Virtual power plant scheduling optimization method and system

Abstract

The invention provides a virtual power plant scheduling optimization method and system, and the method comprises the steps: constructing an evolutionary strategy model which takes the maximization of economic benefits, the minimization of power deviation and the minimization of operation cost as objective functions for a virtual power plant; collecting real-time operation data of each distributed energy source in the virtual power plant; taking the preprocessed real-time operation data and the environment state as model input of the evolutionary strategy model, training and optimizing a scheduling strategy by using an evolutionary strategy algorithm, and outputting an optimal scheduling strategy for the virtual power plant; and regulating and controlling each distributed energy source in the virtual power plant by using the scheduling optimization strategy. According to the method, the scheduling strategy is generated and evaluated in a manner of simulating population evolution, a nearly optimal solution can be quickly found in a complex and multi-target virtual power plant scheduling scene, and the method has relatively high robustness and flexibility and can adapt to different power market environments and scheduling requirements.

Description

Technical Field

[0001] The present invention relates to the technical field of smart grid dispatch optimization, and in particular to a virtual power plant dispatch optimization method and system. Background Art

[0002] A virtual power plant (VPP) is a system that integrates and coordinates distributed energy (such as photovoltaics, wind power, energy storage, etc.) through information and communication technology. Virtual power plants achieve efficient use of power resources through optimized scheduling and participate in power market transactions.

[0003] At present, traditional virtual power plant scheduling methods (such as linear programming, dynamic programming, etc.) are inefficient when faced with complex nonlinear and multi-objective optimization problems, and are difficult to cope with the highly uncertain renewable energy output and diverse user needs in VPP. In addition, although deep reinforcement learning methods based on machine learning perform well, they often require a large amount of training data and computing resources, making them difficult to quickly deploy in actual systems. In addition, existing virtual power plant scheduling methods also have the following major defects:

[0004] (1) Strong data dependence: Existing deep reinforcement learning algorithms require a large amount of data for training and are prone to failure when faced with new scenarios or abnormal situations, lacking flexibility;

[0005] (2) High consumption of computing resources: Deep learning algorithms usually require a large amount of computing resources for training and reasoning, which poses a challenge to virtual power plant scheduling optimization with high real-time requirements;

[0006] (3) Slow algorithm convergence: Existing optimization methods converge slowly in complex scheduling scenarios and it is difficult to provide high-quality scheduling solutions in a short time. Summary of the invention

[0007] To this end, the present invention provides a virtual power plant scheduling optimization method and system, aiming to solve the technical problem that the existing technology has deficiencies in dealing with complex nonlinear and multi-objective optimization problems and it is difficult to quickly and accurately deploy virtual power plant scheduling optimization.

[0008] To achieve the above objectives, the present invention adopts the following technical solutions:

[0009] According to a first aspect of the present invention, the present invention provides a virtual power plant scheduling optimization method, the method comprising:

[0010] For the virtual power plant, an evolutionary strategy model is constructed with maximizing economic benefits and minimizing power deviation and operating costs as objective functions;

[0011] Collect real-time operation data of each distributed energy source in the virtual power plant;

[0012] The preprocessed real-time operation data and environmental status are used as model inputs of the evolution strategy model, and the evolution strategy algorithm is used to train and optimize the scheduling strategy to output the optimal scheduling strategy for the virtual power plant;

[0013] Using the scheduling optimization strategy to regulate each distributed energy source in the virtual power plant;

[0014] The real-time operation data includes at least one of output power, load demand, energy storage status and electricity price.

[0015] Optionally, the objective function formula is expressed as follows:

[0016]

[0017] Among them, the income t is the income calculated based on electricity price and electricity trading volume, in RMB; power deviation t is the deviation between actual power supply and demand, in MW; operating cost t Including energy loss and operation and maintenance cost of energy storage equipment charging and discharging, the unit is yuan; weight coefficients α, β, λ represent the benefits t , Power Deviation t , operating costs t The weight of is used to adjust the priority of the optimization objective; the strategy parameter θ represents the scheduling strategy for the virtual power plant.

