Novel power system operation resource optimal configuration method, device, equipment and medium

Abstract

The invention relates to the technical field of intelligent power grids, in particular to a novel power system operation resource optimal configuration method, device and equipment and a medium, and the method comprises the steps: storing collected historical operation data of operation resources and related data as knowledge in a knowledge base; identifying uncertainty influence factor data of operation resources in the knowledge base; based on the historical operation data in the knowledge base and the corresponding uncertainty influence factor data, performing quantitative calculation to obtain a quantitative result of the uncertainty influence factors of the operation resources; and determining a configuration strategy for the operation resources based on the quantification result of the uncertainty influence factors of the operation resources. The problem that the influence of the uncertainty influence factors on the power system cannot be effectively processed in the prior art can be solved, the uncertainty influence factors can be effectively processed, the operation resources in the power system are reasonably planned, and the resource planning method and device are mainly used for resource planning of the novel power system.

Description

Technical Field

[0001] The present disclosure relates to the technical field of smart grids, and particularly to a method, device, equipment and medium for optimizing the allocation of operating resources in a new power system. Background Art

[0002] In the development process of the new power system, the access of elements such as distributed power sources (such as photovoltaic power generation, wind power generation), electric vehicles, energy storage devices, and flexible loads has brought significant improvements in the flexibility and sustainability of the power system. However, the power resource output and demand of these elements are highly uncertain. For example, photovoltaic power generation is affected by light intensity, wind power generation depends on wind speed changes, and the output power is intermittent and volatile; the charging and discharging behavior of electric vehicles is affected by user travel habits and is random; the charging and discharging capacity of energy storage devices is limited by the battery state, and the charging and discharging state and capacity are uncertain; the response ability of flexible loads is related to factors such as electricity price policies and user comfort. These uncertain influencing factors pose great challenges to the planning, operation and control of the power system. Traditional analysis and optimization methods are difficult to meet the requirements of the new power system. Therefore, there is an urgent need for a method that can effectively handle these uncertain influencing factors and reasonably plan the operating resources in the power system. Summary of the Invention

[0003] To solve the problems in the related art, embodiments of the present disclosure provide a method, device, equipment and medium for optimizing the allocation of operating resources in a new power system.

[0004] In a first aspect, embodiments of the present disclosure provide a method for optimizing the allocation of operating resources in a new power system, including: Collecting historical operation data and related data of the operating resources of the power system; Storing the historical operation data and related data of the operating resources as knowledge in a knowledge base; Identifying the data of uncertain influencing factors of the operating resources in the knowledge base; Based on the historical operation data in the knowledge base and its corresponding data of uncertain influencing factors, quantitatively calculating the uncertain influencing factors of the operating resources to obtain a quantitative result of the uncertain influencing factors of the operating resources; Based on the quantitative result of the uncertain influencing factors of the operating resources, determining a configuration strategy for the operating resources.

[0005] In a possible implementation manner, the operating resources include at least one of distributed power sources, electric vehicles, energy storage devices, and flexible loads.

[0006] In a possible implementation, quantifying the uncertainty influencing factors of the operation resources based on the historical operation data and their corresponding uncertainty influencing factor data in the knowledge base to obtain the quantification result of the uncertainty influencing factors of the operation resources includes: Training a pre-set model according to the historical operation data and their corresponding uncertainty influencing factor data in the knowledge base, and using the model parameters of the trained model as the quantification result of the uncertainty influencing factors.

[0007] In a possible implementation, the trained model includes a prediction model. Determining a configuration strategy for the operation resources based on the quantification result of the uncertainty influencing factors of the operation resources includes: Determining the day-ahead regulation strategy of the operation resources based on the predicted operation data of the operation resources in the future time predicted by the prediction model; Correcting the day-ahead regulation strategy based on the real-time operation data of the operation resources in the future time to determine the intra-day regulation strategy of the operation resources.

[0008] In a possible implementation, the method further includes: Obtaining the resource type of the operation resources, where the resource type includes day-ahead type and intra-day type; After determining the day-ahead regulation strategies of the day-ahead type and intra-day type operation resources, publishing the day-ahead regulation strategy of the day-ahead type operation resources.

[0009] In a possible implementation, determining the day-ahead regulation strategy of the operation resources based on the predicted operation data of the operation resources in the future time predicted by the prediction model includes: The cloud master station determines the day-ahead regulation strategy of the operation resources based on the predicted operation data of the operation resources in the future time predicted by the prediction model; Correcting the day-ahead regulation strategy based on the real-time operation data of the operation resources in the future time to determine the intra-day regulation strategy of the operation resources includes: The edge device corrects the day-ahead regulation strategy based on the real-time operation data of the operation resources in the future time to determine the intra-day regulation strategy of the operation resources.

[0010] In a possible implementation, the method further includes: The cloud master station performs cross-substation regulation based on the current regulation strategies of each substation area.

[0011] In a possible implementation manner, determining a day-ahead regulation strategy for the operating resources based on the predicted operating data of the operating resources predicted by the prediction model includes: Determining the regulation cost of the operating resources based on the predicted operating data of the operating resources predicted by the prediction model; Based on the regulation cost of the operating resources, constructing the following objective function: ; ; Wherein, refers to the regulation cost of the flexible load, refers to the regulation cost of the distributed energy, refers to the regulation cost of the energy storage device, refers to the regulation cost of the electric vehicle, is the minimum total regulation cost of the operating resources within the time period , refers to the power demanded by the flexible load at the moment , refers to the power demanded by the distributed energy at the moment , refers to the power demanded by the energy storage device at the moment , refers to the power demanded by the electric vehicle at the moment , is the load shedding penalty, is the power grid operation cost; the constraint conditions corresponding to the objective function include the reduction upper limit of the day-ahead load in the flexible load, the upper and lower limits of the output of the distributed energy, and the dynamic balance of the state of charge SOC of the energy storage device; Solving the minimum value of the objective function to obtain the day-ahead regulation strategy of the operating resources.

[0012] In a second aspect, an optimized configuration device for operating resources of a new power system provided in an embodiment of the present disclosure includes: A data acquisition module configured to acquire historical operating data and related data of the operating resources of the power system; A storage module configured to store the historical operating data and related data of the operating resources as knowledge in a knowledge base; An identification module configured to identify data of uncertainty influencing factors of the operating resources in the knowledge base; A quantification module configured to perform a quantification calculation on the uncertainty influencing factors of the operating resources based on the historical operating data in the knowledge base and the corresponding data of the uncertainty influencing factors to obtain a quantification result of the uncertainty influencing factors of the operating resources; A configuration module, configured to determine a configuration strategy for the operating resources based on the quantification result of the uncertainty influencing factors of the operating resources.

[0013] In a possible implementation, the operating resources include at least one of distributed power sources, electric vehicles, energy storage devices, and flexible loads.

[0014] In a possible implementation, the quantification module is configured to: Train a pre-set model according to the historical operating data and its corresponding uncertainty influencing factor data in the knowledge base to obtain a trained model, and the model parameters of the trained model are the quantification results of the uncertainty influencing factors.

[0015] In a possible implementation, the trained model includes a prediction model, and the configuration module is configured to: Determine the day-ahead regulation strategy of the operating resources based on the predicted operating data of the operating resources in the future time predicted by the prediction model; Based on the real-time operating data of the operating resources in the future time, correct the day-ahead regulation strategy to determine the intra-day regulation strategy of the operating resources.

