Optimized scheduling method based on multi-element resource aggregate and related device

Abstract

The invention provides an optimal scheduling method based on a multivariate resource aggregate and a related device. The method comprises the following steps: acquiring m sub-models; acquiring historical electricity price data and predicting the electricity price in an intraday stage to obtain a reference predicted electricity price; determining a reference day-ahead market bidding model according to the m sub-models and the reference predicted electricity price; performing electricity price uncertainty and source load uncertainty processing on the reference day-ahead market bidding model to obtain a second target function and a second constraint condition, and determining a target day-ahead market bidding model and a day-ahead clearing result; calculating a day-ahead clearing result to obtain an intra-day deviation punishment cost; determining an intra-day real-time scheduling model based on the intra-day deviation penalty cost; and adjusting the day-ahead clearing result according to the intra-day real-time scheduling model to obtain an intra-day scheduling result. The accuracy and the real-time performance of resource scheduling are improved by processing and optimizing the uncertainty of the electricity price and the uncertainty of the source load in real time.

Description

Technical Field

[0001] The present application relates to the technical field of resource scheduling, and in particular to an optimization scheduling method based on a multi-resource aggregate and related devices. Background Art

[0002] At present, most existing models use deterministic models, assuming that the output of new energy, load demand and market are known and fixed values, ignoring the impact of uncertainty on system operation, and failing to effectively deal with the frequent uncertainty fluctuations in the market, which leads to deviations in scheduling results. At the same time, most existing scheduling models only focus on the optimization of a single stage, usually only scheduling in the day-ahead stage, while ignoring the real-time adjustment in the intraday stage, and failing to fully consider the overall operation strategy of multiple resource aggregates participating in the market environment.

[0003] Therefore, how to improve the accuracy and real-time performance of resource scheduling needs to be solved urgently. Summary of the invention

[0004] The embodiment of the present application provides an optimization scheduling method and related devices based on a multi-resource aggregate, which facilitates improving the accuracy of the day-ahead clearing results by processing the uncertainty of electricity prices and source-load uncertainties, and optimizes them in real time through an intraday deviation penalty cost mechanism, thereby improving the accuracy and real-time performance of resource scheduling.

[0005] In a first aspect, an embodiment of the present application provides an optimization scheduling method based on a multi-resource aggregate, the method comprising: Obtain m sub-models, wherein the m sub-models are obtained by training m MRA models with m resource data in the day-ahead stage; each resource data corresponds to a resource; and m is an integer greater than 1; Obtaining historical electricity price data within a preset time period, and predicting the electricity price of the intraday stage based on the historical electricity price data to obtain a reference predicted electricity price; the end time of the preset time period is earlier than the start time of the day-ahead stage; the end time of the day-ahead stage is earlier than the start time of the day-ahead stage; Determine a reference day-ahead market bidding model according to the m sub-models and the reference predicted electricity price; the reference day-ahead market bidding model includes a first objective function and a first constraint condition; Processing the first objective function for uncertainty in electricity prices to obtain a second objective function; Processing the first constraint condition for source-load uncertainty to obtain a second constraint condition; Determine a target day-ahead market bidding model according to the second objective function and the second constraint condition; Determine the day-ahead clearing result according to the target day-ahead market bidding model; Calculate the day-ahead clearing result according to the preset intraday deviation penalty cost mechanism to obtain the intraday deviation penalty cost; Based on the intraday deviation penalty cost and according to the preset cost correction scheme, a model is constructed to obtain an intraday real-time scheduling model; The day-ahead clearing result is adjusted according to the intraday real-time scheduling model to obtain an intraday scheduling result.

[0006] In a second aspect, an embodiment of the present application provides an optimization scheduling device based on a multi-resource aggregate, the device comprising a first acquisition module, a second acquisition module, a first determination module, a processing module, a second determination module, a calculation module, a construction module and an adjustment module, wherein: The first acquisition module is used to acquire m sub-models, where the m sub-models are obtained by training m MRA models with m resource data in the day-ahead stage; each resource data corresponds to a resource; and m is an integer greater than 1; The second acquisition module is used to acquire historical electricity price data within a preset time period, and predict the electricity price of the intraday stage according to the historical electricity price data to obtain a reference predicted electricity price; the end time of the preset time period is earlier than the start time of the day-ahead stage; the end time of the day-ahead stage is earlier than the start time of the intraday stage; The first determination module is used to determine a reference day-ahead market bidding model according to the m sub-models and the reference predicted electricity price; the reference day-ahead market bidding model includes a first objective function and a first constraint condition; The processing module is used to process the first objective function for uncertainty of electricity price to obtain a second objective function; and process the first constraint condition for uncertainty of source and load to obtain a second constraint condition; The second determination module is used to determine a target day-ahead market bidding model according to the second objective function and the second constraint condition; and determine a day-ahead clearing result according to the target day-ahead market bidding model; The calculation module is used to calculate the day-ahead clearing result according to a preset intraday deviation penalty cost mechanism to obtain the intraday deviation penalty cost; The construction module is used to construct a model based on the intraday deviation penalty cost and according to a preset cost correction scheme to obtain an intraday real-time scheduling model; The adjustment module is used to adjust the day-ahead clearing result according to the intraday real-time scheduling model to obtain an intraday scheduling result.

[0007] In a third aspect, an embodiment of the present application provides an electronic device, comprising a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the program includes instructions for executing the steps of any method in the first aspect of the embodiment of the present application.

[0008] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute part or all of the steps described in any method of the first aspect of the embodiment of the present application.

[0009] In a fifth aspect, an embodiment of the present application provides a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute some or all of the steps described in any method of the first aspect of the embodiment of the present application. The computer program product may be a software installation package.

[0010] By implementing the embodiments of the present application, the uncertainty of electricity prices and source-load uncertainties are processed, which facilitates improving the accuracy of the day-ahead clearing results, and optimizes them in real time through the intraday deviation penalty cost mechanism, thereby improving the accuracy and real-time performance of resource scheduling. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0012] Figure 1 This is an application scenario diagram of resource scheduling of a multi-resource aggregate provided by an embodiment of the present application; Figure 2 It is a structural schematic diagram of a multi-resource aggregate provided in an embodiment of the present application; Figure 3 It is a system architecture diagram of a resource scheduling system provided in an embodiment of the present application; Figure 4 is a structural schematic diagram of an electronic device provided in an embodiment of the present application; Figure 5 It is a flowchart of an optimization scheduling method based on a multi-resource aggregate provided in an embodiment of the present application; Figure 6 It is a flow chart of a source-load uncertainty processing provided by an embodiment of the present application; Figure 7 It is a flow chart of building a real-time scheduling model within a day provided by an embodiment of the present application; Figure 8 It is a functional module composition block diagram of an optimization scheduling device based on a multi-resource aggregate provided in an embodiment of the present application. DETAILED DESCRIPTION

[0013] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0014] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0015] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article indicates that the associated objects before and after are in an "or" relationship. The "plurality" appearing in the embodiments of the present application refers to two or more.

[0016] In the embodiments of the present application, "at least one item" or similar expressions refer to any combination of these items, including any combination of single items or plural items, and refer to one or more, and multiple refers to two or more. For example, at least one item of a, b, or c can represent the following seven situations: a, b, c, a and b, a and c, b and c, a, b, and c. Among them, each of a, b, and c can be an element or a set containing one or more elements.

[0017] The "connection" that appears in the embodiments of the present application refers to various connection methods such as direct connection or indirect connection to achieve communication between devices, and the embodiments of the present application do not impose any limitations on this.

[0018] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0019] The following is an explanation of the relevant terms involved in this application, as follows: Multiresource Aggregator (MRA) refers to an organization or entity that integrates, coordinates and uniformly manages multiple different types of power resources.

