expected auxiliary peak load regulation and issue peak load regulation instructions based on the change of thermal power load demand, the correlation data provided by each thermal power plant and the heat storage and access margin; receiving a peak-shaving dispatch instruction issued by the power grid side; the peak-shaving dispatch instruction carries the unit identification of the target unit and peak-shaving requirement information for the target unit; the peak-shaving requirement information includes a peak-shaving load curve; An auxiliary peak shaving service is performed based on the peak shaving requirement information.

16. The method according to claim 15, characterized in that The process of using the intelligent agent constructed based on the thermal power peak load dispatching operator also includes: Before determining the target unit for the expected auxiliary peak load regulation, according to the peak load curve of each thermal power unit, calculating the quotation information of the auxiliary peak load regulation service provided by the thermal power unit that meets the requirements of the corresponding peak load curve; Sending the quotation information to the power grid side; The grid side determines the target unit for expected auxiliary peak load regulation based on the change of thermal power load demand, the associated data provided by each thermal power plant, and the heat storage and access margin, specifically: The grid side determines the target unit for expected auxiliary peak regulation by weighing costs and indicators through data-driven means based on changes in thermal power load demand, the associated data provided by each thermal power plant, the heat storage and access margin, and the quotation information.

17. The method according to claim 16, characterized in that The grid side determines the target unit for expected auxiliary peak load regulation by weighing costs and indicators through data-driven based on the change of thermal power load demand, the associated data provided by each thermal power plant, the heat storage and access margin and the quotation information, including: The grid side generates a peak load curve for each thermal power unit based on the change in thermal power load demand, the associated data provided by each thermal power plant, and the heat storage and access margin, and calculates the climbing coefficient of each thermal power unit; Preliminarily determine multiple thermal power units expected to assist in peak load regulation based on the ramp coefficients of each thermal power unit; If there is a thermal power unit whose bid information is less than or equal to K times the threshold bid among the multiple thermal power units expected to assist in peak load regulation, the thermal power unit whose bid information is less than or equal to K times the threshold bid is determined as the target unit for expected auxiliary peak load regulation; the K is within the range of 1.1 to 1.3; Among them, the threshold quotation is a quotation reference value obtained by deep learning historical quotation information on the power grid side.

18. The method according to claim 17, characterized in that The process of using the intelligent agent constructed based on the thermal power peak-shaving dispatching operator further includes: after the multiple thermal power units expected to assist in peak-shaving are preliminarily determined, the power grid side sends a heat pre-dispatching instruction to the multiple thermal power units expected to assist in peak-shaving; The target unit among the multiple thermal power units expected to assist in peak load regulation performs heat pre-scheduling in cooperation with the heat storage device in the thermal power plant to which it belongs based on the heat pre-scheduling instruction.

19. The method according to claim 17, characterized in that The peak shaving requirement information also includes climbing speed requirement information; and performing auxiliary peak shaving service based on the peak shaving requirement information includes: Determine whether there is equipment failure and communication failure in the target unit, and determine whether the target unit meets the climbing speed requirement information; If there is no equipment failure and communication failure in the target unit, and the target unit meets the climbing speed requirement information, then according to the peak load curve and the climbing speed requirement information in the peak load requirement information, perform auxiliary peak load shaving service; If there is a device failure or a communication failure in the target unit, a fault message is reported to the power grid side; If the target unit does not meet the ramp speed requirement information, reporting prompt information that the operating condition is not met to the power grid side; The power grid side adjusts the peak load requirement information in the peak load scheduling instruction according to the prompt information that the working condition is not satisfied; The grid side relearns to increase the threshold quotation based on the prompt information of the operating condition not being met fed back by each thermal power plant, so that more units are used as target units for expected auxiliary peak regulation.

20. The method according to claim 17, characterized in that The calculation method of the climbing coefficient of the thermal power unit is: The ramp speed, steam pressure and rated power generation capacity are extracted from the correlation data among the load, performance and cost of the thermal power unit; The climbing coefficient of the thermal power unit is calculated according to the climbing speed, steam pressure, rated power generation capacity, heat storage and access margin of the thermal power unit and the climbing time required by the power plant side for the thermal power unit.