[0016] In a possible implementation, the device further includes: A type acquisition module, configured to acquire the resource type of the operating resources, and the resource type includes day-ahead type and intra-day type; A strategy publishing module, configured to publish the day-ahead regulation strategy of the day-ahead type operating resources after determining the day-ahead regulation strategies of the day-ahead type and intra-day type operating resources.

[0017] In a possible implementation, the part in the configuration module that determines the day-ahead regulation strategy of the operating resources based on the predicted operating data of the operating resources in the future time predicted by the prediction model is configured to: The cloud master station determines the day-ahead regulation strategy of the operating resources based on the predicted operating data of the operating resources in the future time predicted by the prediction model; The part in the configuration module that corrects the day-ahead regulation strategy based on the real-time operating data of the operating resources in the future time to determine the intra-day regulation strategy of the operating resources is configured to: The edge device corrects the day-ahead regulation strategy based on the real-time operating data of the operating resources in the future time to determine the intra-day regulation strategy of the operating resources.

[0018] In a possible implementation, the device further includes: The regulation module is configured to perform cross-substation regulation by the cloud master station based on the current regulation strategies of each substation area.

[0019] In a possible implementation manner, the part in the configuration module that determines the day-ahead regulation strategy of the operating resources based on the predicted operation data of the operating resources predicted by the prediction model is configured to: Determine the regulation cost of the operating resources based on the predicted operation data of the operating resources predicted by the prediction model at future times; Based on the regulation cost of the operating resources, construct the following objective function: ; ; wherein, refers to the regulation cost of flexible loads, refers to the regulation cost of distributed energy, refers to the regulation cost of energy storage devices, refers to the regulation cost of electric vehicles, is the minimum total regulation cost of the operating resources within the time period , refers to the power demanded by the flexible load at the moment , refers to the power demanded by the distributed energy at the moment , refers to the power demanded by the energy storage device at the moment , refers to the power demanded by the electric vehicle at the moment , is the load shedding penalty, is the power grid operation cost; the constraint conditions corresponding to the objective function include the upper limit of the reduction of day-ahead loads in flexible loads, the upper and lower limits of the output of distributed energy, and the dynamic balance of the state of charge SOC of energy storage devices; Solve the minimum value of the objective function to obtain the day-ahead regulation strategy of the operating resources.

[0020] In a third aspect, an embodiment of the present disclosure provides an electronic device, including a memory and a processor, wherein the memory is used to store one or more computer instructions, and one or more of the computer instructions are executed by the processor to implement the method according to any one of the first aspects.

[0021] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium, on which computer instructions are stored, and when the computer instructions are executed by a processor, the method according to any one of the first aspects is implemented.

[0022] According to the technical solution provided by the embodiments of the present disclosure, historical operation data of the operation resources of the power system and its related data can be collected; the historical operation data and related data of the operation resources are stored as knowledge in the knowledge base; the data of the uncertainty influencing factors of the operation resources in the knowledge base are identified; based on the historical operation data in the knowledge base and its corresponding uncertainty influencing factor data, the uncertainty influencing factors of the operation resources are quantitatively calculated to obtain the quantitative result of the uncertainty influencing factors of the operation resources; based on the quantitative result of the uncertainty influencing factors of the operation resources, a configuration strategy for the operation resources is determined. In this way, through the quantitative processing of the uncertain influencing factors, the uncertainty existing in the operation resources is effectively processed, the strategy optimization of these operation resources is realized, and the safety, reliability and economy of the power system are improved.

[0023] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure. Brief Description of the Drawings

[0024] In combination with the drawings, through the following detailed description of non-limiting embodiments, other features, objects and advantages of the present disclosure will become more obvious. The following is the description of the drawings.

[0025] Figure 1 The flowchart showing a novel method for optimizing the configuration of operation resources in a power system provided by the embodiments of the present disclosure.

[0026] Figure 2 The structural block diagram showing a novel device for optimizing the configuration of operation resources in a power system provided by the embodiments of the present disclosure.

[0027] Figure 3 The structural block diagram showing an electronic device according to the embodiments of the present disclosure.

[0028] Figure 4 The structural schematic diagram showing a computer system suitable for implementing the method of the embodiments of the present disclosure. Detailed Embodiments

[0029] Hereinafter, exemplary embodiments of the present disclosure will be described in detail with reference to the drawings, so that those skilled in the art can easily implement them. In addition, for the sake of clarity, parts irrelevant to the description of the exemplary embodiments are omitted in the drawings.

[0030] In the present disclosure, it should be understood that terms such as "including" or "having" are intended to indicate the presence of features, numbers, steps, actions, components, parts, or combinations thereof disclosed in this specification, and are not intended to exclude the possibility of the presence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof.

[0031] It should also be noted that, without conflict, the embodiments in the present disclosure and the features in the embodiments may be combined with each other. The present disclosure will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0032] Figure 1 The flowchart showing a novel power system operation resource optimization configuration method provided by an embodiment of the present disclosure is as follows Figure 1 As shown, the novel power system operation resource optimization configuration method includes the following steps S101 - S105: In step S101, historical operation data and related data of the operation resources of the power system are collected; In step S102, the historical operation data and related data of the operation resources are stored as knowledge in the knowledge base; In step S103, from the related data of the operation resources stored in the knowledge base, the uncertainty influencing factor data of the operation resources are identified; In step S104, based on the historical operation data in the knowledge base and their corresponding uncertainty influencing factor data, the uncertainty influencing factors of the operation resources are quantitatively calculated to obtain the quantitative results of the uncertainty influencing factors of the operation resources; In step S105, based on the quantitative results of the uncertainty influencing factors of the operation resources, a configuration strategy for the operation resources is determined.

[0033] In a possible implementation manner, the novel power system operation resource optimization configuration method can be applied to electronic devices such as computers, servers, computer clusters, etc. that can execute the novel power system operation resource optimization configuration.

[0034] In a possible implementation manner, the operation resources in the power system include at least one of distributed power sources, electric vehicles, energy storage devices, and flexible loads; where: Distributed power sources include wind power generation, photovoltaic power generation, etc. The output (i.e., output power) of wind power generation and photovoltaic power generation in distributed power sources is affected by natural conditions such as light intensity, temperature, and wind speed, and has strong randomness, intermittency, and volatility. The uncertainty of wind power generation and photovoltaic power generation can be divided into two categories: medium - and long - term uncertainty caused by climate system uncertainty and short - term uncertainty caused by meteorological prediction errors.

[0035] The uncertainty of electric vehicles mainly comes from the disordered charging behavior of users. The charging behavior of users for electric vehicles has strong randomness in space and time, and its charging load will change the daily load change trend. The travel habits and charging demands of different users vary greatly, and it is difficult to accurately predict when, where, how long, and at what power they will charge.

[0036] The uncertainty of energy storage devices (mainly batteries) is affected by various factors. For example, the aging degree of the battery and the ambient temperature will affect the charge and discharge state and capacity of the battery. As the battery is used over time, its performance will gradually decline, resulting in changes in the actual amount of electricity that can be stored and released, which in turn affects the allocation of power resources.

[0037] The uncertainty of flexible loads mainly comes from the behavior and demands of users. Users have autonomy and randomness in the use of electrical equipment, and it is difficult to accurately predict when they will adjust the power consumption or change the power consumption time. For example, industrial users may adjust the operating state of equipment according to the production plan, and commercial users will adjust their power consumption demands according to policies, business hours, and passenger flow changes.