[0020] At present, most existing models use deterministic models, assuming that new energy output, load demand and the market are known and fixed values, ignoring the impact of uncertainty on system operation and failing to effectively deal with the frequent uncertainty fluctuations in the market, which leads to deviations in scheduling results. At the same time, most existing scheduling models only focus on the optimization of a single stage, usually only scheduling in the day-ahead stage, while ignoring the real-time adjustment in the intraday stage, and failing to fully consider the overall operation strategy of multiple resource aggregates participating in the market environment. Therefore, how to improve the accuracy and real-time performance of resource scheduling needs to be solved urgently.

[0021] To solve the above problems, the embodiment of the present application provides an optimization scheduling method based on a multi-resource aggregate and a related device, wherein m sub-models are obtained by training m MRA models with m resource data in the day-ahead stage; each resource data corresponds to a resource; m is an integer greater than 1; historical electricity price data in a preset time period is obtained, and the electricity price of the intraday stage is predicted according to the historical electricity price data to obtain a reference predicted electricity price; the end time of the preset time period is earlier than the start time of the day-ahead stage; the end time of the day-ahead stage is earlier than the start time of the intraday stage; a reference day-ahead market bidding model is determined according to the m sub-models and the reference predicted electricity price; the reference day-ahead market bidding model is determined according to the m sub-models and the reference predicted electricity price. The bidding model includes a first objective function and a first constraint; the first objective function is processed for uncertainty in electricity price to obtain a second objective function; the first constraint is processed for uncertainty in source and load to obtain a second constraint; the target day-ahead market bidding model is determined according to the second objective function and the second constraint; the day-ahead clearing result is determined according to the target day-ahead market bidding model; the day-ahead clearing result is calculated according to the preset intraday deviation penalty cost mechanism to obtain the intraday deviation penalty cost; the model is constructed based on the intraday deviation penalty cost and according to the preset cost correction scheme to obtain the intraday real-time scheduling model; the day-ahead clearing result is adjusted according to the intraday real-time scheduling model to obtain the intraday scheduling result. By processing the uncertainty in electricity price and source and load, it is convenient to improve the accuracy of the day-ahead clearing result, and it is optimized in real time through the intraday deviation penalty cost mechanism, thereby improving the accuracy and real-time performance of resource scheduling.

[0022] For easier understanding, see Figure 1 , Figure 1 This is an application scenario diagram of resource scheduling of a multi-resource aggregate provided in an embodiment of the present application, wherein the multi-resource aggregate represents an aggregate that integrates multiple different types of power resources (such as distributed power sources, energy storage, adjustable loads, etc.). The resource scheduling system is responsible for the overall arrangement and deployment of various types of resources of the multi-resource aggregate to achieve optimal utilization of resources. The multi-resource aggregate provides the resource scheduling system with dispatchable resource information, such as the state, capacity, power generation or power consumption capacity of the resources; the power market provides the resource scheduling system with market-related information, such as electricity price fluctuations, trading rules, etc.; the resource scheduling system can formulate a reasonable resource scheduling strategy based on resource information and market-related information, and send scheduling instructions to the multi-resource aggregate according to the resource scheduling strategy to guide the operation mode of its resources, such as the charging and discharging operation of energy storage, the power generation adjustment of distributed power sources, the start and stop of adjustable loads, etc., so as to achieve optimal configuration and efficient utilization of power resources and improve the economy and stability of the overall power operation.

[0023] For easier understanding, see Figure 2 , Figure 2 It is a structural schematic diagram of a multi-resource aggregate provided in an embodiment of the present application, wherein the multi-resource aggregate includes photovoltaic resources, wind power resources, distributed generator sets, interruptible loads, transferable loads, and energy storage resources.

[0024] Among them, photovoltaic resources can be obtained through photovoltaic power generation technology. Photovoltaic power generation technology refers to an energy technology that uses solar cells to directly convert solar radiation energy into electrical energy. It has technical characteristics such as clean, green, and highly reliable. The output characteristics of photovoltaic power generation are closely related to environmental factors, and its output power model is as follows:

[0025] in, Indicates photovoltaic output power; , , It indicates the maximum output power, light intensity and ambient temperature under standard test conditions; G and T indicate the light intensity and temperature in the current environment; k indicates the temperature coefficient, which is usually k=-0.45 and is not specifically limited here. It should be noted that the light intensity in the current environment will change with the change of temperature.

[0026] Among them, wind power resources can be obtained through wind power generation technology. This wind power generation technology refers to an energy technology that uses wind power to drive the rotation of wind turbines, converts wind energy into mechanical energy, and then converts mechanical energy into electrical energy through generators. The core of the wind power generation model is the wind turbine, and its power generation mainly depends on the wind speed and the design characteristics of the wind wheel. Among them, the functional relationship between the output power of wind power generation and wind speed is as follows:

[0027]

[0028]

[0029] in, Indicates the output power of the wind turbine; Indicates the rated power of the wind turbine; , , , Indicates the cut-in wind speed, cut-out wind speed, rated wind speed and actual wind speed of the wind turbine.

[0030] Among them, distributed generator sets refer to power generation equipment that can adjust output power at any time according to power demand. Such power generation equipment includes but is not limited to diesel generators and coal-fired units, which are not specifically limited here. Diesel generators use diesel combustion to drive the engine, which drives the generator to generate electricity. They have the characteristics of rapid start-up and stable output, and are suitable for emergency power supply or scenarios with large load fluctuations; coal-fired units burn coal to heat water to generate steam, drive steam turbines to generate electricity, and are widely used in basic load power supply. Among them, the power generation cost of distributed generator sets is as follows:

[0031] in, , Indicates the operating cost and actual output of distributed generator sets; , Represents the operating cost coefficient of distributed generator sets.

[0032] Among them, the constraints satisfied by the distributed generator set include the unit output constraint and the climbing constraint, as shown below:

[0033]

[0034] in, , Indicates the upper and lower limits of the unit output; , Indicates the upper and lower limits of the unit's climbing; t indicates the time point corresponding to moment t.

[0035] Among them, interruptible load refers to the power load that can be temporarily interrupted according to the needs of the power grid or emergency situations during the operation of the power system. Usually, this type of load is signed by users (such as industrial electricity, commercial facilities, etc.), who agree to actively reduce or stop electricity consumption under certain conditions when the power supply is tight. In this way, the power system can alleviate the pressure of supply and demand and enhance the stability of the system during peak load periods or when the power grid fails. The management of interruptible loads helps to reduce the operating costs of the power system and improve the reliability of power supply. Among them, the call cost of interruptible load users is as follows:

[0036]

[0037] in, represents the calling cost of the interruptible load user; It represents the unit compensation cost for load interruption of interruptible load users; It indicates the load interruption amount of interruptible load users; They respectively represent the maximum interruption upper limit of load.

[0038] Among them, transferable load refers to the load that can be flexibly transferred between different time periods or different regions in the power system. The characteristic of this load is that users can transfer part of the load to the time period or area with lower grid load during the peak period of power demand, thereby optimizing the operation of the grid. Transferable loads are usually applied to loads with flexible scheduling capabilities, such as industrial production lines, cold chain storage, or large-scale air-conditioning systems. By effectively managing transferable loads, the peak-to-valley difference in electricity can be reduced, the economy and stability of the power system can be improved, and excessive loads during peak periods can be avoided. Among them, the call cost of transferable load users is as follows:

[0039]

[0040]

[0041]

[0042] in, represents the call cost of the transferable load user; It represents the unit compensation cost for load transfer of transferable load users; , Indicates the load increase and decrease of the transferable load users, which must be the same in the entire dispatch cycle; Indicates the maximum load transfer upper limit.

[0043] Among them, energy storage resources can be obtained through energy storage equipment. Energy storage equipment can store electricity when there is surplus electricity, such as battery energy storage systems, pumped storage, etc.; release electricity when there is a power shortage, play a role in regulating power supply and demand, smoothing power fluctuations, and improving the stability and reliability of the power system. Among them, the operating costs and constraints of the energy storage equipment are as follows:

[0044]

[0045]

[0046]

[0047]

[0048]

[0049] in, represents the operating cost of the energy storage device; , Indicates the charging power and discharging power of the energy storage device; Represents the unit operating cost of the energy storage equipment; It is the upper limit of charging and discharging of energy storage equipment; Indicates the energy storage capacity of the energy storage device; , Indicates the upper and lower limits of the energy storage capacity of the energy storage device; The charging and discharging efficiency of the energy storage device; Indicates the energy storage capacity of the energy storage device at the initial moment; Represents the energy storage capacity of the energy storage device at time T.