[0018] Optionally, the optimizing scheduling strategy by using an evolutionary strategy algorithm to train and output an optimal scheduling strategy for the virtual power plant includes:

[0019] Randomly generate multiple sets of initial strategy parameters to form an initial population;

[0020] Using the objective function to evaluate the fitness of each group of initial strategy parameters in the initial population;

[0021] Select the initial strategy parameters with higher fitness for mutation operation and perform population iteration;

[0022] During the population iteration process, the strategy parameters that meet the fitness standards are selected as the optimal scheduling strategy for the virtual power plant.

[0023] Optionally, the randomly generating multiple groups of initial strategy parameters to form an initial population includes:

[0024] Set the initial population size to N, and generate N sets of random strategy parameters θ at the initial moment i , i=1,2,....,N;

[0025] The initial population formula is expressed as follows:

[0026]

[0027] Optionally, the using the objective function to evaluate the fitness of each group of initial strategy parameters in the initial population includes:

[0028] Calculating the objective function value of each group of initial strategy parameters in the initial population as the fitness, specifically includes:

[0029] For each time t, based on the strategy parameters and the system status of the virtual power plant t Generate the corresponding system action a t ;

[0030] Based on the system status s t and the system action a t , get the execution of the system action a t The target system state after t+1 ;

[0031] The objective function value is calculated based on the target system state.

[0032] Optionally, the system state s t The formula is as follows:

[0033]

[0034] in, is the output power of distributed energy at time t, in MW; is the load demand at time t, in MW; S t is the energy storage state at time t, in MWh; M t is the electricity price at time t, in yuan / MWh;

[0035] The system action a t The formula is as follows:

[0036]

[0037] in, is the strategy function; is the charging power of the energy storage device at time t, in MW; The discharge power of the energy storage device at time t, in MW; is the output power of distributed energy at time t, in MW;

[0038] The target system state s t+1 The formula is as follows:

[0039]

[0040] in, is the output power of distributed energy at time t+1, in MW; is the load demand at time t+1, in MW; S t+1 is the energy storage state at time t+1, in MWh; M t+1 is the electricity price at time t+1, in Yuan / MWh.

[0041] Optionally, the selecting of initial strategy parameters with higher fitness to perform mutation operation and performing population iteration includes:

[0042] Step S1: using a roulette selection method or a tournament selection method to select k strategy parameters with higher fitness;

[0043] Step S2: Add random noise to the k strategy parameters to obtain a new generation of strategy parameters, which is expressed as follows:

[0044]

[0045] in, is the new generation strategy parameter; σ is the mutation intensity; ε(0,I) is a normal distribution with a mean of 0 and a variance of the unit matrix;

[0046] Step S3: Use the new generation strategy parameters to replace the initial population to form a new generation population And repeat steps S1 to S2.

[0047] Optionally, in the population iteration process, selecting a strategy parameter with satisfactory fitness as the optimal scheduling strategy of the virtual power plant includes:

[0048] During the population iteration process, the fitness of each set of strategy parameters is calculated in real time. If the fitness change is less than a preset threshold, or the maximum number of iterations is reached, the population iteration is terminated;

[0049] After the population iteration is terminated, the strategy parameters with the highest fitness in the latest population are output as the optimal scheduling strategy of the virtual power plant.

[0050] Optionally, the utilizing the scheduling optimization strategy to regulate each distributed energy source in the virtual power plant includes:

[0051] The target system action is generated according to the optimal scheduling strategy, and the formula is as follows:

[0052]

[0053] in, Action for the target system; is the strategy function; is the policy parameter corresponding to the optimal scheduling strategy;

[0054] The target system action is used to regulate the charging power, discharging power of the energy storage device corresponding to each distributed energy in the virtual power plant and / or the output power of each distributed energy.

[0055] According to a second aspect of the present invention, the present invention provides a virtual power plant scheduling optimization system, the system comprising:

[0056] A model building module, used for building an evolutionary strategy model with maximizing economic benefits and minimizing power deviation and operating costs as objective functions for the virtual power plant;

[0057] Data acquisition module, used to collect real-time operation data of each distributed energy source in the virtual power plant;

[0058] A strategy prediction module, used to use the pre-processed real-time operation data and environmental status as the model input of the evolution strategy model, use the evolution strategy algorithm to train the optimization scheduling strategy, and output the optimal scheduling strategy for the virtual power plant;

[0059] An optimization execution module, used to regulate each distributed energy source in the virtual power plant by using the scheduling optimization strategy;

[0060] The real-time operation data includes at least one of output power, load demand, energy storage status and electricity price.