[0038] In a possible implementation manner, in order to effectively handle the uncertain influencing factors of these operating resources in the power system, the historical operating data of the operating resources of the power system and their related data can be collected. Among them, the historical operating data of distributed power sources mainly includes historical output data of distributed power sources such as power generation amount and power generation power at historical times, the historical operating data of electric vehicles mainly includes the historical charging time and historical charging amount data of each electric vehicle, the historical operating data of energy storage devices mainly includes the historical charge and discharge state and historical capacity data of energy storage devices, and the historical operating data of flexible loads mainly includes the power change data of flexible loads at historical times, etc. In addition to collecting the above historical operating data, various data related to the historical operating data can also be collected.

[0039] In a possible implementation manner, in order to facilitate subsequent data processing and use, the historical operating data of the operating resources and their corresponding related data can be stored as knowledge in a knowledge base. Here, appropriate knowledge representation methods, such as ontology, semantic network, etc., can be used to represent and store the collected data for subsequent query and use. It should be noted here that before performing knowledge representation, the collected data can be preprocessed, such as data cleaning, data normalization, etc., to improve the quality and usability of the data.

[0040] In a possible implementation, the knowledge in the knowledge base can be analyzed to identify the data of the uncertainty influencing factors of the operating resources in the knowledge base. For example, for distributed power sources, wind power generation is usually affected by wind speed, and the uncertainty influencing factor data corresponding to the wind power generation can be identified as including wind speed data; photovoltaic power generation is usually affected by environmental factors such as light intensity and temperature, and the uncertainty influencing factor data corresponding to the photovoltaic power generation can be identified as including light intensity data, temperature data, etc.; for electric vehicles, the user charging time is affected by work and rest habits, electricity price policies (such as peak-valley electricity prices), etc., which may lead to concentrated charging at night or differences between weekdays and weekends; the battery capacities (20 kWh - 200 kWh) and charging powers (slow charging 3 kW - fast charging 350 kW) of different vehicle models (such as passenger cars, logistics vehicles) vary significantly. At extreme temperatures, the battery efficiency decreases, the charging demand increases (such as heating energy consumption in winter), and the charging power may be limited (such as low-temperature protection); moreover, with the reduction of subsidies, the progress of charging facility construction, changes in carbon emission policies, etc., the user charging mode may be changed; based on the above analysis, the uncertainty influencing factor data corresponding to the electric vehicle can be identified as including data such as user charging habits, electricity price policies, vehicle models, temperature, and relevant policies. For energy storage devices (mainly batteries), as the usage time of the battery increases, its performance will gradually decline, resulting in changes in the actual electricity that can be stored and released. Therefore, the uncertainty influencing factor data corresponding to the energy storage device can be identified as including data such as the operating duration of the energy storage device; for flexible loads, industrial users may adjust the operating status of equipment according to production plans, and commercial users may adjust electricity consumption demands according to policies, business hours, and changes in customer flow, thus causing fluctuations in flexible loads; therefore, the uncertainty influencing factor data corresponding to the flexible load can be identified as including policy data, production plan data of industrial users, changes in business hours and customer flow of commercial users, etc.

[0041] In a possible implementation, based on the historical operating data in the knowledge base and its corresponding uncertainty influencing factor data, a suitable uncertainty analysis method can be adopted to quantitatively analyze the influence of the uncertainty influencing factors of the operating resource on the operating data of the operating resource, perform quantitative calculations on the uncertainty influencing factors of the operating resource, and obtain the quantitative results of the uncertainty influencing factors of the operating resource. The quantitative results can quantitatively describe the influence of the uncertainty influencing factors of the operating resource on the operating data of the operating resource. The uncertainty analysis methods described here can be analysis methods such as probability distribution, fuzzy set, and interval analysis.

[0042] In a possible implementation, based on the quantification result of the uncertainty influencing factors of the operating resources, the influence evaluation result of these uncertainty influencing factors on the uncertainty of the operating resources can be determined, and this influence evaluation result can be the degree of influence. For example, if the operating data of the operating resources fluctuates greatly with the fluctuation of the uncertainty influencing factors, it indicates that this uncertainty influencing factor has a greater influence on the uncertainty of the operating resources; if the operating data of the operating resources fluctuates slightly with the fluctuation of the uncertainty influencing factors, it indicates that this uncertainty influencing factor has a smaller influence on the uncertainty of the operating resources.

[0043] In a possible implementation, for the influence evaluation result of the uncertainty of the operating resources analyzed above, a configuration strategy for the operating resources can be determined. For example, if the influence evaluation result indicates that the distributed power source is greatly affected by the uncertainty influencing factors, the planning and layout strategy of the distributed power source can be deployed more flexibly to avoid being affected by the fluctuation of the uncertainty influencing factors; if the influence evaluation result indicates that the distributed power source is less affected by the uncertainty influencing factors, the planning and layout strategy of the distributed power source can be deployed more stably to ensure the power consumption quality of users. Or, the influence evaluation result can identify the influence of each type of power source and load on the power grid. If the power grid needs a certain type of power source or load to participate in regulation, one or more of them can be preferentially selected according to this influence evaluation result for corresponding incentive strategies. For example, for electric vehicles, the battery can be used as a distributed energy storage unit to discharge to the power grid during peak electricity price periods to flatten the load curve. When the power grid has a demand, the power grid can promote the discharge of electric vehicles to the power grid through a reward mechanism; the charging demand of electric vehicles can match the output period of renewable energy to reduce curtailment of wind and solar power. Therefore, during the peak period of renewable energy generation, electric vehicles can be encouraged to charge more by reducing the charging cost. The determination of the relevant strategies for energy storage devices and flexible loads is similar and will not be described one by one.

[0044] This implementation can collect the historical operating data of the operating resources of the power system and its related data; store the historical operating data and related data of the operating resources as knowledge in the knowledge base; identify the uncertainty influencing factor data of the operating resources in the knowledge base; based on the historical operating data in the knowledge base and its corresponding uncertainty influencing factor data, perform a quantification calculation on the uncertainty influencing factors of the operating resources to obtain the quantification result of the uncertainty influencing factors of the operating resources; based on the quantification result of the uncertainty influencing factors of the operating resources, determine the configuration strategy for the operating resources. In this way, through the quantification process of the uncertain influencing factors, the uncertainty existing in the operating resources is effectively processed, the strategy optimization of these operating resources is realized, and the safety, reliability and economy of the power system are improved.

[0045] In a possible implementation manner, quantifying and calculating the uncertainty influencing factors of the operating resources based on the historical operation data and the corresponding uncertainty influencing factor data in the knowledge base to obtain the quantification result of the uncertainty influencing factors of the operating resources includes: Training a pre-set model according to the historical operation data and the corresponding uncertainty influencing factor data in the knowledge base to obtain a trained model, and using the model parameters of the trained model as the quantification result of the uncertainty influencing factors.

[0046] In this implementation manner, a pre-set model can be applied to analyze the relationship between the uncertainty influencing factor data and the historical operation data. The input of the pre-set model is the uncertainty influencing factor data, and the output is the historical operation data. Based on the historical operation data and the corresponding uncertainty influencing factor data in the knowledge base, the pre-set model can be trained to obtain a trained model, and the model parameters of the trained model are the quantification results of the uncertainty influencing factors.

[0047] In a possible implementation manner, the trained model includes a prediction model. Determining a configuration strategy for the operating resources based on the quantification result of the uncertainty influencing factors of the operating resources includes: Determining a day-ahead regulation strategy for the operating resources based on the predicted operation data of the operating resources in the future time predicted by the prediction model; Correcting the day-ahead regulation strategy based on the real-time operation data of the operating resources in the future time to determine the intra-day regulation strategy of the operating resources.