[0050] It can be seen that by integrating different types of resources into a multi-resource aggregate and conducting unified coordination and management, it is easier to participate in electricity market transactions and grid operation and dispatching.

[0051] For easier understanding, see Figure 3 , Figure 3 It is a system architecture diagram of a resource scheduling system provided by an embodiment of the present application, and the resource scheduling system includes an information collection module, a scheduling analysis module and a strategy output module. Among them, the information collection module is used to collect the power generation capacity of the internal resources of the multi-resource aggregate (such as photovoltaic and wind power power forecasts), the energy storage power state, the regulation potential of the adjustable load, etc., and obtain the electricity price information, market supply and demand situation and transaction rules in the power market in real time. The scheduling analysis module is used to analyze the information collected by the information collection module, and combine the power system operation constraints, such as power balance constraints, equipment operation parameter constraints, etc., to build a resource scheduling model. For example, with cost minimization or profit maximization as the objective function, the power generation cost, power purchase cost, power sales revenue, etc. of the resources are considered, and the operating characteristic constraints of various resources are included (such as the upper and lower limits of the output of distributed generators, the charging and discharging power limits of energy storage, etc.). Then use the preset optimization algorithm (such as linear programming, integer programming, heuristic algorithm, etc.) to solve the resource scheduling model to obtain a preliminary resource scheduling strategy, including the power generation, power consumption, energy storage charging and discharging arrangements of each resource in different time periods. Then, the resource scheduling strategy is evaluated and optimized based on the actual situation and the preset mechanism to obtain the final resource scheduling strategy. The strategy output module is used to output the formulated scheduling strategy to the multi-resource aggregate for execution. During the execution process, the resource operation status, power market changes, etc. are continuously monitored. If the actual situation does not meet expectations, timely feedback can be provided and the scheduling strategy can be readjusted to ensure that resource scheduling is always in the optimal or better state.

[0052] It can be seen that by analyzing the electricity price fluctuations in the power market and combining the cost characteristics of various resources in the multi-resource aggregate to schedule resources, it is convenient to improve the overall resource utilization efficiency and reduce the cost of resource scheduling.

[0053] Combine the following Figure 4 The electronic device in the embodiment of the present application is described. Figure 4 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application, such as Figure 4 As shown, the electronic device includes one or more processors, a memory, a communication interface and one or more programs, and the processor is communicatively connected with the memory and the communication interface via an internal communication bus.

[0054] Among them, the processor is mainly used for: Obtain m sub-models, wherein the m sub-models are obtained by training m MRA models with m resource data in the day-ahead stage; each resource data corresponds to a resource; and m is an integer greater than 1; Obtaining historical electricity price data within a preset time period, and predicting the electricity price of the intraday stage based on the historical electricity price data to obtain a reference predicted electricity price; the end time of the preset time period is earlier than the start time of the day-ahead stage; the end time of the day-ahead stage is earlier than the start time of the day-ahead stage; Determine a reference day-ahead market bidding model according to the m sub-models and the reference predicted electricity price; the reference day-ahead market bidding model includes a first objective function and a first constraint condition; Processing the first objective function for uncertainty in electricity prices to obtain a second objective function; Processing the first constraint condition for source-load uncertainty to obtain a second constraint condition; Determine a target day-ahead market bidding model according to the second objective function and the second constraint condition; Determine the day-ahead clearing result according to the target day-ahead market bidding model; Calculate the day-ahead clearing result according to the preset intraday deviation penalty cost mechanism to obtain the intraday deviation penalty cost; Based on the intraday deviation penalty cost and according to the preset cost correction scheme, a model is constructed to obtain an intraday real-time scheduling model; The day-ahead clearing result is adjusted according to the intraday real-time scheduling model to obtain an intraday scheduling result.

[0055] The one or more programs are stored in the above-mentioned memory and are configured to be executed by the above-mentioned processor, and the one or more programs include instructions for executing any step in the above-mentioned method embodiment.

[0056] Among them, the processor can be a central processing unit, a general processor, a digital signal processor, an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a transistor logic device, a hardware component or any combination thereof, which is not specifically limited here. The processor can also be a combination that implements a computing function, such as a combination of one or more microprocessors. The communication unit can be a communication interface, a transceiver, a transceiver circuit, etc., and the storage unit can be a memory. The memory can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories.

[0057] It is understandable that the electronic device may include more or fewer structural elements than those in the above structural block diagram, for example, including a power module, physical buttons, Wi-Fi module, speaker, Bluetooth module, sensor, display module, etc., which are not limited here. It is understandable that the electronic device may be equipped with Figure 3 The system architecture described.

[0058] After understanding the software and hardware architecture of this application, Figure 5 An optimization scheduling method based on a multi-resource aggregate in an embodiment of the present application is described. Figure 5 : is a flow chart of an optimization scheduling method based on a multi-resource aggregate provided in an embodiment of the present application, which specifically includes the following steps: Step S501, obtaining m sub-models.

[0059] Among them, the m sub-models are obtained by training m MRA models through m resource data in the day-ahead stage; each resource data corresponds to a resource; and m is an integer greater than 1.

[0060] The step of obtaining m sub-models specifically includes: A1. Obtain reference resource data; the reference resource data is any one of the m resource data; A2. Determine the reference resource type corresponding to the reference resource data; the reference resource type includes any one of the following: photovoltaic, wind power, distributed generator set, interruptible load, transferable load, energy storage; A3. Determine reference type parameters according to the reference resource type; A4. Determine a reference objective function and reference constraint conditions according to the reference type parameters; A5. Determine a reference sub-model according to the reference objective function and the reference constraint condition; the reference sub-model is a sub-model corresponding to the reference resource data among the m sub-models.

[0061] In a specific embodiment, first, one resource data is selected from m resource data as reference resource data, and then the reference resource type corresponding to the reference resource data is determined. Among them, different resource types correspond to different operating characteristics and influencing factors, and the reference resource type includes any one of the following: photovoltaic, wind power, distributed generator set, interruptible load, transferable load, energy storage. Then, the corresponding reference type parameters are determined according to the reference resource type. For example, when the reference resource type is photovoltaic, the reference type parameters include but are not limited to light intensity, temperature, photovoltaic panel efficiency. When the reference resource type is energy storage, the reference type parameters include but are not limited to energy storage capacity, charging and discharging efficiency, and charging and discharging power limit. No specific limitation is made here.

[0062] Next, the corresponding reference objective function and reference constraint conditions are determined according to the reference type parameters. For example, when the reference resource type is energy storage, a reference objective function can be constructed according to the reference type parameters corresponding to the energy storage. The reference objective function can be a related function for the energy storage operating cost to meet the preset charging and discharging requirements and minimize the charging and discharging costs. The operating parameter restrictions corresponding to the reference type parameters can be determined according to the actual operating restrictions of the energy storage equipment, and then the reference constraint conditions are determined according to the operating parameter restrictions. The reference constraint conditions include but are not limited to the upper limit of charging and discharging of the energy storage equipment and the upper and lower limits of the energy storage capacity, which are not specifically limited here.

[0063] Finally, the reference objective function and the reference constraint conditions are combined to construct a reference sub-model for the reference resource data. The reference sub-model can predict or guide the operation strategy of the resource by solving the optimal solution of the reference objective function under the reference constraint conditions based on the input related parameters.

[0064] It can be seen that by analyzing the characteristics and operating rules of different resources, a detailed and accurate model basis can be provided for the subsequent overall scheduling decision of multiple resource aggregates, which will help improve the accuracy and scientificity of resource scheduling and better cope with various complex situations in the power market.

[0065] Step S502 , obtaining historical electricity price data within a preset time period, and predicting the electricity price within the day based on the historical electricity price data to obtain a reference predicted electricity price.