21. The method according to claim 20, characterized in that The heat storage margin is expressed as a percentage; the climbing coefficient of the thermal power unit is calculated according to the climbing coefficient, steam pressure, rated power generation capacity, heat storage margin and the climbing time required by the power plant side for the thermal power unit, including: Calculate the product of the thermal power unit's ramp-up speed, ramp-up time, steam pressure and heat storage margin; The ratio of the product to the rated power generation capacity of the thermal power unit is calculated, and the ratio is used as the climbing coefficient of the thermal power unit.

22. The method according to any one of claims 15 to 21, characterized in that The heat storage and access margin and the associated data are calculated based on the coal type parameters of the selected target coal type; the target coal type is selected in the following manner: According to the high calorific value and the low calorific value corresponding to each of the multiple types of coal to be selected, the difference percentage between the high and low calorific value of each type of coal to be selected is obtained; The coal type with the smallest percentage difference between high and low calorific values ​​among the multiple coal types to be selected is determined as the target coal type.

23. The method according to claim 22, characterized in that The percentage of the difference between high and low calorific values ​​is a low-order feature obtained by extracting features based on the coal type parameters of the corresponding coal type in the thermal power plant; The grid side determines the target unit for expected auxiliary peak load regulation and issues a peak load regulation instruction based on the change of thermal power load demand, the associated data provided by each thermal power plant, and the heat storage and access margin, including: The grid side extracts intermediate features based on the associated data and the heat storage and access margin provided by each thermal power plant, and the intermediate features include features reflecting the energy consumption level and thermal energy reserve level of the power plant; the grid side fuses the coal price cost in the associated data with the intermediate features to obtain high-order features, and the high-order features include the relationship between fuel, electricity and electricity price; The grid side determines the target units for expected auxiliary peak load regulation and issues peak load regulation dispatching instructions based on the changes in thermal power load demand, the mid-order characteristics and the high-order characteristics.

24. The method according to claim 5, characterized in that The power function requirement for realizing the dispatching control of the power plant side by the power grid side is specifically the water resource dispatching of the cascade hydropower station, the functional operator is the water resource dispatching operator, and the water resource dispatching operator is used to realize the water resource dispatching of the cascade hydropower station; the process of the digital power system using the intelligent agent constructed based on the water resource dispatching operator includes: Obtain water resource data of each hydropower station in the cascade hydropower station at the current moment; For each of the hydropower stations, judging whether the hydropower station is in a safe operating state according to the water resources data of the hydropower station; When it is determined that all the hydropower stations are in the safe operation state, judging whether to perform water resource scheduling according to the water resource data of each hydropower station, the preset electricity price scheme and the target historical data; the target historical data includes the average water consumption for power generation and the average power plant revenue corresponding to the month at the current moment; If it is determined to carry out water resource scheduling, a water resource scheduling plan is determined based on the water resource data and water resource scheduling model of each hydropower station; the water resource scheduling model is a pre-trained model for outputting a water resource scheduling plan; the water resource scheduling plan includes day-ahead scheduling and seasonal scheduling.

25. The method according to claim 24, characterized in that The safe operation state includes a water conservation safety state; For each of the hydropower stations, judging whether the hydropower station is in a safe operating state according to the water resources data of the hydropower station includes: For each of the hydropower stations, obtaining the measured velocity rise rate and the measured turbine hydrostatic pressure from the water resource data of the hydropower station; For each of the hydropower stations, if the measured speed increase rate is less than the theoretical speed increase rate, and the measured turbine hydrostatic pressure is less than the theoretical turbine hydrostatic pressure, it is determined that the hydropower station is in the water conservation safety state; If the measured speed increase rate is greater than or equal to the theoretical speed increase rate, or the measured turbine hydrostatic pressure is greater than or equal to the theoretical turbine hydrostatic pressure, it is determined that the hydropower station is not in the water conservation safety state.

26. The method according to claim 24, characterized in that The safe operation state includes a vibration safety state. For each of the hydropower stations, judging whether the hydropower station is in a safe operation state according to the water resources data of the hydropower station includes: For each of the hydropower stations, the power of the turbine engine is obtained from the water resource data of the hydropower station, and recorded as the first power; Determining whether the first power is within a preset power range; If the first power is within the preset power range, the first power is adjusted to the second power; the second power is outside the preset power range; If the first power is outside the preset power range, it is determined whether the hydropower station is in the vibration safety state.