[0048] In this implementation manner, the day-ahead regulation strategy refers to a pre-determined regulation strategy one day or several days in advance; the intra-day regulation strategy refers to the real-time regulation strategy on the same day. This implementation manner adopts a "day-ahead + intra-day" mode, combining the regulation strategies of advance planning and real-time adjustment.

[0049] In this embodiment, the trained model can be a prediction model for predicting the predicted operation data of operation resources at future times. The model parameters in the prediction model are the quantization results of uncertainty influencing factors determined based on the historical operation data of the operation resources and the corresponding uncertainty influencing factor data. By inputting the uncertainty influencing factor data currently corresponding to the operation device into the prediction model and executing the prediction model, the predicted operation data of the operation resources at future times can be predicted in advance. Based on the predicted operation data of the operation resources at future times predicted in advance, the day-ahead regulation strategy of the corresponding operation resources can be predicted in advance. For example, the prediction model corresponding to the distributed power source can predict the predicted power generation data of the distributed power source at future times, so that power regulation can be carried out in advance based on the predicted power generation data at future times.

[0050] In this embodiment, when the future time arrives, the day-ahead regulation strategy can be corrected based on the real-time operation data of the operation resources at the future time to determine the intra-day regulation strategy of the operation resources.

[0051] In a possible embodiment, the method further includes: Obtaining the resource type of the operation resources, where the resource type includes day-ahead type and intra-day type; After determining the day-ahead regulation strategy of the operation resources, publishing the day-ahead regulation strategy of the operation resources of the day-ahead type.

[0052] In this embodiment, Table 1 below shows the resource types of four operation resources: Operating resources Regulation characteristics Resource type Distributed energy High flexibility, short-term response Day-ahead type + intra-day type Flexible load Interruptible / transferable, medium response speed Day-ahead type, intra-day type Energy storage device Bidirectional power regulation, energy time shift Day-ahead type + intra-day type Electric vehicle Strong randomness, fast response speed Intra-day type Table 1 As shown in Table 1, the distributed energy has high flexibility, strong reliability, and short response time, and can play a greater role in both day-ahead and intra-day regulation. Therefore, the distributed energy can be of two types, day-ahead type and intra-day type. Some of the flexible loads in the flexible load are of the day-ahead type, and some are of the intra-day type; the energy storage device has bidirectional power regulation and energy time shift, and can participate in regulation throughout the day, including the day-ahead type and the intra-day type; the electric vehicle has strong randomness and fast response speed, and can be of the intra-day type.

[0053] In this embodiment, the day-ahead stage is a control strategy determined based on predicted operation data to achieve the control objective. Considering that the day-ahead stage only controls day-ahead operation resources, there may be a situation where the day-ahead operation resources are controlled to a relatively deep degree, resulting in unnecessary resource waste and more control costs, and the result will no longer be globally optimal. Therefore, in this embodiment, the predicted operation data of day-ahead and intra-day operation resources can be obtained in the day-ahead stage, and the day-ahead and intra-day operation resources are made to jointly participate in the determination of the control strategy in the day-ahead stage, so as to obtain the day-ahead control strategy for the day-ahead and intra-day operation resources. When actually notifying the user of the day-ahead control strategy, only the day-ahead control strategy of the day-ahead operation resources may be published, and the day-ahead control strategy of the intra-day operation resources is not published.

[0054] In this embodiment, the intra-day stage is to further optimize the day-ahead control strategy. Considering that there is a deviation between the predicted operation data and the real-time operation data in the future time, and there is a large uncertainty in the actual response degree of the day-ahead operation resources, there is a difference between the intra-day measured value and the day-ahead control result value, and it is necessary to correct the intra-day control strategy to meet the control conditions. It should be noted here that in the intra-day control stage, on the basis of the day-ahead control strategy, it can be further corrected and optimized to obtain the intra-day control strategy. After determining the intra-day control strategy for the day-ahead and intra-day operation resources, the intra-day control strategy for the day-ahead and intra-day operation resources can be published.

[0055] In a possible embodiment, determining the day-ahead control strategy for the operation resources based on the predicted operation data of the operation resources predicted by the prediction model in the future time includes: The cloud master station determines the day-ahead control strategy for the operation resources based on the predicted operation data of the operation resources predicted by the prediction model in the future time; Correcting the day-ahead control strategy based on the real-time operation data of the operation resources in the future time to determine the intra-day control strategy for the operation resources includes: The edge device corrects the day-ahead control strategy based on the real-time operation data of the operation resources in the future time to determine the intra-day control strategy for the operation resources.

[0056] In this embodiment, in the day-ahead stage, the edge-side device can perform data collection, aggregation and upload to the substation area, and the cloud master station executes the above configuration optimization method; in the intra-day stage, in order to adapt to the randomness of the intra-day controllable load and the low latency of the control, after data collection on the edge side, the edge device can directly execute the above configuration optimization method.

[0057] In a possible embodiment, the method further includes: The cloud master station performs cross-substation area regulation based on the current regulation strategies of each substation area.

[0058] In this embodiment, in some special scenarios, such as an emergency energy shortage, a regulation request can be sent to the cloud master station, which can perform cross-substation area regulation based on the current regulation strategies of each substation area. For example, if there is an emergency power shortage in Substation Area A, the cloud master station can, based on the current regulation strategies of each substation area, find that there is excess power in Substation Area B that can be regulated over, and then regulate the power of Substation Area B to Substation Area A to achieve cross-substation area resource regulation.

[0059] In a possible embodiment, determining the day-ahead regulation strategy for the operating resources based on the predicted operating data of the operating resources at a future time predicted by the prediction model includes: Determining the regulation cost of the operating resources based on the predicted operating data of the operating resources at a future time predicted by the prediction model; Based on the regulation cost of the operating resources, constructing the following objective function: ; ; Wherein, refers to the regulation cost of flexible loads, refers to the regulation cost of distributed energy, refers to the regulation cost of energy storage devices, refers to the regulation cost of electric vehicles, is the minimum total regulation cost of the operating resources within the time period , refers to the power demanded by the flexible load at the moment, refers to the power demanded by the distributed energy at the moment, refers to the power demanded by the energy storage device at the moment, refers to the power demanded by the electric vehicle at the moment, is the load shedding penalty, is the grid operation cost; the constraint conditions corresponding to the objective function include the upper limit of the reduction of the day-ahead load in the flexible load, the upper and lower limits of the output of the distributed energy, and the dynamic balance of the state of charge (SOC) of the energy storage device; Solving the minimum value of the objective function to obtain the day-ahead regulation strategy of the operating resources.

[0060] In this embodiment, the regulation cost of the operating resources can be determined based on the predicted operating data of the operating resources predicted by the prediction model at a future time. For example, the greater the predicted power generation of distributed energy at a future time, the lower the regulation cost, and so on.

[0061] In this embodiment, the grid energy regulation costs of distributed power sources, electric vehicles, energy storage devices, and flexible loads can be considered to construct a model that minimizes the regulation cost to minimize the global total operating cost. Taking this as the objective function, solve this objective function. Then the corresponding future time 、 、 、 can be obtained; afterwards, perform the day-ahead regulation strategies for each operating resource according to the calculated future time 、 、 、 . The power corresponding to the above 、 、 、 demands includes the power that needs to be output or the power that needs to be input. It should be noted here that when solving the objective function , some constraint conditions need to be followed; among them, in order to ensure user power consumption and avoid excessive load reduction, the reduction upper limit of the day-ahead load in the flexible load can be set. When solving the objective function , it is necessary to ensure that the reduction of the day-ahead load during the regulation of the flexible load does not exceed this reduction upper limit; the output of distributed energy is affected by the physical environment and power generation components and has certain upper and lower limits, and the upper and lower limits of the output of distributed energy can be set. When solving the objective function , the regulation of distributed energy needs to follow that the output of distributed energy does not exceed this output upper and lower limits; in order to improve the overall performance, safety, and lifespan of the energy storage device, it is necessary to ensure that the power demanded by the energy storage device at time enables the dynamic balance of the SOC (State of Charge) of the energy storage device; therefore, when solving the objective function , set the dynamic balance of the state of charge SOC of the energy storage device as a constraint condition.