[0066] Among them, the end time of the preset time period is earlier than the start time of the day-ahead stage; the end time of the day-ahead stage is earlier than the start time of the intra-day stage.

[0067] Specifically, the preset time period includes but is not limited to one day, one week, and one month, which are not specifically limited here. The historical electricity price data is analyzed by a preset prediction method, that is, according to the trend, periodicity and other characteristics in the historical electricity price data, combined with the current electricity market information and influencing factors, the prediction result of the electricity price within the day stage is obtained, that is, the reference predicted electricity price. Among them, the prediction method can be time series analysis or machine learning algorithm, which is not specifically limited here.

[0068] Step S503: determining a reference day-ahead market bidding model according to the m sub-models and the reference predicted electricity price.

[0069] The reference day-ahead market bidding model includes a first objective function and a first constraint condition; the reference day-ahead market bidding model is determined according to the m sub-models and the reference predicted electricity price, and the specific steps include: B1. Constructing the objective function of the reference day-ahead market bidding model to obtain the first objective function; the first objective function is as follows:

[0070] in, represents the total market return on the day before; represents the reference predicted electricity price; represents the day-ahead transaction volume; , represents the electricity sold the day before, represents the amount of electricity purchased the day before; represents the power generation cost of distributed generation units; represents the calling cost of the interruptible load user; represents the call cost of the transferable load user; represents the operating cost of the energy storage device; B2. Obtaining the sub-models whose resource types are the photovoltaic and wind power in the m sub-models, and obtaining a photovoltaic power model and a wind power model; B3. Predicting the power generation power in the intraday stage according to the photovoltaic power model and the wind power model to obtain a photovoltaic power prediction value and a wind power prediction value; B4. Obtain the constraint condition corresponding to each sub-model in the m sub-models to obtain m constraint conditions; B5. Determine a first power balance condition corresponding to the reference day-ahead market bidding model according to the photovoltaic power forecast value and the wind power forecast value; B6. Determine the first constraint condition according to the m constraint conditions, the first power balance condition and the preset market power purchase and sale constraint condition; B7. Determine the reference day-ahead market bidding model according to the first objective function and the first constraint condition.

[0071] In a specific embodiment, first, the objective function of the reference day-ahead market bidding model is constructed according to the reference predicted electricity price, the day-ahead transaction power, and the sum of the costs of various resources to obtain the first objective function. Then, the sub-models of the m sub-models whose resource types are photovoltaic and wind power are obtained to obtain the photovoltaic power model and the wind power model, and then the power generation power in the intraday stage is predicted according to the photovoltaic power model and the wind power model to obtain the photovoltaic power prediction value and the wind power prediction value.

[0072] Next, obtain the constraints corresponding to each of the m sub-models to obtain m constraints. For example, the upper and lower limits of the power generation of distributed generators, the charging and discharging power limits and the upper and lower limits of the capacity of energy storage devices, etc. Then, determine the first power balance condition corresponding to the reference day-ahead market bidding model based on the photovoltaic power forecast value and the wind power forecast value. Among them, the first power balance condition is as follows:

[0073] in, Represents the predicted value of photovoltaic power; Indicates the predicted value of wind power; Indicates the load forecast value.

[0074] Among them, the multi-resource aggregation should meet the transaction constraints of the power market, that is, it cannot purchase and sell electricity at the same time. Indicates that multiple resource aggregates sell electricity in the day-ahead market. It means no electricity is sold. It means that the multi-resource aggregation buys electricity in the day-ahead market. Therefore, when the product of the two is 0, it is proved that at least one of them is 0, and the preset market purchase and sale constraints are as follows:

[0075] Finally, the m constraints, the first power balance condition and the market power purchase and sale constraint are integrated to obtain the first constraint. By combining the first objective function with the first constraint, a reference day-ahead market bidding model is constructed. The reference day-ahead market bidding model is used to make market bidding decisions in the day-ahead stage. Under the premise of satisfying the first constraint, the first objective function is optimized to determine the optimal resource scheduling and trading strategy, thereby improving resource utilization efficiency and economic benefits.

[0076] It can be seen that building a reference day-ahead market bidding model by comprehensively considering multiple factors and constraints can help improve the accuracy and rationality of decision-making, reduce market risks, improve resource utilization efficiency, and promote the healthy development of the electricity market.

[0077] Step S504: performing electricity price uncertainty processing on the first objective function to obtain a second objective function.

[0078] The step of performing electricity price uncertainty processing on the first objective function to obtain the second objective function specifically includes: C1. Analyze the historical electricity price data to obtain the probability distribution of electricity prices; C2. Divide the electricity price probability distribution into N equal parts to obtain N intervals; the length of each interval is 1 / N; N is an integer greater than 1; C3. Randomly draw each of the N intervals according to a preset random drawing formula to obtain N random numbers; the random drawing formula is as follows:

[0079] in, represents a random number drawn from the i-th interval among the N intervals; r represents any random number in [0,1]; C4. Calculate according to a preset electricity price scenario value calculation formula to obtain N electricity price scenario values; the electricity price scenario value calculation formula is as follows:

[0080] in, represents the i-th electricity price scenario value among the N electricity price scenario values; Represents a probability distribution function corresponding to the historical electricity price data; C5. Calculate the N electricity price scenario values ​​according to a preset clustering algorithm to obtain S electricity price scenario values; S is an integer greater than 1 and less than N; C6. Adjust the first objective function according to the S electricity price scenario values ​​to obtain the second objective function.

[0081] In a specific embodiment, first, the historical electricity price data is deeply analyzed, and the probability of the electricity price appearing in different value ranges is determined by statistical and probability calculation methods, thereby obtaining the probability distribution of the electricity price. The probability distribution of the electricity price is then divided into N equal parts to obtain N intervals, each of which is 1 / N in length. By discretizing the probability space of the electricity price, it is convenient for subsequent random extraction and calculation of scenario values. Then, each of the N intervals is randomly extracted according to the random extraction formula to obtain N random numbers. By simulating the random value of the electricity price in different intervals, the uncertainty of the electricity price is taken into consideration.

[0082] Next, according to the calculation formula of the electricity price scenario value, N electricity price scenario values ​​are calculated, and each scenario value represents a different electricity price situation that may occur. Then, according to the pre-set clustering algorithm, the N electricity price scenario values ​​are calculated to obtain S electricity price scenario values. Among them, the clustering algorithm can be a K-means clustering algorithm, which randomly extracts from the N electricity price scenario values ​​to obtain S initial electricity price scenario values, and sets them as S initial clustering centers, and then calculates the distance between each electricity price scenario value and the S initial clustering centers according to the Euclidean distance formula, and then assigns each electricity price scenario value to the initial clustering center with the smallest distance therefrom, and then calculates the mean corresponding to each clustering center, and uses it as the updated clustering center. Finally, the steps of assigning electricity price scenario values ​​and updating clustering centers are repeated until the S clustering centers no longer change, thereby obtaining the S electricity price scenario values ​​corresponding to the final S clustering centers. By using this clustering algorithm, similar electricity price scenario values ​​can be classified into one category, thereby reducing the number of scenario values, retaining representative electricity price scenarios, and simplifying subsequent analysis and calculations.

[0083] Then, the first objective function is adjusted according to the S electricity price scenario values ​​to obtain the second objective function. The second objective function is as follows:

[0084] Where S represents the number of electricity price scenario values; represents the scenario probability corresponding to the sth electricity price scenario value; , , , They respectively represent the reference predicted electricity price, the day-ahead electricity sales, the day-ahead electricity purchase, the power generation cost of distributed generators, the call cost of interruptible load users, the call cost of transferable load users, and the operating cost of energy storage equipment corresponding to the s-th electricity price scenario value.

[0085] It can be seen that through a series of operations such as analysis of historical electricity price data, random sampling and scenario value calculation, the uncertainty of electricity prices is fully considered. Simulating multiple possible electricity price scenarios makes the decision more robust and reduces the risks caused by electricity price fluctuations.

[0086] Step S505: performing source-load uncertainty processing on the first constraint condition to obtain a second constraint condition.