[0061] The present invention adopts the above technical solution and has at least the following beneficial effects:

[0062] Through the scheme of the present invention, for the virtual power plant, an evolutionary strategy model with maximizing economic benefits, minimizing power deviation and operating costs as objective functions is constructed; the real-time operating data of each distributed energy source in the virtual power plant is collected; the pre-processed real-time operating data and environmental status are used as the model input of the evolutionary strategy model, and the evolutionary strategy algorithm is used to train the optimization scheduling strategy, and the optimal scheduling strategy for the virtual power plant is output; the scheduling optimization strategy is used to regulate each distributed energy source in the virtual power plant. Therefore, by simulating population evolution to generate and evaluate scheduling strategies, it is possible to quickly find a near-optimal solution in a complex, multi-objective virtual power plant scheduling scenario, and it has strong robustness and flexibility, and can adapt to different power market environments and scheduling needs.

[0063] It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0065] Figure 1 A schematic diagram of a flow chart of a virtual power plant scheduling optimization method provided by an embodiment of the present invention is shown;

[0066] Figure 2 A schematic diagram of the structure of a virtual power plant scheduling optimization system provided by an embodiment of the present invention is shown;

[0067] Figure 3 A schematic diagram of the physical structure of a computer device provided by an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0068] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0069] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "include..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0070] The embodiment of the present invention provides a virtual power plant scheduling optimization method, such as Figure 1 As shown, at least the following steps S101 to S104 may be included:

[0071] Step S101, for the virtual power plant, construct an evolutionary strategy model with maximizing economic benefits and minimizing power deviation and operating costs as objective functions.

[0072] Evolution strategy is an optimization method based on natural selection and genetic algorithms. It optimizes the objective function by simulating the evolutionary process of the population. It has the advantages of strong adaptability and high computational efficiency. It does not rely on gradient information and is suitable for high-dimensional, non-convex optimization problems. In the embodiment of the present invention, the evolution strategy model is used to perform scheduling optimization analysis on each distributed energy source in the virtual power plant. The objective function is defined as the cumulative revenue from within the entire scheduling period, and the optimization goal is to optimize the economic benefits, including expanding revenue, reducing power deviation and operating costs. The objective function is defined as the cumulative revenue from (t=1 to T) during the entire scheduling period, and the formula is expressed as follows:

[0073]

[0074] Among them, the income t is the income calculated based on electricity price and electricity trading volume, in RMB; power deviation t is the deviation between actual power supply and demand, in MW; operating cost t Including energy loss and operation and maintenance cost of energy storage equipment charging and discharging, the unit is yuan; weight coefficients α, β, λ represent the benefits t , Power Deviation t , operating costs t The weight of is used to adjust the priority of the optimization objective; the strategy parameter θ is a set of parameters used to generate system actions, representing the scheduling strategy for the virtual power plant.

[0075] The evolution strategy model proposed in the embodiment of the present invention is based on the evolution strategy algorithm to train and optimize the scheduling strategy. The model input includes pre-processed real-time operation data and environmental status, and the output is a scheduling decision.

[0076] Step S102, collecting real-time operating data of each distributed energy source in the virtual power plant.

[0077] Real-time operation data includes but is not limited to power generation, load demand, energy storage status, etc., which are used to clarify the dispatchable capacity of each distributed energy source in the virtual power plant. In the virtual power plant dispatch optimization based on evolutionary strategy, it is first necessary to define the system status of the virtual power plant and the system action related parameters.

[0078] System Status t It can be represented by a vector:

[0079]

[0080] in, is the output power of distributed energy (such as photovoltaic and wind power) at time t, in MW; is the load demand at time t, in MW; S tis the energy storage (e.g., electricity level) status at time t, in MWh; M t is the electricity price at time t, in yuan / MWh.