[0062] Of course, the real-time regulation cost of the operating resources can be determined based on the real-time operating data of the operating resources, and then the above objective function can be used to calculate the intra-day regulation strategies of each operating resource; here, on the basis of calculating the day-ahead regulation strategy, adjust time , , , , thereby obtaining the adjusted at the moment of , , , as the intraday regulation strategy for each operating resource; adjusting based on the day-ahead regulation strategy can quickly obtain the adjusted intraday regulation strategy.

[0063] The present disclosure also provides a novel power system operating resource optimization configuration device. Figure 2 shows a structural block diagram of a novel power system operating resource optimization configuration device provided by an embodiment of the present disclosure. This device can be implemented as part or all of an electronic device through software, hardware, or a combination of both. As Figure 2 shown, the configuration optimization device includes: A data acquisition module 201, configured to acquire historical operation data and related data of the operating resources of the power system; A storage module 202, configured to store the historical operation data and related data of the operating resources as knowledge in a knowledge base; An identification module 203, configured to identify the uncertainty influencing factor data of the operating resources in the knowledge base; A quantification module 204, configured to perform a quantification calculation on the uncertainty influencing factors of the operating resources based on the historical operation data in the knowledge base and its corresponding uncertainty influencing factor data, and obtain a quantification result of the uncertainty influencing factors of the operating resources; A configuration module 205, configured to determine a configuration strategy for the operating resources based on the quantification result of the uncertainty influencing factors of the operating resources.

[0064] In a possible implementation manner, this novel power system operating resource optimization configuration device can be applied to electronic devices such as computers, servers, and computer clusters that can perform the optimization configuration of novel power system operating resources.

[0065] In a possible implementation manner, the operating resources include at least one of distributed power sources, electric vehicles, energy storage devices, and flexible loads; where: Distributed power sources include wind power generation, photovoltaic power generation, etc. The power output of wind power generation and photovoltaic power generation in distributed power sources is affected by natural conditions such as light intensity, temperature, and wind speed, and has strong randomness, intermittency, and volatility. The uncertainties of wind power generation and photovoltaic power generation can be divided into two categories: medium- and long-term uncertainties caused by the uncertainty of the climate system and short-term uncertainties caused by meteorological prediction errors.

[0066] The uncertainties of electric vehicles mainly come from the disordered charging behaviors of users. The charging behaviors of users are highly random in terms of time and space, and their charging loads will change the daily load variation trend. There are significant differences in the travel habits and charging demands of different users, making it difficult to accurately predict when, where they will charge, as well as the charging duration and charging power.

[0067] The uncertainties of energy storage devices (mainly batteries) are affected by various factors. For example, the degree of battery aging, environmental temperature, etc. will affect the charge and discharge state and capacity of the battery. As the battery is used over time, its performance will gradually decline, resulting in changes in the actual amount of electricity that can be stored and released, thereby affecting the allocation of power resources.

[0068] The uncertainties of flexible loads mainly come from the behaviors and demands of users. Users have autonomy and randomness in the use of electrical equipment, making it difficult to accurately predict when they will adjust the electrical power or change the electricity usage time. For example, industrial users may adjust the operating status of equipment according to production plans, and commercial users will adjust their electricity demands according to policies, business hours, and changes in customer flow.

[0069] In a possible implementation manner, in order to effectively handle the uncertain influencing factors of these operating resources in the power system, the historical operating data of the operating resources of the power system and their related data can be collected. Among them, the historical operating data of distributed power sources mainly includes historical output data of distributed power sources such as power generation and power generation power at historical times, the historical operating data of electric vehicles mainly includes the historical charging time and historical charging amount data of each electric vehicle, the historical operating data of energy storage devices mainly includes the historical charge and discharge state and historical capacity data of energy storage devices, and the historical operating data of flexible loads mainly includes the power change data of flexible loads at historical times, etc. In addition to collecting the above historical operating data, various data related to this historical operating data can also be collected.

[0070] In a possible implementation manner, for the convenience of subsequent data processing and use, the historical operating data of the operating resources and their corresponding related data can be stored as knowledge in a knowledge base. Here, appropriate knowledge representation methods, such as ontology, semantic network, etc., can be used to represent and store the collected data for subsequent query and use. It should be noted here that before knowledge representation, the collected data can be preprocessed, such as data cleaning, data normalization, etc., to improve the quality and usability of the data.

[0071] In a possible implementation, the knowledge in the knowledge base can be analyzed to identify the data of the uncertainty influencing factors of the operating resources in the knowledge base. For example, for distributed power sources, wind power generation is usually affected by wind speed, and the uncertainty influencing factor data corresponding to the wind power generation can be identified as including wind speed data; photovoltaic power generation is usually affected by environmental factors such as light intensity and temperature, and the uncertainty influencing factor data corresponding to the photovoltaic power generation can be identified as including light intensity data, temperature data, etc.; for electric vehicles, the user charging time is affected by work and rest habits, electricity price policies (such as peak-valley electricity prices), etc., which may lead to concentrated charging at night or differences between weekdays and weekends; the battery capacities (20 kWh - 200 kWh) and charging powers (slow charging 3 kW - fast charging 350 kW) of different vehicle types (such as passenger cars, logistics vehicles) vary significantly. At extreme temperatures, the battery efficiency decreases, the charging demand increases (such as heating energy consumption in winter), and the charging power may be limited (such as low-temperature protection); moreover, with the withdrawal of subsidies, the progress of charging facility construction, changes in carbon emission policies, etc., the user charging mode may be changed; based on the above analysis, the uncertainty influencing factor data corresponding to the electric vehicle can be identified as including data such as user charging habits, electricity price policies, vehicle types, temperature, relevant policies, etc. For energy storage devices (mainly batteries), as the usage time of the battery increases, its performance will gradually decline, resulting in changes in the actual electricity that can be stored and released. Therefore, the uncertainty influencing factor data corresponding to the energy storage device can be identified as including data such as the operating duration of the energy storage device; for flexible loads, industrial users may adjust the operating status of equipment according to production plans, and commercial users may adjust electricity consumption demands according to policies, business hours, and changes in customer flow, thus causing fluctuations in flexible loads; therefore, the uncertainty influencing factor data corresponding to the flexible load can be identified as including policy data, production plan data of industrial users, changes in business hours and customer flow of commercial users, etc.

[0072] In a possible implementation, based on the historical operating data in the knowledge base and its corresponding uncertainty influencing factor data, a suitable uncertainty analysis method can be adopted to quantitatively analyze the impact of the uncertainty influencing factors of the operating resource on the operating data of the operating resource, perform quantitative calculation on the uncertainty influencing factors of the operating resource, and obtain the quantitative result of the uncertainty influencing factors of the operating resource. This quantitative result can quantitatively describe the impact of the uncertainty influencing factors of the operating resource on the operating data of the operating resource. The uncertainty analysis method described here can be analysis methods such as probability distribution, fuzzy set, interval analysis, etc.