[0087] For easier understanding, see Figure 6 , Figure 6 : is a flow chart of a source-load uncertainty processing provided by an embodiment of the present application, wherein the source-load uncertainty processing is performed on the first constraint condition to obtain the second constraint condition, and the specific steps include: D1. Calculate the net load according to a preset net load calculation formula to obtain a reference net load; the net load calculation formula is as follows:

[0088] in, represents the reference payload; Indicates load power; Represents photovoltaic power; represents wind power; D2. Calculate the photovoltaic power prediction value and the wind power prediction value according to the net load calculation formula to obtain a net load prediction value; D3. Determine a first target formula according to the reference net load and the net load forecast value; the first target formula is as follows:

[0089] in, represents the net load forecast value; represents the random error corresponding to the net load forecast value, where the error mean is 0 and the variance is ; D4. Adjusting the first power balance condition according to the first target formula to obtain an opportunity constraint condition; D5. Determine the second constraint condition based on the m constraints, the opportunity constraint condition and the market power purchase and sale constraint condition.

[0090] In a specific embodiment, first, the net load is calculated according to a pre-set net load calculation formula to obtain a reference net load. The net load represents the difference between the load power and the new energy output. The new energy output can be photovoltaic power and wind power, which are not specifically limited here. Then, the photovoltaic power prediction value and the wind power prediction value are substituted into the net load calculation formula to obtain the net load prediction value. Then, the first target formula is determined based on the reference net load and the net load prediction value.

[0091] Next, the first power balance condition is adjusted according to the first target formula to obtain the opportunity constraint condition, wherein the opportunity constraint condition is as follows:

[0092] in, It indicates the confidence probability level, which can be set according to a preset reference range, which can be 90%-99%, and is not specifically limited here. It should be noted that the opportunity constraint condition is difficult to solve directly, and it can be converted into a deterministic form for calculation. The deterministic form of the opportunity constraint condition is as follows:

[0093] in, Represents the inverse function of the standard normal distribution. Finally, the m constraints, opportunity constraints and market power purchase and sales constraints are integrated to obtain the second constraint.

[0094] It can be seen that by predicting the net load, the uncertainty of new energy power generation such as photovoltaic and wind power and load is fully considered, making the constraints more in line with the actual operation of the power system and improving the reliability and robustness of the decision.

[0095] Step S506: determining a target day-ahead market bidding model according to the second objective function and the second constraint condition.

[0096] Specifically, the target day-ahead market bidding model is determined according to the second objective function and the second constraint. Among them, the second objective function takes into account the uncertainty of electricity prices. By processing historical electricity price data to obtain multiple electricity price scenario values ​​and adjusting accordingly, it can more accurately reflect the market revenue under different electricity price scenarios; the second constraint condition processes the source-load uncertainty of the first constraint condition, integrates the constraints of each resource sub-model, the opportunity constraints after considering the uncertainty of net load, and the market purchase and sale constraints, and comprehensively covers various restrictions in the operation of the power system.

[0097] Step S507, determining the day-ahead clearing result according to the target day-ahead market bidding model.

[0098] Specifically, the target day-ahead market bidding model can be solved according to a preset optimization algorithm to obtain the optimal value of the decision variable. Among them, the optimization algorithm includes but is not limited to linear programming, integer programming, genetic algorithm, particle swarm algorithm, and the decision variables include but are not limited to the power generation power of distributed generators, the adjustment amount of interruptible loads and transferable loads, the charging and discharging power of energy storage equipment, and the power purchase and sales of the day-ahead market, which are not specifically limited here. Among them, the day-ahead clearing results include the power generation side clearing results, the load side clearing results, the energy storage clearing results and the market transaction clearing results, among which the power generation side clearing results represent the power generation of various power generation resources in different periods of the day-ahead plan, the load side clearing results represent the specific adjustment scheme of interruptible loads and transferable loads, the energy storage clearing results represent the charging and discharging power and power changes of energy storage equipment in different periods, and the market transaction clearing results represent the power purchase and sales of the day-ahead market.

[0099] Step S508, calculating the day-ahead clearing result according to a preset intra-day deviation penalty cost mechanism to obtain an intra-day deviation penalty cost.

[0100] The step of calculating the day-ahead clearing result according to the preset intraday deviation penalty cost mechanism to obtain the intraday deviation penalty cost specifically includes: E1. Calculate according to the preset deviation power calculation formula to obtain positive deviation power and negative deviation power; The calculation formula of the deviation power is as follows:

[0101]

[0102] in, Indicates the positive deviation quantity; Indicates the negative deviation quantity; and They respectively represent the actual winning bid purchase amount of the multi-resource aggregate in the day-ahead market and the actual purchase amount in the intraday market; and They respectively represent the actual winning bid power sales of the multi-resource aggregate in the day-ahead market and the actual power sales in the intraday market; and They represent the actual winning transaction volume of the multi-resource aggregate in the day-ahead market and the actual transaction volume in the intraday market respectively; E2. Calculate according to a preset intraday deviation penalty cost calculation formula to obtain the intraday deviation penalty cost; The intraday deviation penalty cost calculation formula is as follows:

[0103] in, represents the intraday deviation penalty cost; Indicates the real-time market price during the day; represents the day-ahead clearing price corresponding to the day-ahead clearing result; represents the deviation of the bid electricity of the multi-resource aggregate in the intraday market and the day-ahead market; ,when When greater than or equal to 0, is 1; when When it is less than 0, is 0.

[0104] In a specific embodiment, first, a calculation is performed according to a preset deviation power calculation formula to obtain positive deviation power and negative deviation power. The deviation power calculation formula is as follows:

[0105]

[0106] It should be noted that when the actual power purchase of a multi-resource aggregate exceeds the bid power purchase amount, or the actual power sales are lower than the bid power sales, the aggregate must pay the corresponding deviation cost according to the real-time electricity price; when the actual power purchase of a multi-resource aggregate is lower than the bid power purchase amount, or the actual power sales exceed the bid power sales, the aggregate can obtain corresponding benefits according to the difference between the real-time electricity price and the day-ahead electricity price. , .

[0107] Next, the positive deviation electricity and the negative deviation electricity are substituted into the intraday deviation penalty cost calculation formula to calculate the intraday deviation penalty cost.

[0108] The calculation formula for intraday deviation penalty cost is as follows:

[0109] It should be noted that when u is 1, If it is greater than or equal to 0, it means that the deviation power is positive, and the multi-resource aggregate needs to pay the deviation cost, that is, ; When u is 0, If it is less than 0, it means that the deviation power is negative, then the multi-resource aggregate can obtain part of the benefits, that is, .

[0110] It can be seen that by calculating the positive and negative deviation electricity volume and the intraday deviation penalty cost, the economic impact brought about by the deviation of electricity volume in the day-ahead and intraday market transactions of the multi-resource aggregate can be quantified, which is convenient for more accurate prediction of power generation and consumption, reducing electricity volume deviation and penalty cost. At the same time, it also helps to maintain the trading order of the electricity market and reasonably reflect the impact of market price fluctuations on trading results.

[0111] Step S509: constructing a model based on the intraday deviation penalty cost and according to a preset cost correction scheme to obtain an intraday real-time scheduling model.

[0112] For easier understanding, see Figure 7 , Figure 7 : This is a flow chart of constructing a real-time scheduling model within a day provided by an embodiment of the present application. The model is constructed based on the intraday deviation penalty cost and according to a preset cost correction scheme to obtain the real-time scheduling model within a day. The specific steps include: F1. Calculate according to the preset cost correction calculation formula to obtain the energy storage cost change and the distributed generator cost change; the cost correction calculation formula is as follows:

[0113] in, represents the change in energy storage cost; represents the unit operating cost of energy storage; Indicates the energy storage charging power in the day-ahead period; Indicates the energy storage discharge power in the day-ahead stage; Indicates the energy storage charging power during the intra-day stage; Indicates the energy storage discharge power during the intra-day stage;

[0114] in, Indicates the cost change of the distributed generator set; Indicates the unit operation cost coefficient; represents the output of the distributed generator set in the day-ahead period; Indicates the output of the distributed generator set during the intraday stage; F2. Determine a third objective function according to the energy storage cost change and the distributed generator cost change; the third objective function is as follows:

[0115] in, represents the total cost of the intraday period; F3. Determine a second power balance condition corresponding to the third objective function; F4. Determine a third constraint condition according to the m constraint conditions, the second power balance condition and the market power purchase and sale constraint condition; F5. Determine the intraday real-time scheduling model according to the third objective function and the third constraint condition.