[0081] System Action t It can be represented by a vector:

[0082]

[0083] in, is the charging power of the energy storage device at time t, in MW; The discharge power of the energy storage device at time t, in MW; is the output power of distributed energy at time t, in MW.

[0084] Step S103, using the pre-processed real-time operation data and environmental status as the model input of the evolution strategy model, using the evolution strategy algorithm to train the optimization scheduling strategy, and outputting the optimal scheduling strategy for the virtual power plant.

[0085] Specifically, the evolutionary strategy algorithm may include randomly generating multiple groups of initial strategy parameters to form an initial population; using an objective function to evaluate the fitness of each group of initial strategy parameters in the initial population; selecting initial strategy parameters with higher fitness for mutation operations, and performing population iteration; during the population iteration process, selecting strategy parameters that meet the fitness standards as the optimal scheduling strategy for the virtual power plant.

[0086] That is to say, we first need to set the initial population size to N and generate N sets of random strategy parameters θ at the initial moment. i , i=1,2,....,N;

[0087] The initial population formula is as follows:

[0088]

[0089] Furthermore, for each strategy parameter in the initial population Evaluate and calculate the objective function value as fitness, which may include: for each time t, based on the strategy parameters and the system status of the virtual power plant t Generate the corresponding system action a t ;

[0090]

[0091] in, is the policy function, which is used to determine the current system state s t and strategy parameters Generate action a at current time tt ,In reinforcement learning, the policy function is a deterministic function, and the ,actions of the virtual power plant are obtained by inputting ,the policy.

[0092] Therefore, the system state s can be used t and system action a t , we can get the value of executing system action a t The target system state after s t+1 :

[0093]

[0094] in, is the output power of distributed energy at time t+1, in MW; is the load demand at time t+1, in MW; S t+1 is the energy storage state at time t+1, in MWh; M t+1 is the electricity price at time t+1, in Yuan / MWh.

[0095] Further, an initial strategy parameter with a higher fitness is selected for mutation operation, and population iteration is performed, which may specifically include the following steps S1 to S3:

[0096] Step S1: Use Roulette Wheel Selection or Tournament Selection to select k strategy parameters with higher fitness;

[0097] Step S2: Add random noise to k strategy parameters to obtain a new generation of strategy parameters, which is expressed as follows:

[0098]

[0099] in, is the new generation strategy parameter; σ is the mutation intensity; ε(0,I) is a normal distribution with a mean of 0 and a variance of the unit matrix;

[0100] Step S3: Use the new generation strategy parameters to replace the initial population to form a new generation population And repeat steps S1 to S2.

[0101] That is to say, the new generation strategy parameters after adding noise replace the old generation population to form a new generation population, and continue the strategy evaluation and selection mutation process until the stopping condition is met.

[0102] Furthermore, during the population iteration process, the fitness of each set of strategy parameters can be calculated in real time. If the fitness change is less than the preset threshold, or the maximum number of iterations G is reached, max, it is considered that it has converged to the optimal solution and the population iteration is terminated; after the population iteration is terminated, the strategy parameter with the highest fitness in the latest population is output As the optimal scheduling strategy for virtual power plants, it can be used for scheduling execution of actual systems.

[0103] Step S104, using the scheduling optimization strategy to regulate the distributed energy in the virtual power plant.

[0104] In actual system operation, according to the optimal scheduling strategy Generate the target system action, the formula is as follows:

[0105]

[0106] in, Action for the target system; is the strategy function; is the policy parameter corresponding to the optimal scheduling strategy. Then, using the target system action The charging power, discharging power and / or output power of the energy storage devices corresponding to each distributed energy in the virtual power plant are regulated.