[0073] In a possible implementation manner, based on the quantification result of the uncertainty influencing factors of the operating resources, the influence evaluation result of these uncertainty influencing factors on the uncertainty of the operating resources can be determined, and this influence evaluation result can be the degree of influence. For example, if the operating data of the operating resources fluctuates greatly with the fluctuation of the uncertainty influencing factors, it indicates that the uncertainty influencing factor has a greater influence on the uncertainty of the operating resources; if the operating data of the operating resources fluctuates slightly with the fluctuation of the uncertainty influencing factors, it indicates that the uncertainty influencing factor has a smaller influence on the uncertainty of the operating resources.

[0074] In a possible implementation manner, for the influence evaluation result of the uncertainty of the operating resources analyzed above, a configuration strategy for the operating resources can be determined. For example, if the influence evaluation result indicates that the distributed power source is greatly affected by the uncertainty influencing factors, the planning and layout strategy of the distributed power source can be deployed more flexibly to avoid being affected by the fluctuation of the uncertainty influencing factors; if the influence evaluation result indicates that the distributed power source is less affected by the uncertainty influencing factors, the planning and layout strategy of the distributed power source can be deployed more stably to ensure the power consumption quality of users.

[0075] This implementation manner can collect the historical operating data of the operating resources of the power system and its related data; store the historical operating data and related data of the operating resources as knowledge in the knowledge base; identify the uncertainty influencing factor data of the operating resources in the knowledge base; based on the historical operating data in the knowledge base and its corresponding uncertainty influencing factor data, perform quantitative calculation on the uncertainty influencing factors of the operating resources to obtain the quantification result of the uncertainty influencing factors of the operating resources; based on the quantification result of the uncertainty influencing factors of the operating resources, determine the configuration strategy for the operating resources. In this way, through the quantitative processing of the uncertain influencing factors, the uncertainty existing in the operating resources is effectively processed, the strategy optimization of these operating resources is realized, and the safety, reliability and economy of the power system are improved.

[0076] In a possible implementation manner, the quantification module is configured to: Train a pre-set model according to the historical operating data in the knowledge base and its corresponding uncertainty influencing factor data to obtain a trained model, and the model parameters of the trained model are the quantification results of the uncertainty influencing factors.

[0077] In this embodiment, a pre-set model can be applied to analyze the relationship between the uncertainty influencing factor data and the historical operation data. The input of the pre-set model is the uncertainty influencing factor data, and the output is the historical operation data. Based on the historical operation data in the knowledge base and its corresponding uncertainty influencing factor data, the pre-set model is trained to obtain a trained model, and the model parameters of the trained model are the quantization results of the uncertainty influencing factors.

[0078] In a possible embodiment, the trained model includes a prediction model, and the configuration module is configured to: Determine the day-ahead regulation strategy of the operating resource based on the predicted operation data of the operating resource at a future time predicted by the prediction model; Based on the real-time operation data of the operating resource at a future time, correct the day-ahead regulation strategy to determine the intra-day regulation strategy of the operating resource.

[0079] In this embodiment, the day-ahead regulation strategy refers to a pre-determined regulation strategy one or several days in advance; the intra-day regulation strategy refers to the real-time regulation strategy on the same day. This embodiment adopts the "day-ahead + intra-day" mode, combining the regulation strategies of advance planning and real-time adjustment.

[0080] In this embodiment, the trained model can be a prediction model for predicting the predicted operation data of the operating resource at a future time. The model parameters in the prediction model are the quantization results of the uncertainty influencing factors determined based on the historical operation data of the operating resource and its corresponding uncertainty influencing factor data. By inputting the current corresponding uncertainty influencing factor data of the operating device into the prediction model and executing the prediction model, the predicted operation data of the operating resource at a future time can be predicted in advance. Based on the predicted operation data of the operating resource at a future time predicted in advance, the day-ahead regulation strategy of the corresponding operating resource can be predicted in advance. For example, the prediction model corresponding to the distributed power source can predict the predicted power generation data of the distributed power source at a future time, so that power regulation can be carried out in advance based on the predicted power generation data at a future time.

[0081] In this embodiment, when reaching the future time, the day-ahead regulation strategy can be corrected based on the real-time operation data of the operating resource at the future time to determine the intra-day regulation strategy of the operating resource.

[0082] In a possible embodiment, the device further includes: A type acquisition module configured to acquire the resource type of the operating resource, where the resource type includes day-ahead type and intra-day type; The strategy publishing module is configured to publish the day-ahead regulation strategy of the day-ahead type of operating resources after determining the day-ahead regulation strategy of the day-ahead type and intra-day type of operating resources.

[0083] In this embodiment, as shown in Table 1 above, there are four resource types of operating resources. As shown in Table 1, distributed energy has high flexibility, strong reliability, and short response time, and can play a greater role in both day-ahead and intra-day regulation. Therefore, the distributed energy can be of two types: day-ahead type and intra-day type. Some of the flexible loads in the flexible load are of the day-ahead type, and some are of the intra-day type; the energy storage device has bidirectional power regulation and energy time shift, and can participate in regulation throughout the whole period, including the day-ahead type and intra-day type; electric vehicles have strong randomness and fast response speed, and can be of the intra-day type.

[0084] In this embodiment, the day-ahead stage is a regulation strategy determined based on predicted operation data to achieve the regulation target. Considering that the day-ahead stage only regulates the day-ahead type of operating resources, there may be a situation where the regulation degree of the day-ahead type of operating resources is relatively deep, resulting in unnecessary resource waste and more regulation costs, and the result will no longer be globally optimal. Therefore, in this embodiment, the predicted operation data of the day-ahead type and intra-day type of operating resources can be obtained in the day-ahead stage, and the day-ahead type and intra-day type of operating resources are allowed to jointly participate in the determination of the day-ahead regulation strategy to obtain the day-ahead regulation strategy of the day-ahead type and intra-day type of operating resources. When actually notifying the user of the day-ahead regulation strategy, only the day-ahead regulation strategy of the day-ahead type of operating resources can be published, and the day-ahead regulation strategy of the intra-day type of operating resources is not published.

[0085] In this embodiment, the intra-day stage is to further optimize the day-ahead regulation strategy. Considering that there is a deviation between the predicted operation data in the future time and the real-time operation data, and the actual response degree of the day-ahead type of operating resources has great uncertainty, there is a difference between the intra-day measured value and the day-ahead regulation result value, and it is necessary to correct the intra-day regulation strategy to meet the regulation conditions. It should be noted here that in the intra-day regulation stage, the day-ahead regulation strategy can be further corrected and optimized on the basis of the day-ahead regulation strategy to obtain the intra-day regulation strategy. After determining the intra-day regulation strategy of the day-ahead type and intra-day type of operating resources, the intra-day regulation strategy of the day-ahead type and intra-day type of operating resources can be published.

[0086] In a possible embodiment, the part of the configuration module that determines the day-ahead regulation strategy of the operating resources based on the predicted operation data of the operating resources predicted by the prediction model is configured to: The cloud master station determines the day-ahead regulation strategy of the operating resources based on the predicted operation data of the operating resources predicted by the prediction model; The part in the configuration module that modifies the day-ahead regulation strategy based on the real-time operation data of the operation resources in the future time and determines the intra-day regulation strategy of the operation resources is configured as: The edge device modifies the day-ahead regulation strategy based on the real-time operation data of the operation resources in the future time and determines the intra-day regulation strategy of the operation resources.

[0087] In this embodiment, in the day-ahead stage, data collection, aggregation and uploading to the substation area can be performed by the edge-side device, and the cloud master station executes the above configuration optimization method; in the intra-day stage, in order to adapt to the randomness of intra-day controllable load and the low latency of regulation, after data collection on the edge side, the above configuration optimization method can be directly executed by the edge device.