[0116] In a specific embodiment, first, a calculation is performed according to a preset cost correction calculation formula to obtain the energy storage cost change and the distributed generator set cost change. Then, a third objective function is determined according to the energy storage cost change and the distributed generator set cost change. Then, a second power balance condition corresponding to the third objective function is determined, wherein the second power balance condition is as follows:

[0117] in, represents the photovoltaic power in the intraday phase; Indicates the wind power renewable energy in the intraday stage; Indicates the load power during the intraday phase; , , It indicates the corresponding amount of demand in the day-ahead phase, which remains unchanged in the intraday phase.

[0118] Next, the m constraints, the second power balance condition and the market power purchase and sale constraint condition are integrated to obtain the third constraint condition. Finally, the intraday real-time dispatch model is determined according to the third objective function and the third constraint condition.

[0119] It can be seen that by optimizing the third objective function and constructing a real-time scheduling model within the day, the optimal output of distributed generators and the charging and discharging strategies of energy storage can be determined during the day, thereby achieving optimal resource allocation of multi-resource aggregates in real-time operation within the day, reducing total costs, and improving overall economy and reliability.

[0120] Step S510, adjusting the day-ahead clearing result according to the intraday real-time scheduling model to obtain an intraday scheduling result.

[0121] Specifically, through the intraday real-time dispatch model, the day-ahead clearing results can be optimized and adjusted based on the real-time power system status and power market information during the intraday stage, thereby obtaining the intraday dispatch results. Among them, by executing the intraday dispatch results, it is possible to better adapt to the actual operation of the intraday power system, reduce the risk of cost increase due to forecast deviations and actual operation changes, and improve the stability and economy of power system operation. At the same time, it also helps to make more rational use of various types of power resources, improve resource utilization efficiency, ensure the balance of power supply and demand, and provide more practical operation guidance plans for power market participants and system operators.

[0122] The above mainly introduces the scheme of the embodiment of the present application from the perspective of the execution process of the method side. It is understandable that in order to realize the above functions, the electronic device includes a hardware structure and / or software module corresponding to each function. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiment provided herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software.

[0123] The embodiment of the present application can divide the electronic device into functional units according to the above method example. For example, each functional unit can be divided according to each function, or two or more functions can be integrated into one processing unit. The above integrated unit can be implemented in the form of hardware or in the form of software functional units. It should be noted that the division of units in the embodiment of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation.

[0124] In the case of dividing each functional module into corresponding functional modules, Figure 8 800 is a functional module composition block diagram of an optimization scheduling device based on a multi-resource aggregate provided in an embodiment of the present application. The optimization scheduling device based on a multi-resource aggregate 800 includes a first acquisition module 810, a second acquisition module 820, a first determination module 830, a processing module 840, a second determination module 850, a calculation module 860, a construction module 870 and an adjustment module 880, wherein: The first acquisition module 810 is used to acquire m sub-models, where the m sub-models are obtained by training m MRA models with m resource data in the day-ahead stage; each resource data corresponds to a resource; and m is an integer greater than 1; The second acquisition module 820 is used to acquire historical electricity price data within a preset time period, and predict the electricity price of the intraday stage according to the historical electricity price data to obtain a reference predicted electricity price; the end time of the preset time period is earlier than the start time of the day-ahead stage; the end time of the day-ahead stage is earlier than the start time of the intraday stage; The first determination module 830 is used to determine a reference day-ahead market bidding model according to the m sub-models and the reference predicted electricity price; the reference day-ahead market bidding model includes a first objective function and a first constraint condition; The processing module 840 is used to process the first objective function for uncertainty of electricity price to obtain a second objective function; and process the first constraint condition for uncertainty of source and load to obtain a second constraint condition; The second determination module 850 is used to determine a target day-ahead market bidding model according to the second objective function and the second constraint condition; and determine a day-ahead clearing result according to the target day-ahead market bidding model; The calculation module 860 is used to calculate the day-ahead clearing result according to a preset intraday deviation penalty cost mechanism to obtain the intraday deviation penalty cost; The construction module 870 is used to construct a model based on the intraday deviation penalty cost and according to a preset cost correction scheme to obtain an intraday real-time scheduling model; The adjustment module 880 is used to adjust the day-ahead clearing result according to the intraday real-time scheduling model to obtain an intraday scheduling result.

[0125] Optionally, in the aspect of acquiring m sub-models, the first acquiring module 810 is specifically used for: Acquire reference resource data; the reference resource data is any one of the m resource data; Determine the reference resource type corresponding to the reference resource data; the reference resource type includes any one of the following: photovoltaic, wind power, distributed generator set, interruptible load, transferable load, energy storage; Determining a reference type parameter according to the reference resource type; Determine a reference objective function and a reference constraint condition according to the reference type parameter; A reference sub-model is determined according to the reference objective function and the reference constraint condition; the reference sub-model is a sub-model corresponding to the reference resource data among the m sub-models.

[0126] Optionally, in determining the reference day-ahead market bidding model according to the m sub-models and the reference predicted electricity price, the first determining module 830 is specifically configured to: The objective function of the reference day-ahead market bidding model is constructed to obtain the first objective function; the first objective function is as follows:

[0127] in, represents the total market return on the day before; represents the reference predicted electricity price; represents the day-ahead transaction volume; , represents the electricity sold the day before, represents the amount of electricity purchased the day before; represents the power generation cost of distributed generation units; represents the calling cost of the interruptible load user; represents the call cost of the transferable load user; Represents the operating cost of the energy storage device; Obtaining the sub-models whose resource types are the photovoltaic and the wind power in the m sub-models, and obtaining a photovoltaic power model and a wind power model; Predicting the power generation power in the intra-day stage according to the photovoltaic power model and the wind power model to obtain a photovoltaic power prediction value and a wind power prediction value; Obtaining the constraint condition corresponding to each sub-model in the m sub-models to obtain m constraint conditions; Determine a first power balance condition corresponding to the reference day-ahead market bidding model according to the photovoltaic power forecast value and the wind power forecast value; Determine the first constraint condition according to the m constraint conditions, the first power balance condition and the preset market power purchase and sale constraint condition; The reference day-ahead market bidding model is determined according to the first objective function and the first constraint condition.

[0128] Optionally, in the aspect of performing electricity price uncertainty processing on the first objective function to obtain the second objective function, the processing module 840 is specifically used for: Analyzing the historical electricity price data to obtain an electricity price probability distribution; Divide the electricity price probability distribution into N equal parts to obtain N intervals; the length of each interval is 1 / N; N is an integer greater than 1; Each of the N intervals is randomly selected according to a preset random selection formula to obtain N random numbers; the random selection formula is as follows:

[0129] in, represents a random number drawn from the i-th interval among the N intervals; r represents any random number in [0,1]; Calculate according to the preset electricity price scenario value calculation formula to obtain N electricity price scenario values; the electricity price scenario value calculation formula is as follows:

[0130] in, represents the i-th electricity price scenario value among the N electricity price scenario values; Represents a probability distribution function corresponding to the historical electricity price data; The N electricity price scenario values ​​are calculated according to a preset clustering algorithm to obtain S electricity price scenario values; S is an integer greater than 1 and less than N; The first objective function is adjusted according to the S electricity price scenario values ​​to obtain the second objective function.