[0107] The embodiment of the present invention provides a virtual power plant scheduling optimization method, by constructing an evolutionary strategy model with maximizing economic benefits, minimizing power deviation and operating costs as objective functions for the virtual power plant; collecting real-time operating data of each distributed energy source in the virtual power plant; using the pre-processed real-time operating data and environmental status as the model input of the evolutionary strategy model, using the evolutionary strategy algorithm to train the optimization scheduling strategy, and outputting the optimal scheduling strategy for the virtual power plant; and using the scheduling optimization strategy to regulate each distributed energy source in the virtual power plant. The present invention proposes an innovative solution to the shortcomings of traditional scheduling methods in dealing with complex nonlinear and multi-objective optimization problems. By simulating the evolutionary strategy of natural selection and genetic algorithms, the present invention can quickly adapt to and optimize the scheduling of distributed energy sources (such as photovoltaics, wind power, energy storage, etc.) in virtual power plants without relying on large amounts of data and computing resources, so as to maximize economic benefits, minimize power deviations and operating costs, and improve the robustness and flexibility of the system. In addition, this technology also involves the field of electricity market transactions and real-time operation data processing. By real-time collection and processing of key data such as power generation, load demand, and energy storage status of distributed energy resources, it provides input for the evolutionary strategy model, and then generates and executes scheduling decisions to achieve efficient utilization of power resources and optimization of market transactions. In summary, the present invention uses evolutionary strategies to achieve the optimization of virtual power plant scheduling, improve the economic benefits and operational stability of the system; this method does not rely on gradient information, has high computational efficiency, and is suitable for complex and changeable electricity market environments. The technical fields directly applied by the present invention cover multiple aspects such as smart grid scheduling optimization, virtual power plant management, electricity market trading strategies, and real-time data processing and analysis, providing important technical support and innovative ideas for the future development of virtual power plant scheduling management.

[0108] Further, as Figure 1 The specific implementation of the present invention provides a virtual power plant scheduling optimization system, such as Figure 2 As shown, the system may include: a model building module 210 , a data collection module 220 , a strategy prediction module 230 and an optimization execution module 240 .

[0109] The model building module 210 can be used to build an evolution strategy model with maximizing economic benefits and minimizing power deviation and operating costs as objective functions for a virtual power plant;

[0110] The data collection module 220 can be used to collect real-time operation data of each distributed energy source in the virtual power plant;

[0111] The strategy prediction module 230 can be used to use the pre-processed real-time operation data and environmental status as the model input of the evolution strategy model, use the evolution strategy algorithm to train the optimization scheduling strategy, and output the optimal scheduling strategy for the virtual power plant;

[0112] The optimization execution module 240 can be used to control each distributed energy source in the virtual power plant using a scheduling optimization strategy;

[0113] The real-time operation data includes at least one of output power, load demand, energy storage status and electricity price.

[0114] Optionally, the strategy prediction module 230 may also be used to randomly generate multiple groups of initial strategy parameters to form an initial population;

[0115] The objective function is used to evaluate the fitness of each set of initial strategy parameters in the initial population;

[0116] Select the initial strategy parameters with higher fitness for mutation operation and perform population iteration;

[0117] During the population iteration process, the strategy parameters that meet the fitness standards are selected as the optimal scheduling strategy for the virtual power plant.

[0118] Optionally, the strategy prediction module 230 can also be used to set the initial population size to N, and generate N groups of random strategy parameters θ at the initial moment. i , i=1,2,....,N;

[0119] The initial population formula is as follows:

[0120]

[0121] Optionally, the strategy prediction module 230 may also be used to calculate the objective function value of each group of initial strategy parameters in the initial population as fitness, specifically including:

[0122] For each time t, based on the strategy parameters and the system status of the virtual power plant t Generate the corresponding system action a t ;

[0123] Based on the system status t and system action a t , get the execution system action a t The target system state after t+1 ;

[0124] The objective function value is calculated based on the target system state.

[0125] Optionally, the strategy prediction module 230 may also be used to perform the following steps S1 to S3:

[0126] Step S1: using a roulette selection method or a tournament selection method to select k strategy parameters with higher fitness;

[0127] Step S2: Add random noise to k strategy parameters to obtain a new generation of strategy parameters, which is expressed as follows:

[0128]

[0129] in, is the new generation strategy parameter; σ is the mutation intensity; ε(0,I) is a normal distribution with a mean of 0 and a variance of the unit matrix;

[0130] Step S3: Use the new generation strategy parameters to replace the initial population to form a new generation population And repeat steps S1 to S2.