27. The method according to claim 26, characterized in that The determining whether the hydropower station is in the vibration safe state comprises: For each of the hydropower stations, the rotation speed of the turbine engine and actual vibration values ​​of different parts of the turbine engine are obtained from the water resource data of the hydropower station; For each of the hydropower stations, if the actual vibration value of each of the parts is less than the vibration allowable value corresponding to the part at the rotation speed, it is determined that the hydropower station is in the vibration safety state; Otherwise, it is determined that the hydropower station is not in the vibration safe state.

28. The method according to claim 24, characterized in that Before obtaining the water resource data of each hydropower station in the cascade hydropower station at the current moment, the process of using the intelligent agent constructed based on the water resource scheduling operator also includes: A load shedding test is performed on the cascade hydropower stations to determine whether the operating parameters of each hydropower station in the cascade hydropower stations meet the requirements of preset load shedding test indicators.

29. The method according to claim 24, characterized in that The determining whether to perform water resource dispatch according to the water resource data of each hydropower station, the preset electricity price scheme and the target historical data includes: Based on the water resource data of each hydropower station and the preset electricity price scheme, determine the actual water consumption for power generation of each hydropower station and the actual power plant revenue of each hydropower station as current actual data; Based on the difference between the current actual data and the target historical data, it is determined whether to perform water resource scheduling.

30. The method according to claim 29, characterized in that The determining of the actual water consumption for power generation of each hydropower station and the actual power plant revenue of each hydropower station based on the water resource data of each hydropower station and the preset electricity price scheme includes: For each of the hydropower stations, the actual power generation and actual water consumption in a target time period are obtained from the water resource data of the hydropower station; the target time period is a period of time in the past with the current moment as the end point; For each of the hydropower stations, based on the actual power generation and actual water consumption during the target time period, the actual power generation and water consumption during the target time period are obtained; For each of the hydropower stations, the actual power plant revenue for the target time period is determined based on the electricity price plan corresponding to the target time period and the actual water level of the hydropower station.

31. The method according to any one of claims 24 to 30, characterized in that The method for acquiring the target historical data includes: Count the historical water consumption for power generation and the historical power plant revenue for each month in the past N years; N is an integer greater than or equal to 1; For each month, based on the N historical power generation water consumption corresponding to the month, a historical power generation water consumption map corresponding to the month is obtained; and based on the N historical power plant revenues corresponding to the month, a historical power plant revenue map corresponding to the month is obtained; the historical power generation water consumption map represents the relationship between the historical power generation water consumption and time; the historical power plant revenue map represents the relationship between the historical power plant revenue and time; The average power generation water consumption corresponding to the historical power generation water consumption map corresponding to the month of the current moment and the average power plant revenue corresponding to the historical power plant revenue map corresponding to the month of the current moment are used as the target historical data.

32. The method according to any one of claims 24 to 30, characterized in that The training steps of the water resource scheduling model include: Acquire training data; the training data includes sample water resource data of each hydropower station in the cascade hydropower stations at a sample time point, an electricity price plan at the sample time point, and a sample water resource scheduling plan at the sample time point; the sample time point is any time point among multiple time points at which the hydropower station operates under full working conditions; the sample water resource data includes historical water consumption for power generation, historical power plant revenue, and historical average water assets; the sample water resource scheduling plan includes day-ahead scheduling and seasonal scheduling; Inputting the training data into a deep learning model to obtain a predicted water resources debugging plan corresponding to the training data; Taking the sample water resource scheduling plan as the true value, the back propagation error of the sample water resource deep debugging plan and the predicted water resource debugging plan is determined through the loss function, and the network parameters of the deep learning model are updated based on the back propagation error until the back propagation error reaches the set value, thereby obtaining the water resource scheduling model.