[0088] In a possible embodiment, the device further includes: A regulation module configured to perform cross-substation area regulation by the cloud master station based on the current regulation strategies of each substation area.

[0089] In this embodiment, in some special scenarios, such as an emergency lack of energy, the regulation request can be sent to the cloud master station, and the cloud master station can perform cross-substation area regulation based on the current regulation strategies of each substation area; for example, if there is an emergency lack of power in Substation Area A, the cloud master station can, based on the current regulation strategies of each substation area, find that there is surplus power in Substation Area B that can be regulated over, and then the power of Substation Area B can be regulated to Substation Area A to achieve cross-substation area resource regulation.

[0090] The part in the configuration module that determines the day-ahead regulation strategy of the operation resources based on the predicted operation data of the operation resources in the future time predicted by the prediction model is configured as: Based on the predicted operation data of the operation resources in the future time predicted by the prediction model, determine the regulation cost of the operation resources; Based on the regulation cost of the operation resources, construct the following objective function: ; ; Wherein, refers to the regulation cost of flexible load, refers to the regulation cost of distributed energy, refers to the regulation cost of energy storage devices, refers to the regulation cost of electric vehicles, is the minimum total regulation cost of the operation resources in time period , refers to the power demanded by the flexible load at moment, refers to the distributed energy at The power demanded at a certain moment refers to the power demanded by the energy storage device at a certain moment and refers to the power demanded by the electric vehicle at a certain moment is the load shedding penalty and is the grid operation cost; the constraint conditions corresponding to the objective function include the upper limit of the reduction of the day-ahead load in the flexible load, the upper and lower limits of the output of the distributed energy, and the dynamic balance of the state of charge SOC of the energy storage device Solve the minimum value of the objective function to obtain the day-ahead regulation strategy of the operating resources

[0091] In this embodiment, based on the predicted operation data of the operating resources in the future time predicted by the prediction model, the regulation cost of the operating resources can be determined. For example, the larger the predicted power generation of the distributed energy in the future time, the lower the regulation cost, and so on

[0092] In this embodiment, the grid energy regulation costs of distributed power sources, electric vehicles, energy storage devices, and flexible loads can be considered to construct a model for minimizing the regulation cost to minimize the global total operation cost Take it as the objective function and solve this objective function to obtain the corresponding future when the total operation cost of the entire grid is the lowest at a certain moment , , , ; then perform the day-ahead regulation strategy of each operating resource according to the calculated future at a certain moment , , , . The power demanded corresponding to the above , , , includes the power that needs to be output or the power that needs to be input. It should be noted here that when solving the objective function , some constraint conditions need to be followed; among them, in order to ensure user power consumption and avoid too much load reduction, the upper limit of the reduction of the day-ahead load in the flexible load can be set. When solving the objective function , it is necessary to ensure that the reduction of the day-ahead load does not exceed this reduction upper limit during the regulation process of the flexible load; the output of the distributed energy is limited by the physical environment and the power generation components, and the upper and lower limits of the output of the distributed energy can be set. When solving the objective function When regulating distributed energy, it is necessary to ensure that the output of distributed energy does not exceed its upper and lower limits; to improve the overall performance, safety, and lifespan of energy storage devices, it is necessary to ensure that the power demanded at a certain moment keeps the State of Charge (SOC) of the energy storage device in dynamic balance; therefore, when solving the objective function the dynamic balance of the State of Charge (SOC) of the energy storage device is set as a constraint condition. When calculating the objective function

[0093] Of course, based on the real-time operation data of the operation resources, the real-time regulation cost of the operation resources can be determined, and then the above-mentioned objective function can be used to calculate the intra-day regulation strategies of each operation resource; here, based on the calculation of the day-ahead regulation strategy, the at a certain moment , , , can be adjusted, and then the at the adjusted moment , , , are used as the intra-day regulation strategies of each operation resource; adjusting based on the day-ahead regulation strategy can quickly obtain the adjusted intra-day regulation strategy.

[0094] The technical terms and technical features mentioned in the embodiments of the present device are the same as or similar to those mentioned in the above method embodiments. For the explanations and descriptions of the technical terms and technical features involved in the present device, reference can be made to the explanations and descriptions of the above method embodiments, which will not be elaborated here.

[0095] The present disclosure also discloses an electronic device, Figure 3 showing a structural block diagram of the electronic device according to an embodiment of the present disclosure.

[0096] As shown in Figure 3 , the electronic device 300 includes a memory 301 and a processor 302. Among them, the memory 301 is used to store one or more computer instructions, and the one or more computer instructions are executed by the processor 302 to implement the method according to the embodiment of the present disclosure.

[0097] Figure 4 showing a structural schematic diagram of a computer system suitable for implementing the method of the embodiment of the present disclosure.

[0098] As shown in Figure 4As shown, the computer system 400 includes a processing unit 401, which can perform various processes in the above embodiments according to a program stored in a read-only memory (ROM) 402 or a program loaded from a storage section 408 into a random access memory (RAM) 403. In the RAM 403, various programs and data required for the operation of the computer system 400 are also stored. The processing unit 401, the ROM 402, and the RAM 403 are connected to each other via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0099] The following components are connected to the I / O interface 405: an input section 406 including a keyboard, a mouse, etc.; an output section 407 including, for example, a cathode ray tube (CRT), a liquid crystal display (LCD), etc. and a speaker, etc.; a storage section 408 including a hard disk, etc.; and a communication section 409 including a network interface card such as a LAN card, a modem, etc. The communication section 409 performs communication processing via a network such as the Internet. A drive 410 is also connected to the I / O interface 405 as needed. A removable medium 411, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 410 as needed so that a computer program read from it can be installed into the storage section 408 as needed. Among them, the processing unit 401 can be implemented as a processing unit such as a CPU, a GPU, a TPU, an FPGA, an NPU, etc.

[0100] In particular, according to an embodiment of the present disclosure, the method described above can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes computer instructions that, when executed by a processor, implement the method steps described above. In such an embodiment, the computer program product can be downloaded and installed from a network via the communication section 409, and / or installed from the removable medium 411.

[0101] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a part of code, which contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than that marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, as well as combinations of blocks in the block diagram and / or flowchart, may be implemented by a dedicated hardware-based system that performs the specified functions or operations, or may be implemented by a combination of dedicated hardware and computer instructions.

[0102] The units or modules described in the embodiments of the present disclosure can be implemented in software or in programmable hardware. The described units or modules can also be provided in a processor, and the names of these units or modules do not, in some cases, constitute a limitation on the units or modules themselves.

[0103] As another aspect, the present disclosure also provides a computer-readable storage medium, which can be the computer-readable storage medium included in the electronic device or computer system in the above embodiments; or can exist separately and be unassembled into the device. The computer-readable storage medium stores one or more programs, and the programs are used by one or more processors to execute the methods described in the present disclosure.

[0104] The above description is only the preferred embodiments of the present disclosure and the explanation of the applied technical principles. Those skilled in the art should understand that the scope of the invention involved in the present disclosure is not limited to the technical solutions formed by the specific combination of the above technical features, and should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the inventive concept. For example, the technical solutions formed by mutually replacing the above features with the (but not limited to) technical features having similar functions disclosed in the present disclosure.

Claims

1. A novel method for optimizing the allocation of operating resources in a power system, characterized in that, Including: Collecting historical operation data and related data of the operation resources of the power system; Storing the historical operation data and related data of the operation resources as knowledge in a knowledge base; Identifying the uncertainty influencing factor data of the operation resources from the related data of the operation resources stored in the knowledge base; Quantitatively calculating the uncertainty influencing factors of the operation resources based on the historical operation data in the knowledge base and their corresponding uncertainty influencing factor data, to obtain the quantitative results of the uncertainty influencing factors of the operation resources; Determining a configuration strategy for the operation resources based on the quantitative results of the uncertainty influencing factors of the operation resources.