[0131] Optionally, the strategy prediction module 230 may also be used to calculate the fitness of each set of strategy parameters in real time during the population iteration process, and terminate the population iteration if the fitness change is less than a preset threshold or the maximum number of iterations is reached;

[0132] After the population iteration is terminated, the strategy parameters with the highest fitness in the latest population are output as the optimal scheduling strategy for the virtual power plant.

[0133] Optionally, the optimization execution module 240 can also be used to generate a target system action according to the optimal scheduling strategy, which is expressed as follows:

[0134]

[0135] in, Action for the target system; is the strategy function; is the policy parameter corresponding to the optimal scheduling strategy;

[0136] The target system action is used to regulate the charging power, discharging power and / or output power of the energy storage device corresponding to each distributed energy in the virtual power plant.

[0137] It should be noted that for other corresponding descriptions of the functional modules involved in the virtual power plant scheduling optimization system provided in the embodiment of the present invention, reference can be made to Figure 1 The corresponding description of the method shown will not be repeated here.

[0138] Based on the above Figure 1 The method shown, accordingly, an embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the virtual power plant scheduling optimization method of any of the above embodiments are implemented.

[0139] Based on the above Figure 1 The method shown and Figure 2The embodiment of the system shown in the figure, the embodiment of the present invention also provides a physical structure diagram of a computer device, such as Figure 3 As shown, the computer device may include a communication bus, a processor, a memory and a communication interface, and may also include an input / output interface and a display device, wherein each functional unit may communicate with each other through the bus. The memory stores a computer program, and the processor is used to execute the program stored in the memory and execute the steps of the virtual power plant scheduling optimization method of the above embodiment.

[0140] Those skilled in the art can clearly understand that the specific working processes of the systems, devices, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and for the sake of brevity, they are not further described here.

[0141] In addition, the functional units in various embodiments of the present invention may be physically independent of each other, or two or more functional units may be integrated together, or all functional units may be integrated into one processing unit. The above integrated functional units may be implemented in the form of hardware, or in the form of software or firmware.

[0142] Those skilled in the art can understand that if the integrated functional unit is implemented in the form of software and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention can essentially or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, which includes a number of instructions to enable a computing device (such as a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention when running the instructions. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk and other media that can store program codes.

[0143] Alternatively, all or part of the steps of implementing the aforementioned method embodiments may be accomplished by hardware associated with program instructions (such as a computing device such as a personal computer, a server, or a network device), and the program instructions may be stored in a computer-readable storage medium. When the program instructions are executed by a processor of a computing device, the computing device executes all or part of the steps of the methods described in the embodiments of the present invention.

[0144] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that within the spirit and principles of the present invention, the technical solutions described in the aforementioned embodiments can still be modified, or some or all of the technical features therein can be replaced by equivalents. However, these modifications or replacements do not deviate from the protection scope of the present invention.

Claims

1. A virtual power plant scheduling optimization method, characterized in that: The method comprises: For the virtual power plant, an evolutionary strategy model is constructed with maximizing economic benefits and minimizing power deviation and operating costs as objective functions; Collect real-time operation data of each distributed energy source in the virtual power plant; The preprocessed real-time operation data and environmental status are used as model inputs of the evolution strategy model, and the evolution strategy algorithm is used to train the optimization scheduling strategy to output the optimal scheduling strategy for the virtual power plant; Using the scheduling optimization strategy to regulate each distributed energy source in the virtual power plant; The real-time operation data includes at least one of output power, load demand, energy storage status and electricity price.

2. The method according to claim 1, characterized in that The objective function formula is expressed as follows: Among them, the income t is the income calculated based on electricity price and electricity trading volume, in RMB; power deviation t is the deviation between actual power supply and demand, in MW; operating cost t Including energy loss and operation and maintenance cost of energy storage equipment charging and discharging, the unit is yuan; weight coefficients α, β, λ represent the benefits t , Power Deviation t , operating costs t The weight of is used to adjust the priority of the optimization objective; the strategy parameter θ represents the scheduling strategy for the virtual power plant.