33. The method according to claim 5, characterized in that The power function requirement for realizing the dispatching control of the power grid side to the power plant side is specifically the dispatching of the power grid to the power plant in the large-machine small-grid power system, and the functional operator is the large-machine small-grid dispatching operator, which is used to realize the dispatching of the power grid to the power plant in the large-machine small-grid power system; the process of the digital power system using the intelligent agent constructed based on the large-machine small-grid dispatching operator includes: Based on the digital feature extraction of the power grid and power supply points of various power generation types in the power system, determine the emergency reserve capacity of various power generation types that should be reserved in the power system and configure the emergency reserve capacity; Based on the output of the power source points of the multiple power generation types, judging whether the current power system meets the characteristics of large machine and small grid; If it is determined that the current power system meets the characteristics of large machines and small grids, the power grid utilizes the configured emergency reserve capacity of multiple power generation types to dispatch power supply points in the power system for voltage adjustment based on a voltage multi-round adjustment scheme, and / or dispatches power supply points in the power system for frequency adjustment based on a frequency multi-round adjustment scheme; the voltage multi-round adjustment scheme includes: voltage multi-round adjustment methods, voltage multi-round adjustment ranges, and voltage multi-round adjustment priority information for the multiple power generation types; the frequency multi-round adjustment scheme includes: frequency multi-round adjustment methods, frequency multi-round adjustment ranges, and frequency multi-round adjustment priority information for the multiple power generation types; Based on the stability control requirements of the frequency dynamic characteristic index of the whole network of the power system, the expected load of the whole network and the characteristics of the units of each power source point, the power grid generates the output curve of the units of each power source point in the future period; the frequency dynamic characteristic index is used to numerically characterize the power change of the whole network required to cause the unit frequency change of the power system; The power grid sends a power generation dispatching instruction to each power source point to adjust the power; the power generation dispatching instruction includes an output curve of the unit at the corresponding power source point.

34. The method according to claim 33, characterized in that The voltage multi-round adjustment range includes: photovoltaic, hydropower, nuclear power, thermal power and energy storage; the voltage multi-round adjustment priority information includes: photovoltaic>hydropower>nuclear power>thermal power>energy storage; The multiple rounds of voltage adjustments include: four basic rounds of voltage adjustments corresponding to photovoltaic, hydropower, nuclear power and thermal power, and one accident round of voltage adjustments corresponding to fault conditions; The voltage multi-round adjustment method includes: the action voltage and delay of the first basic round, the action voltage difference and delay of the remaining basic rounds, and the action voltage and delay of the accident round.

35. The method according to claim 34, characterized in that The action voltage of the first basic wheel is 0.84pu, with a delay of 15 to 20s; The action voltage difference of the remaining basic wheels is 0.01pu, and the delay is 0.2s; The operating voltage of the accident wheel is 0.8pu and the delay is 0.1s; Utilize the emergency reserve capacity of various types of power generation that have been configured to adjust the voltage based on the multi-round voltage adjustment scheme, including: If the voltage of the power system is as low as 0.84 pu, the voltage adjustment corresponding to the first basic round of photovoltaic is started and lasts for 15 to 20 seconds; During the voltage adjustment of the first basic round, a portion of the photovoltaic emergency reserve capacity is injected into the power grid; If the voltage adjustment effect of the first basic round does not achieve the expected effect, when the voltage of the power system drops to 0.83pu, the second basic round of voltage adjustment corresponding to the hydropower is started and lasts for 0.2s; during the voltage adjustment period of the second basic round, a part of the emergency reserve capacity of the hydropower is injected into the power grid; If the voltage adjustment effect of the second basic round does not achieve the expected effect, when the voltage of the power system drops to 0.82pu, the third basic round of voltage adjustment corresponding to the nuclear power is started and lasts for 0.2s; during the voltage adjustment period of the third basic round, a part of the emergency reserve capacity of the nuclear power is injected into the power grid; If the voltage adjustment effect of the third basic round does not achieve the expected effect, when the voltage of the power system drops to 0.81pu, the fourth basic round of voltage adjustment corresponding to thermal power is started and lasts for 0.2s; during the fourth basic round of voltage adjustment, a part of the emergency reserve capacity of thermal power is injected into the power grid; If the voltage adjustment effect of the fourth basic round fails to achieve the expected effect, and the voltage of the power system is monitored to be as low as 0.8pu, the voltage adjustment of the accident round is started, the load is cut off or the energy storage system is started; during the voltage adjustment of the accident round, all or part of the remaining accident reserve capacity of each power generation type is injected into the power grid.