2. The method according to claim 1, wherein The operation resources include at least one of distributed power sources, electric vehicles, energy storage devices, and flexible loads.

3. The method according to claim 1, characterized in that, The quantitatively calculating the uncertainty influencing factors of the operation resources based on the historical operation data in the knowledge base and their corresponding uncertainty influencing factor data, to obtain the quantitative results of the uncertainty influencing factors of the operation resources, includes: Training a pre-set model according to the historical operation data in the knowledge base and their corresponding uncertainty influencing factor data, to obtain a trained model, and using the model parameters of the trained model as the quantitative results of the uncertainty influencing factors.

4. The method according to claim 3, wherein The trained model includes a prediction model, and the determining a configuration strategy for the operation resources based on the quantitative results of the uncertainty influencing factors of the operation resources, includes: Determining a day-ahead regulation strategy for the operation resources based on the predicted operation data of the operation resources in the future predicted by the prediction model; Correcting the day-ahead regulation strategy based on the real-time operation data of the operation resources in the future, to determine an intra-day regulation strategy for the operation resources.

5. The method according to claim 4, wherein The method further includes: Obtaining the resource type of the operation resources, where the resource type includes day-ahead type and intra-day type; After determining the day-ahead regulation strategies for the day-ahead type and intra-day type operation resources, publishing the day-ahead regulation strategy for the day-ahead type operation resources.

6. The method according to claim 4, wherein The determining a day-ahead regulation strategy for the operation resources based on the predicted operation data of the operation resources in the future predicted by the prediction model, includes: The cloud master station determines the day-ahead regulation strategy for the operation resources based on the predicted operation data of the operation resources in the future predicted by the prediction model; The correcting the day-ahead regulation strategy based on the real-time operation data of the operation resources in the future, to determine an intra-day regulation strategy for the operation resources, includes: The edge device corrects the day-ahead regulation strategy based on the real-time operation data of the operation resources in the future, to determine an intra-day regulation strategy for the operation resources.

7. The method according to claim 4, wherein The method further includes: The cloud master station performs cross-substation regulation based on the current regulation strategies of each substation area.

8. The method according to claim 4, characterized in that, The determining a day-ahead regulation strategy for the operation resources based on the predicted operation data of the operation resources in the future predicted by the prediction model, includes: Determining the regulation cost of the operation resources based on the predicted operation data of the operation resources in the future predicted by the prediction model; Construct the following objective function based on the regulation cost of the operating resources: ； ； Among them, refers to the regulation cost of flexible loads, refers to the regulation cost of distributed energy, refers to the regulation cost of energy storage devices, refers to the regulation cost of electric vehicles, is the minimum total regulation cost of operating resources within the time period ; refers to the power demanded by the flexible load at the moment ; refers to the power demanded by the distributed energy at the moment ; refers to the power demanded by the energy storage device at the moment ; refers to the power demanded by the electric vehicle at the moment ; is the load shedding penalty, is the grid operation cost; the constraint conditions corresponding to the objective function include the upper limit of the reduction of the day-ahead load in the flexible load, the upper and lower limits of the output of the distributed energy, and the dynamic balance of the state of charge (SOC) of the energy storage device; Solve the minimum value of the objective function to obtain the day-ahead regulation strategy of the operating resources.

9. A novel device for optimizing the allocation of operating resources in a power system, characterized in that, Including: A data acquisition module configured to acquire historical operation data and related data of the operating resources of the power system; A storage module configured to store the historical operation data and related data of the operating resources as knowledge in a knowledge base; An identification module configured to identify the data of the uncertainty influencing factors of the operating resources in the knowledge base; A quantification module configured to perform quantification calculation on the uncertainty influencing factors of the operating resources based on the historical operation data in the knowledge base and their corresponding uncertainty influencing factor data, and obtain the quantification result of the uncertainty influencing factors of the operating resources; A configuration module configured to determine a configuration strategy for the operating resources based on the quantification result of the uncertainty influencing factors of the operating resources.

10. The device according to claim 9, characterized in that The operating resources include at least one of distributed power sources, electric vehicles, energy storage devices, and flexible loads.

11. The device according to claim 9, characterized in that, The quantification module is configured to: Train a pre-set model according to the historical operation data in the knowledge base and their corresponding uncertainty influencing factor data to obtain a trained model, and the model parameters of the trained model are the quantification results of the uncertainty influencing factors.

12. The device according to claim 11, wherein The trained model includes a prediction model, and the configuration module is configured to: Determine the day-ahead regulation strategy of the operating resources based on the predicted operation data of the operating resources in the future predicted by the prediction model; Correct the day-ahead regulation strategy based on the real-time operation data of the operating resources in the future to determine the intra-day regulation strategy of the operating resources.

13. The device according to claim 12, characterized in that, The device further includes: A type acquisition module configured to acquire the resource type of the operating resources, and the resource type includes day-ahead type and intra-day type; A strategy publishing module configured to publish the day-ahead regulation strategy of the day-ahead type operating resources after determining the day-ahead regulation strategies of the day-ahead type and intra-day type operating resources.

14. The device according to claim 12, characterized in that, The part in the configuration module that determines the day-ahead regulation strategy of the operating resources based on the predicted operation data of the operating resources in the future predicted by the prediction model is configured to: The cloud master station determines the day-ahead regulation strategy of the operating resources based on the predicted operation data of the operating resources in the future predicted by the prediction model; The part in the configuration module that corrects the day-ahead regulation strategy based on the real-time operation data of the operating resources in the future to determine the intra-day regulation strategy of the operating resources is configured to: The edge device corrects the day-ahead regulation strategy based on the real-time operation data of the operating resources in the future to determine the intra-day regulation strategy of the operating resources.

15. The device according to claim 12, characterized in that, The device further includes: A regulation module configured to perform cross-substation regulation by the cloud master station based on the current regulation strategies of each substation area.

16. The device according to claim 12, characterized in that, The part in the configuration module that determines the day-ahead regulation strategy of the operating resources based on the predicted operation data of the operating resources in the future predicted by the prediction model is configured to: Determine the regulation cost of the operating resource based on the predicted operation data of the operating resource at a future time predicted by the prediction model; Construct the following objective function based on the regulation cost of the operating resource; ； ； Among them, refers to the regulation cost of flexible loads, refers to the regulation cost of distributed energy, refers to the regulation cost of energy storage devices, refers to the regulation cost of electric vehicles, is the minimum total regulation cost of operation resources during time period ; refers to the power demanded by the flexible load at time; refers to the power demanded by the distributed energy at time; refers to the power demanded by the energy storage device at time; refers to the power demanded by the electric vehicle at time; is the load shedding penalty, is the power grid operation cost; the constraint conditions corresponding to the objective function include the upper limit of the reduction of the day-ahead load in the flexible load, the upper and lower limits of the output of the distributed energy, and the dynamic balance of the state of charge (SOC) of the energy storage device; Solve the minimum value of the objective function to obtain the day-ahead regulation strategy of the operating resource.

17. An electronic device, characterized in that, It includes a memory and a processor, and the memory is used to store one or more computer instructions, wherein the one or more computer instructions are executed by the processor to implement the method according to any one of claims 1 to 8.

18. A readable storage medium, characterized in that, Computer instructions are stored thereon, and when the computer instructions are executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images