3. The method according to claim 1, characterized in that The method of using the evolutionary strategy algorithm to train the optimization scheduling strategy and outputting the optimal scheduling strategy for the virtual power plant includes: Randomly generate multiple sets of initial strategy parameters to form an initial population; Using the objective function to evaluate the fitness of each group of initial strategy parameters in the initial population; Select the initial strategy parameters with higher fitness for mutation operation and perform population iteration; During the population iteration process, the strategy parameters that meet the fitness standards are selected as the optimal scheduling strategy for the virtual power plant.

4. The method according to claim 3, characterized in that The randomly generated multiple groups of initial strategy parameters form an initial population, including: Set the initial population size to N, and generate N sets of random strategy parameters θ at the initial moment i , i=1,2,....,N; The initial population formula is expressed as follows:

5. The method according to claim 4, characterized in that The using the objective function to evaluate the fitness of each group of initial strategy parameters in the initial population includes: Calculating the objective function value of each group of initial strategy parameters in the initial population as the fitness, specifically includes: For each time t, based on the strategy parameters and the system status of the virtual power plant t Generate the corresponding system action a t ; Based on the system status s t and the system action a t , get the execution of the system action a t The target system state after t+1 ; The objective function value is calculated based on the target system state.

6. The method according to claim 5, characterized in that The system status s t The formula is as follows: in, is the output power of distributed energy at time t, in MW; is the load demand at time t, in MW; S t is the energy storage state at time t, in MWh; M t is the electricity price at time t, in yuan / MWh; The system action a t The formula is as follows: in, is the strategy function; is the charging power of the energy storage device at time t, in MW; The discharge power of the energy storage device at time t, in MW; is the output power of distributed energy at time t, in MW; The target system state s t+1 The formula is as follows: in, is the output power of distributed energy at time t+1, in MW; is the load demand at time t+1, in MW; S t+1 is the energy storage state at time t+1, in MWh; M t+1 is the electricity price at time t+1, in Yuan / MWh.

7. The method according to claim 3, characterized in that The initial strategy parameters with higher fitness are selected for mutation operation and population iteration is performed, including: Step S1: using a roulette selection method or a tournament selection method to select k strategy parameters with higher fitness; Step S2: Add random noise to the k strategy parameters to obtain a new generation of strategy parameters, which is expressed as follows: in, is the new generation strategy parameter; σ is the mutation intensity; ε(0,I) is a normal distribution with a mean of 0 and a variance of the unit matrix; Step S3: Use the new generation strategy parameters to replace the initial population to form a new generation population And repeat steps S1 to S2.

8. The method according to claim 3, characterized in that In the population iteration process, the strategy parameters with satisfactory fitness are selected as the optimal scheduling strategy of the virtual power plant, including: During the population iteration process, the fitness of each set of strategy parameters is calculated in real time. If the fitness change is less than a preset threshold, or the maximum number of iterations is reached, the population iteration is terminated; After the population iteration is terminated, the strategy parameters with the highest fitness in the latest population are output as the optimal scheduling strategy of the virtual power plant.

9. The method according to claim 1, characterized in that: The method of using the scheduling optimization strategy to regulate each distributed energy source in the virtual power plant includes: The target system action is generated according to the optimal scheduling strategy, and the formula is as follows: in, Action for the target system; is the strategy function; is the policy parameter corresponding to the optimal scheduling strategy; The target system action is used to regulate the charging power, discharging power of the energy storage device corresponding to each distributed energy in the virtual power plant and / or the output power of each distributed energy.

10. A virtual power plant dispatch optimization system, characterized in that: The system comprises: A model building module, used for building an evolutionary strategy model with maximizing economic benefits and minimizing power deviation and operating costs as objective functions for the virtual power plant; Data acquisition module, used to collect real-time operation data of each distributed energy source in the virtual power plant; A strategy prediction module, used to use the pre-processed real-time operation data and environmental status as the model input of the evolution strategy model, use the evolution strategy algorithm to train the optimization scheduling strategy, and output the optimal scheduling strategy for the virtual power plant; An optimization execution module, used to regulate each distributed energy source in the virtual power plant by using the scheduling optimization strategy; The real-time operation data includes at least one of output power, load demand, energy storage status and electricity price.

Images