36. The method according to claim 33, characterized in that The frequency multi-round adjustment range includes: thermal power, hydropower, nuclear power and energy storage; the frequency multi-round adjustment priority information includes: thermal power>hydropower>nuclear power>energy storage; The multiple rounds of frequency adjustments include: three basic rounds of frequency adjustments corresponding to thermal power, hydropower, and nuclear power, and one round of accident frequency adjustments corresponding to fault conditions; The frequency multi-round adjustment method includes: the action frequency and delay of the first basic wheel, the action frequency difference and delay of the remaining basic wheels, and the action frequency and delay of the accident wheel.

37. The method according to claim 36, characterized in that The action frequency of the first basic wheel is 49.8 Hz, with a delay of 0.2 s; The action frequency difference of the remaining basic wheels is 0.2 Hz, and the delay is 0.2 s; The operating frequency of the accident wheel is 49.2 Hz, with a delay of 0.1 s; Utilize the configured emergency reserve capacity of various power generation types to adjust the frequency based on the frequency multi-round adjustment scheme, including: If the frequency of the power system drops to 49.8 Hz, the frequency adjustment of the first basic round corresponding to thermal power is started and lasts for 0.2 s; During the first basic round of frequency adjustment, a portion of the emergency reserve capacity of thermal power is injected into the power grid; If the frequency adjustment effect of the first basic round does not achieve the expected effect, when the frequency of the power system drops to 49.6 Hz, the second basic round of frequency adjustment corresponding to the hydropower is started and lasts for 0.2 s; during the second basic round of frequency adjustment, a part of the emergency reserve capacity of the hydropower is injected into the power grid; If the frequency adjustment effect of the second basic round does not achieve the expected effect, when the frequency of the power system drops to 49.4 Hz, the third basic round of frequency adjustment corresponding to the nuclear power is started and lasts for 0.2 s; during the third basic round of frequency adjustment, a part of the nuclear power emergency reserve capacity is injected into the power grid; If the frequency adjustment effect of the third basic round does not achieve the expected effect, wait until the frequency of the power system drops to 49.2Hz, start the frequency adjustment of the accident round, cut off the load or start the energy storage system; during the frequency adjustment of the accident round, all or part of the remaining accident reserve capacity of each power generation type will be injected into the power grid.

38. The method according to claim 33, characterized in that Based on the stability control requirements of the frequency dynamic characteristic index of the whole network of the power system, the estimated whole network load and the characteristics of the units of each power source point, the power grid generates the output curve of the units of each power source point in the future period, including: Determine the target value of the frequency dynamic characteristic index; Based on the target value, the monitored frequency disturbance of the power system, the expected load of the entire network and the unit characteristics of each power source, the output curve of the units at each power source in the future period is generated, so as to control the power of each unit through the output curve, so that the deviation between the actual value of the frequency dynamic characteristic index and the target value is within the preset index floating range; the unit characteristics include the power change that the unit of the power source needs to provide for unit frequency change.

39. The method according to claim 38, characterized in that The generating unit output curve of each power source point in the future period is generated based on the target value, the monitored frequency disturbance of the power system, the expected load of the entire network and the characteristics of the units of each power source point, including: Based on the target value, the monitored frequency disturbance of the power system, and the unit characteristics of each power source point, determine the power change amount that should be provided by the power source point of each power generation type so that the deviation amount between the actual value of the frequency dynamic characteristic index and the target value is within a preset index floating range; Based on the predicted total grid load in the future period and the power variation that the power sources of each type of power generation should provide, the output curve of the units at each power source in the future period is generated.

40. The method according to any one of claims 33 to 39, characterized in that The determining, based on the outputs of the power supply points of the multiple power generation types, whether the current power system meets the large-machine-small-grid feature includes: If the sum of the outputs of any two units in any current power source point of any power generation type exceeds 15% of the total capacity of the current power system, it is determined that the power system meets the characteristics of large units and small grids.

41. The method according to claim 5, characterized in that The power function requirement for self-regulation of the power grid is specifically to regulate the grid structure of the power grid, and the functional operator is a grid structure regulation operator, which is used to achieve regulation of the grid structure of the power grid; The process of the digital power system using an intelligent agent constructed based on the grid structure adjustment operator includes: Get the current system inertia corresponding to the current grid structure; Calculating a frequency change rate based on the current system inertia and a difference between a power demand and an actual power supply; If the frequency change rate is greater than a preset first threshold, a target grid structure and a target constant value corresponding to the target grid structure are determined based on a pre-established deep learning model; the frequency change rate of the target grid structure is less than or equal to the first threshold; The current set values ​​applied in the current grid structure are modified based on the target set values, and the current grid structure of the power grid is adjusted to the target grid structure.