[0131] Optionally, in the aspect of performing source-load uncertainty processing on the first constraint condition to obtain the second constraint condition, the processing module 840 is further specifically used to: The net load is calculated according to a preset net load calculation formula to obtain a reference net load; the net load calculation formula is as follows:

[0132] in, represents the reference payload; Indicates load power; Represents photovoltaic power; represents wind power; Calculate the photovoltaic power prediction value and the wind power prediction value according to the net load calculation formula to obtain a net load prediction value; A first target formula is determined according to the reference net load and the net load forecast value; the first target formula is as follows:

[0133] in, represents the net load forecast value; represents the random error corresponding to the net load forecast value, where the error mean is 0 and the variance is ; Adjusting the first power balance condition according to the first target formula to obtain an opportunity constraint condition; The second constraint condition is determined according to the m constraint conditions, the opportunity constraint condition and the market power purchase and sale constraint condition.

[0134] Optionally, in calculating the day-ahead clearing result according to the preset intraday deviation penalty cost mechanism to obtain the intraday deviation penalty cost, the calculation module 860 is specifically used to: Calculate according to the preset deviation power calculation formula to obtain positive deviation power and negative deviation power; The calculation formula of the deviation power is as follows:

[0135]

[0136] in, Indicates the positive deviation quantity; Indicates the negative deviation quantity; and They respectively represent the actual winning bid purchase amount of the multi-resource aggregate in the day-ahead market and the actual purchase amount in the intraday market; and They respectively represent the actual winning bid power sales of the multi-resource aggregate in the day-ahead market and the actual power sales in the intraday market; and They represent the actual winning transaction volume of the multi-resource aggregate in the day-ahead market and the actual transaction volume in the intraday market respectively; Calculate according to the preset intraday deviation penalty cost calculation formula to obtain the intraday deviation penalty cost; The intraday deviation penalty cost calculation formula is as follows:

[0137] in, represents the intraday deviation penalty cost; Indicates the real-time market price during the day; represents the day-ahead clearing price corresponding to the day-ahead clearing result; represents the deviation of the bid electricity of the multi-resource aggregate in the intraday market and the day-ahead market; ,when When greater than or equal to 0, is 1; when When it is less than 0, is 0.

[0138] Optionally, in the aspect of constructing a model based on the intraday deviation penalty cost and according to a preset cost correction scheme to obtain an intraday real-time scheduling model, the construction module 870 is specifically used to: The change in energy storage cost and the change in distributed generator cost are calculated according to the preset cost correction calculation formula; the cost correction calculation formula is as follows:

[0139] in, represents the change in energy storage cost; It represents the unit operating cost of energy storage; Indicates the energy storage charging power in the day-ahead period; Indicates the energy storage discharge power in the day-ahead stage; Indicates the energy storage charging power during the intra-day stage; Indicates the energy storage discharge power during the intra-day stage;

[0140] in, Indicates the cost change of the distributed generator set; Indicates the unit operation cost coefficient; represents the output of the distributed generator set in the day-ahead period; Indicates the output of the distributed generator set during the intraday stage; The third objective function is determined according to the energy storage cost change and the distributed generator cost change; the third objective function is as follows:

[0141] in, represents the total cost of the intraday period; Determining a second power balance condition corresponding to the third objective function; Determine a third constraint condition according to the m constraint conditions, the second power balance condition and the market power purchase and sale constraint condition; The intraday real-time scheduling model is determined according to the third objective function and the third constraint condition.

[0142] It can be seen that by processing the uncertainty of electricity prices and source-load uncertainties, it is convenient to improve the accuracy of the day-ahead clearing results, and to optimize them in real time through the intraday deviation penalty cost mechanism, thereby improving the accuracy and real-time performance of resource scheduling.

[0143] It should be noted that the specific implementation of each operation can adopt the corresponding description of the method embodiment shown above, and the optimization scheduling device 800 based on the multi-resource aggregate can be used to execute the above method embodiment of the present application, which will not be repeated here.

[0144] An embodiment of the present application also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute part or all of the steps of any method recorded in the above method embodiments, and the above computer includes an electronic device.

[0145] The embodiment of the present application also provides a computer program product, the computer program product includes a non-transitory computer-readable storage medium storing a computer program, the computer program is operable to cause a computer to execute some or all of the steps of any method described in the method embodiment. The computer program product may be a software installation package, and the computer includes an electronic device.

[0146] It should be noted that, for the above-mentioned various embodiments, for the sake of simple description, they are all expressed as a series of action combinations. Those skilled in the art should be aware that the present application is not limited by the described order of actions, because some steps in the embodiments of the present application can be performed in other orders or simultaneously. In addition, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions, steps, modules or units involved are not necessarily required by the embodiments of the present application.

[0147] In the above embodiments, the embodiments of the present application have different focuses on the description of each embodiment. For parts not described in detail in a certain embodiment, please refer to the relevant description of other embodiments. The steps of the method or algorithm described in the embodiments of the present application can be implemented in hardware or by a processor executing software instructions.

[0148] Those skilled in the art should be aware that in one or more of the above examples, the functions described in the embodiments of the present application can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website site, computer, server, or data center to another website site, computer, server, or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a digital video disc (DVD)), or a semiconductor medium (eg, a solid state disk (SSD)).

[0149] The modules / units included in the devices and products described in the above embodiments may be software modules / units or hardware modules / units, or may be partially software modules / units and partially hardware modules / units. For example, for the devices and products applied to or integrated in the chip, the modules / units included therein may all be implemented in the form of hardware such as circuits, or at least some of the modules / units may be implemented in the form of software programs, which run on the processor integrated inside the chip, and the remaining (if any) modules / units may be implemented in the form of hardware such as circuits; for the devices and products applied to or integrated in the chip module, the modules / units included therein may all be implemented in the form of hardware such as circuits, and different modules / units may be located in the same component (such as chip, circuit module, etc.) or different components of the chip module, or at least some of the modules / units may be implemented in the form of software programs. It is implemented in the form of a software program that runs on a processor integrated inside the chip module, and the remaining (if any) modules / units can be implemented in hardware such as circuits; for various devices and products applied to or integrated in the terminal equipment, the various modules / units contained therein can be implemented in hardware such as circuits, and different modules / units can be located in the same component (for example, chip, circuit module, etc.) or different components in the terminal equipment, or at least some of the modules / units can be implemented in the form of a software program that runs on a processor integrated inside the terminal equipment, and the remaining (if any) modules / units can be implemented in hardware such as circuits.

[0150] The specific implementation methods described above further illustrate the purpose, technical solutions and beneficial effects of the embodiments of the present application. It should be understood that the above description is only the specific implementation method of the embodiments of the present application and is not intended to limit the protection scope of the embodiments of the present application. Any modifications, equivalent substitutions, improvements, etc. made on the basis of the technical solutions of the embodiments of the present application should be included in the protection scope of the embodiments of the present application.

Claims

1. An optimization scheduling method based on a multi-resource aggregate, characterized in that: The method comprises: Obtain m sub-models, wherein the m sub-models are obtained by training m MRA models with m resource data in the day-ahead stage; each resource data corresponds to a resource; and m is an integer greater than 1; Obtaining historical electricity price data within a preset time period, and predicting the electricity price of the intraday stage based on the historical electricity price data to obtain a reference predicted electricity price; the end time of the preset time period is earlier than the start time of the day-ahead stage; the end time of the day-ahead stage is earlier than the start time of the day-ahead stage; Determine a reference day-ahead market bidding model according to the m sub-models and the reference predicted electricity price; the reference day-ahead market bidding model includes a first objective function and a first constraint condition; Processing the first objective function for uncertainty in electricity prices to obtain a second objective function; Processing the first constraint condition for source-load uncertainty to obtain a second constraint condition; Determine a target day-ahead market bidding model according to the second objective function and the second constraint condition; Determine the day-ahead clearing result according to the target day-ahead market bidding model; Calculate the day-ahead clearing result according to the preset intraday deviation penalty cost mechanism to obtain the intraday deviation penalty cost; Based on the intraday deviation penalty cost and according to the preset cost correction scheme, a model is constructed to obtain an intraday real-time scheduling model; The day-ahead clearing result is adjusted according to the intraday real-time scheduling model to obtain an intraday scheduling result.

2. The method according to claim 1, characterized in that The obtaining of m sub-models comprises: Acquire reference resource data; the reference resource data is any one of the m resource data; Determine the reference resource type corresponding to the reference resource data; the reference resource type includes any one of the following: photovoltaic, wind power, distributed generator set, interruptible load, transferable load, energy storage; Determining a reference type parameter according to the reference resource type; Determine a reference objective function and a reference constraint condition according to the reference type parameter; A reference sub-model is determined according to the reference objective function and the reference constraint condition; the reference sub-model is a sub-model corresponding to the reference resource data among the m sub-models.

3. The method according to claim 1, characterized in that The step of determining a reference day-ahead market bidding model according to the m sub-models and the reference predicted electricity price includes: The objective function of the reference day-ahead market bidding model is constructed to obtain the first objective function; the first objective function is as follows: in, represents the total market return on the day before; represents the reference predicted electricity price; represents the day-ahead transaction volume; , represents the electricity sold the day before, represents the amount of electricity purchased the day before; represents the power generation cost of distributed generation units; represents the calling cost of the interruptible load user; represents the call cost of the transferable load user; Represents the operating cost of the energy storage device; Obtaining the sub-models whose resource types are the photovoltaic and the wind power in the m sub-models, and obtaining a photovoltaic power model and a wind power model; Predicting the power generation power in the intra-day stage according to the photovoltaic power model and the wind power model to obtain a photovoltaic power prediction value and a wind power prediction value; Obtaining the constraint condition corresponding to each sub-model in the m sub-models to obtain m constraint conditions; Determine a first power balance condition corresponding to the reference day-ahead market bidding model according to the photovoltaic power forecast value and the wind power forecast value; Determine the first constraint condition according to the m constraint conditions, the first power balance condition and the preset market power purchase and sale constraint condition; The reference day-ahead market bidding model is determined according to the first objective function and the first constraint condition.

4. The method according to claim 3, characterized in that The performing electricity price uncertainty processing on the first objective function to obtain a second objective function includes: Analyzing the historical electricity price data to obtain an electricity price probability distribution; Divide the electricity price probability distribution into N equal parts to obtain N intervals; the length of each interval is 1 / N; N is an integer greater than 1; Each of the N intervals is randomly selected according to a preset random selection formula to obtain N random numbers; the random selection formula is as follows: in, represents a random number drawn from the i-th interval among the N intervals; r represents any random number in [0,1]; Calculate according to the preset electricity price scenario value calculation formula to obtain N electricity price scenario values; the electricity price scenario value calculation formula is as follows: in, represents the i-th electricity price scenario value among the N electricity price scenario values; Represents a probability distribution function corresponding to the historical electricity price data; The N electricity price scenario values ​​are calculated according to a preset clustering algorithm to obtain S electricity price scenario values; S is an integer greater than 1 and less than N; The first objective function is adjusted according to the S electricity price scenario values ​​to obtain the second objective function.

5. The method according to claim 3, characterized in that The performing source-load uncertainty processing on the first constraint condition to obtain the second constraint condition includes: The net load is calculated according to a preset net load calculation formula to obtain a reference net load; the net load calculation formula is as follows: in, represents the reference payload; Indicates load power; Represents photovoltaic power; represents wind power; Calculate the photovoltaic power prediction value and the wind power prediction value according to the net load calculation formula to obtain a net load prediction value; A first target formula is determined according to the reference net load and the net load forecast value; the first target formula is as follows: in, represents the net load forecast value; represents the random error corresponding to the net load forecast value, where the error mean is 0 and the variance is ; Adjusting the first power balance condition according to the first target formula to obtain an opportunity constraint condition; The second constraint condition is determined according to the m constraint conditions, the opportunity constraint condition and the market power purchase and sale constraint condition.

6. The method according to any one of claims 1 to 5, characterized in that: The day-ahead clearing result is calculated according to the preset intraday deviation penalty cost mechanism to obtain the intraday deviation penalty cost, including: Calculate according to the preset deviation power calculation formula to obtain positive deviation power and negative deviation power; The calculation formula of the deviation power is as follows: in, Indicates the positive deviation quantity; Indicates the negative deviation quantity; and They respectively represent the actual winning bid purchase amount of the multi-resource aggregate in the day-ahead market and the actual purchase amount in the intraday market; and They respectively represent the actual winning bid power sales of the multi-resource aggregate in the day-ahead market and the actual power sales in the intraday market; and They represent the actual winning transaction volume of the multi-resource aggregate in the day-ahead market and the actual transaction volume in the intraday market respectively; Calculate according to the preset intraday deviation penalty cost calculation formula to obtain the intraday deviation penalty cost; The intraday deviation penalty cost calculation formula is as follows: in, represents the intraday deviation penalty cost; Indicates the real-time market price during the day; represents the day-ahead clearing price corresponding to the day-ahead clearing result; represents the deviation of the bid electricity of the multi-resource aggregate in the intraday market and the day-ahead market; ,when When greater than or equal to 0, is 1; when When it is less than 0, is 0.

7. The method according to claim 6, characterized in that The model is constructed based on the intraday deviation penalty cost and according to a preset cost correction scheme to obtain an intraday real-time scheduling model, including: The change in energy storage cost and the change in distributed generator cost are calculated according to the preset cost correction calculation formula; the cost correction calculation formula is as follows: in, represents the change in energy storage cost; It represents the unit operating cost of energy storage; Indicates the energy storage charging power in the day-ahead period; Indicates the energy storage discharge power in the day-ahead stage; Indicates the energy storage charging power during the intra-day stage; Indicates the energy storage discharge power during the intra-day stage; in, Indicates the cost change of the distributed generator set; Indicates the unit operation cost coefficient; represents the output of the distributed generator set in the day-ahead period; Indicates the output of the distributed generator set during the intraday stage; The third objective function is determined according to the energy storage cost change and the distributed generator cost change; the third objective function is as follows: in, represents the total cost of the intraday period; Determining a second power balance condition corresponding to the third objective function; Determine a third constraint condition according to the m constraint conditions, the second power balance condition and the market power purchase and sale constraint condition; The intraday real-time scheduling model is determined according to the third objective function and the third constraint condition.

8. An optimization scheduling device based on a multi-resource aggregate, characterized in that: The device includes a first acquisition module, a second acquisition module, a first determination module, a processing module, a second determination module, a calculation module, a construction module and an adjustment module, wherein: The first acquisition module is used to acquire m sub-models, where the m sub-models are obtained by training m MRA models with m resource data in the day-ahead stage; each resource data corresponds to a resource; and m is an integer greater than 1; The second acquisition module is used to acquire historical electricity price data within a preset time period, and predict the electricity price of the intraday stage according to the historical electricity price data to obtain a reference predicted electricity price; the end time of the preset time period is earlier than the start time of the day-ahead stage; the end time of the day-ahead stage is earlier than the start time of the intraday stage; The first determination module is used to determine a reference day-ahead market bidding model according to the m sub-models and the reference predicted electricity price; the reference day-ahead market bidding model includes a first objective function and a first constraint condition; The processing module is used to process the first objective function for uncertainty of electricity price to obtain a second objective function; and process the first constraint condition for uncertainty of source and load to obtain a second constraint condition; The second determination module is used to determine a target day-ahead market bidding model according to the second objective function and the second constraint condition; and determine a day-ahead clearing result according to the target day-ahead market bidding model; The calculation module is used to calculate the day-ahead clearing result according to a preset intraday deviation penalty cost mechanism to obtain the intraday deviation penalty cost; The construction module is used to construct a model based on the intraday deviation penalty cost and according to a preset cost correction scheme to obtain an intraday real-time scheduling model; The adjustment module is used to adjust the day-ahead clearing result according to the intraday real-time scheduling model to obtain an intraday scheduling result.

9. An electronic device, characterized in that: include: A processor, a memory, a communication interface, and one or more programs; The one or more programs are stored in the memory and configured to be executed by the processor, the programs comprising instructions for executing the steps in the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the processor is caused to perform the method according to any one of claims 1 to 7.

Images