42. The method according to claim 41, characterized in that Determine the target grid structure based on a pre-established deep learning model, including: Based on the pre-established deep learning model, the simulation system inertia of all optional grid structures is calculated in parallel, and the optional grid structure with the largest simulation system inertia is determined as the target grid structure.

43. The method according to claim 41, characterized in that Determine the target grid structure based on a pre-established deep learning model, including: Based on the operating parameters of all optional grid structures, the frequency change rate and the difference change between the power generation and the power demand corresponding to each of the multiple adjustment schemes switched from the current grid structure to each optional grid structure are calculated through a pre-established deep learning model, and the scheme types to which the multiple adjustment schemes belong are obtained; the scheme types include stable and aggressive; If a stable adjustment scheme exists, the target grid structure is determined from the optional grid structures corresponding to the stable adjustment scheme.

44. The method according to claim 41, characterized in that Before determining the target grid structure and the target value corresponding to the target grid structure based on the pre-established deep learning model, the method further includes: If there is a faulty node, the faulty node is removed from the current grid structure; the node includes at least one of a power plant, a substation and a dispatching control center.

45. The method according to claim 41, characterized in that Determine the target grid structure based on a pre-established deep learning model, including: Based on a pre-established deep learning model, and according to the matching situation between power generation and power demand in the current grid structure, a target grid structure that satisfies the balance condition between power generation and power demand is determined.

46. ​​The method according to claim 45, characterized in that The method of determining a target grid structure that satisfies a balance condition between power generation and power demand based on a pre-established deep learning model and according to a matching condition between power generation and power demand in the current grid structure comprises: Obtaining the power generation change rate of each power generation type grid node in the current grid structure; If there are grid nodes whose power generation is reduced and whose power generation change rate is greater than a preset change rate threshold, then based on the pre-established deep learning model and according to the matching of power generation and power demand in the current grid structure, determine a target grid structure in which a power generation type grid grid is added on the basis of the current grid structure; If there are grid nodes with increased power generation and a power generation change rate greater than a preset change rate threshold, then based on a pre-established deep learning model and according to the matching of power generation and power demand in the current grid structure, a target grid structure for adding a load-type power grid grid is determined based on the current grid structure.

47. The method according to claim 41, characterized in that Determine the target grid structure based on a pre-established deep learning model, including: Based on a pre-established deep learning model, and according to the security priority of the current grid structure, a target network structure having a stability higher than a preset limit is determined.

48. The method according to claim 41, characterized in that Determine the target grid structure based on a pre-established deep learning model, including: Based on the pre-established deep learning model and grid transfer function, the performance impact of multiple regulation schemes switching from the current grid structure to various optional grid structures on other grids in the power system is obtained; Based on the pre-established deep learning model and the performance impact, a target grid structure is determined.

49. The method according to claim 41, characterized in that Determine the target value corresponding to the target grid structure based on the pre-established deep learning model, including: Through a pre-established deep learning model, based on a typical value library and a target grid structure, a target constant value corresponding to the target grid structure is determined; the typical value library at least includes a correspondence between historical constant value data and a grid structure.

50. The method according to claim 41, characterized in that The adjusting the current grid structure of the power grid to the target grid structure comprises: Based on the current grid structure and the target grid structure, determining a target action that a plurality of relays need to perform; the target action is opening or closing; Based on the action time information of each relay, multiple relays are controlled to perform the target action to achieve adjustment from the current grid structure to the target grid structure; the action time information includes the transmission time of the target set value, the time required to write the target set value, the duration of the protection action, the time required for the relay to close, the time required for the relay to open, and the time required to return the status information.

51. The method according to claim 41, characterized in that The adjusting the current grid structure of the power grid to the target grid structure comprises: Based on the target constants stored in the binary tree structure, parallel calculation is performed to obtain the action information of multiple relays that need to perform the target action during the process of adjusting the current grid structure to the target grid structure; the target action is opening or closing; the action information includes the time node when the relay is allowed to act and the order in which the multiple relays perform the actions; Based on the action information of each of the plurality of relays, the plurality of relays are controlled to perform a target action, so as to adjust the current grid structure to the target grid structure.

52. A device for constructing a digital power system based on a multifunctional intelligent agent, characterized in that: include: A data extraction module is used to extract characteristic production factor data corresponding to the characteristic production factor group from the power data on the power plant side; and, extracting control production factor data corresponding to the control production factor group from the power data on the grid side; The characteristic production factor group includes characteristic production factors of multiple levels; the control production factor group includes control production factors of multiple aspects; A vector construction module, used to construct a target data vector using the extracted characteristic production factor data based on the power function requirements of the digital power system; A data determination module, used to determine key control production factor data associated with the power function requirement from the extracted control production factor data; An operator construction module is used to use an artificial intelligence algorithm to learn a mapping function between the target data vector and the key control production factor data based on the target data vector and the key control production factor data, construct a functional operator with the mapping function as the core, and construct an intelligent agent based on the functional operator; The intelligent agent adding module is used to add intelligent agents corresponding to various different power function requirements to the digital power system, and use each intelligent agent as a power function realization unit in the digital power system.

53. The device according to claim 52, characterized in that The power function requirements are: The power function requirements are used for power trading between the grid and the power plant, the power function requirements are used to implement the grid's dispatching and control over the power plant, or the power function requirements are used for the grid's own regulation.

54. The device according to claim 53, characterized in that The power function requirement for power trading between the power grid side and the power plant side is specifically to calculate the power price, the functional operator is the power price operator, and the power price operator is used to calculate the power price; the process of the digital power system using the intelligent agent constructed based on the power price operator includes: Calling the intelligent agent to obtain the electricity price calculation result of the power plant side through the electricity price operator; The electricity price calculation result is verified by a financial verification model on the grid side; the financial verification model includes: a first verification condition and a second verification condition; the first verification condition is: the actual output of various types of power plants ≥ the grid power; the second verification condition is: the sum of the products of the actual output of various types of power plants, the grid power price at the corresponding time and the power generation time ≤ the product of the grid average price and the grid power; If the electricity price calculation result satisfies the first verification condition and the second verification condition, it is determined that the electricity price calculation result has been verified; if the electricity price calculation result does not satisfy any of the first verification condition and the second verification condition, it is determined that the electricity price calculation result has not been verified; If the electricity price calculation result is verified, then further selecting an electricity price calculation function that is adapted and feasible on the grid side from the dispatch strategy library, and loading the electricity price calculation function into the electricity price operator to perform function update on the electricity price operator; The electricity price calculation result on the grid side is obtained through the updated electricity price operator.

55. The device according to claim 53, characterized in that The power function requirement for power trading between the power grid side and the power plant side is specifically power clearing, the functional operator is a clearing operator, and the clearing operator is used for power clearing; the process of the digital power system using an intelligent agent constructed based on the clearing operator includes: Perform low-order data abstraction processing according to the power generation element characteristics of each associated power plant of the power grid to obtain a first data vector of each power generation element characteristic; Performing long-term transaction electricity price prediction according to a preset long-term electricity price function library and each of the first data vectors to establish a long-term transaction stack; Establishing a spot transaction stack based on the spot transaction electricity price of each of the associated power plants, and determining a first clearing function through the long-term transaction stack and the spot transaction stack; Determining, according to the first clearing function, a power supply and demand balance state of the power grid when clearing under the first clearing function; The first clearing function is adjusted according to the power supply and demand balance state to obtain a second clearing function, and power clearing is performed based on the second clearing function.

56. The device according to claim 53, characterized in that The power function requirement for realizing the dispatching control of the power plant side by the power grid side is specifically peak-shaving dispatching in the high-frequency variable load scenario of thermal power, and the functional operator is a thermal power peak-shaving dispatching operator, which is used to realize peak-shaving dispatching in the high-frequency variable load scenario of thermal power; the process of the digital power system using an intelligent agent constructed based on the thermal power peak-shaving dispatching operator includes: Calculating the heat storage margin of the energy storage device in the thermal power plant; the heat storage margin includes a heat storage margin characterization value and a heat release capacity characterization value; Sending the correlation data between the load, performance and cost of each thermal power unit in the thermal power plant and the heat storage and access margin to the power grid side, so that the power grid side can determine the target unit for expected auxiliary peak load regulation and issue peak load regulation instructions based on the change of thermal power load demand, the correlation data provided by each thermal power plant and the heat storage and access margin; receiving a peak-shaving dispatch instruction issued by the power grid side; the peak-shaving dispatch instruction carries the unit identification of the target unit and peak-shaving requirement information for the target unit; the peak-shaving requirement information includes a peak-shaving load curve; An auxiliary peak shaving service is performed based on the peak shaving requirement information.

57. The device according to claim 53, characterized in that The power function requirement for realizing the dispatching control of the power plant side by the power grid side is specifically the water resource dispatching of the cascade hydropower station, the functional operator is the water resource dispatching operator, and the water resource dispatching operator is used to realize the water resource dispatching of the cascade hydropower station; the process of the digital power system using the intelligent agent constructed based on the water resource dispatching operator includes: Obtain water resource data of each hydropower station in the cascade hydropower station at the current moment; For each of the hydropower stations, judging whether the hydropower station is in a safe operating state according to the water resources data of the hydropower station; When it is determined that all the hydropower stations are in the safe operation state, judging whether to perform water resource scheduling according to the water resource data of each hydropower station, the preset electricity price scheme and the target historical data; the target historical data includes the average water consumption for power generation and the average power plant revenue corresponding to the month at the current moment; If it is determined to carry out water resource scheduling, a water resource scheduling plan is determined based on the water resource data and water resource scheduling model of each hydropower station; the water resource scheduling model is a pre-trained model for outputting a water resource scheduling plan; the water resource scheduling plan includes day-ahead scheduling and seasonal scheduling.

58. The device according to claim 53, characterized in that The power function requirement for realizing the dispatching control of the power grid side to the power plant side is specifically the dispatching of the power grid to the power plant in the large-machine small-grid power system, and the functional operator is the large-machine small-grid dispatching operator, which is used to realize the dispatching of the power grid to the power plant in the large-machine small-grid power system; the process of the digital power system using the intelligent agent constructed based on the large-machine small-grid dispatching operator includes: Based on the digital feature extraction of the power grid and power supply points of various power generation types in the power system, determine the emergency reserve capacity of various power generation types that should be reserved in the power system and configure the emergency reserve capacity; Based on the output of the power source points of the multiple power generation types, judging whether the current power system meets the characteristics of large machine and small grid; If it is determined that the current power system meets the characteristics of large machines and small grids, the power grid utilizes the configured emergency reserve capacity of multiple power generation types to dispatch power supply points in the power system for voltage adjustment based on a voltage multi-round adjustment scheme, and / or dispatches power supply points in the power system for frequency adjustment based on a frequency multi-round adjustment scheme; the voltage multi-round adjustment scheme includes: voltage multi-round adjustment methods, voltage multi-round adjustment ranges, and voltage multi-round adjustment priority information for the multiple power generation types; the frequency multi-round adjustment scheme includes: frequency multi-round adjustment methods, frequency multi-round adjustment ranges, and frequency multi-round adjustment priority information for the multiple power generation types; Based on the stability control requirements of the frequency dynamic characteristic index of the whole network of the power system, the expected load of the whole network and the characteristics of the units of each power source point, the power grid generates the output curve of the units of each power source point in the future period; the frequency dynamic characteristic index is used to numerically characterize the power change of the whole network required to cause the unit frequency change of the power system; The power grid sends a power generation dispatching instruction to each power source point to adjust the power; the power generation dispatching instruction includes an output curve of the unit at the corresponding power source point.

59. The device according to claim 53, characterized in that The power function requirement for self-regulation of the power grid is specifically to regulate the grid structure of the power grid, and the functional operator is a grid structure regulation operator, which is used to achieve regulation of the grid structure of the power grid; The process of the digital power system using an intelligent agent constructed based on the grid structure adjustment operator includes: Get the current system inertia corresponding to the current grid structure; Calculating a frequency change rate based on the current system inertia and a difference between a power demand and an actual power supply; If the frequency change rate is greater than a preset first threshold, a target grid structure and a target constant value corresponding to the target grid structure are determined based on a pre-established deep learning model; the frequency change rate of the target grid structure is less than or equal to the first threshold; The current set values ​​applied in the current grid structure are modified based on the target set values, and the current grid structure of the power grid is adjusted to the target grid structure.

Images