Data-driven environmental and economic dispatching method and system for power system containing wind power

Abstract

The application belongs to the technical field of power systems, and provides a data-driven environmental and economic dispatching method and system for a wind power system, which is based on a data-driven agent model, a knowledge distillation technology and a modified multi-objective slime mold algorithm, and based on the obtained actual parameters of the wind power grid of any structure, aims to minimize the power generation cost and minimize the environmental pollution, considers the actual power grid operation flow, uses a data-driven fuzzy neural network model to replace the original power generation cost model and environmental pollution model described by mathematical functions, quickly constructs a real-time data-driven fuzzy neural network model by using the knowledge distillation scheme, obtains a set of non-dominated solution set based on the modified multi-objective slime mold algorithm, forms the Pareto optimal frontier of the two optimization targets of "power generation cost-environmental pollution", and then uses the membership function method to obtain a set of optimal dispatching decision basis for the current period; the convergence speed and accuracy of the optimization algorithm are improved.

Description

Technical Field

[0001] This invention belongs to the field of power system technology, and in particular relates to a data-driven environmental and economic dispatching method and system for wind power systems. Background Technology

[0002] The statements in this section are merely background information related to the present invention and do not necessarily constitute prior art.

[0003] With the increasing scale of the power grid and the integration of various new energy sources, environmental pollution is becoming more and more serious. How to balance environmental and economic benefits while ensuring that the quality of power supply is not affected is a major technical challenge worthy of research, and it is also a key aspect of promoting energy conservation and emission reduction in power companies.

[0004] Typically, after load forecasters predict electricity demand for a given period, dispatching plays a decisive role in power supply. This involves issues of load balancing, network losses, environmental impact, and economic efficiency. How to reduce network losses, minimize environmental pollution, and increase the profitability of power companies while ensuring power supply demand is a key area of ​​research.

[0005] Currently, in order to solve the above technical problems, the main research ideas of the existing solutions are: (1) to consider the power generation cost and pollutant emission problems of thermal power units and wind turbines at the same time; (2) to consider different constraints in the power generation and dispatching process; and (3) to select appropriate algorithms for analysis and solution on the basis of meeting the dispatching time requirements.

[0006] The inventors discovered that existing methods have the following technical defects:

[0007] 1. Most methods only consider generator active power constraints and load balancing issues, and use approximate calculation methods for line network losses, which affects the actual load balancing problem. Although traditional methods also consider the actual operation of the power grid, they do not take into account the reality of a large number of renewable energy sources being connected to the grid and participating in dispatch, and are no longer suitable for the dispatch problems of the existing power system.

[0008] 2. Existing scheduling models are based on historical data and use offline methods for scheduling, which cannot meet the needs of real-time scheduling and are inefficient.

[0009] 3. In terms of algorithm application, since the optimal environmental economic dispatch model of a wind power system is a nonlinear and non-convex mathematical model, the traditional multi-objective slime mold algorithm has problems of insufficient convergence ability and slow convergence speed, which greatly prolongs the optimization time and cannot meet the needs of real-time dispatch. Summary of the Invention

[0010] To address at least one of the technical problems mentioned above, this invention provides a data-driven environmental economic dispatch method and system for wind-powered power systems. Based on a data-driven agent model, knowledge distillation, and an improved multi-objective slime mold algorithm, this method minimizes the power generation cost of generator sets while simultaneously minimizing pollutant emissions and reducing fossil fuel consumption, all while meeting electricity load requirements. Furthermore, it significantly reduces computation time, providing timely decision-making support for power companies.

[0011] To achieve the above objectives, the present invention adopts the following technical solution:

[0012] The first aspect of the present invention provides a data-driven environmental economic dispatch method for wind power systems, comprising the following steps:

[0013] Based on the obtained operating parameters of the power grid with wind power, and with the objectives of simultaneously minimizing power generation costs and minimizing environmental pollution, a multi-objective optimization model for the environmental and economic dispatch of the power system with wind power is constructed, taking into account the actual power grid operation flow.

[0014] Acquire unit operation data, replace the multi-objective optimization model with a data-driven fuzzy neural network model, and construct an online data-driven agent model using knowledge distillation technology;

[0015] The online data-driven agent model is solved based on the multi-objective slime mold algorithm. The global optimal solution of the solved model is obtained through the membership function and used as the basis for optimal scheduling decision to complete the environmental and economic optimization scheduling of the wind power system.

[0016] A second aspect of the present invention provides a data-driven environmental and economic dispatch system for wind power systems, comprising:

[0017] The objective optimization model construction module is used to construct a multi-objective optimization model for the environmental and economic dispatch of a power system with wind power, based on the acquired operating parameters of the power grid with wind power, with the objectives of simultaneously minimizing power generation costs and minimizing environmental pollution, and taking into account the actual power grid operation flow.

[0018] The data-driven module is used to acquire unit operation data, replaces the multi-objective optimization model with a data-driven fuzzy neural network model, and uses knowledge distillation technology to build an online data-driven agent model.

[0019] The scheduling module is used to solve the online data-driven agent model based on the multi-objective slime mold algorithm. It obtains the global optimal solution of the solved model through the membership function as the basis for optimal scheduling decision to complete the environmental and economic optimization scheduling of the wind power system.

[0020] A third aspect of the present invention provides a computer-readable storage medium.

[0021] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the data-driven environmental economic dispatch method for wind-powered power systems as described in the first aspect above.

[0022] A fourth aspect of the present invention provides a computer device.

[0023] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the data-driven environmental economic dispatch method for wind-powered power systems as described in the first aspect above.

[0024] Compared with the prior art, the beneficial effects of the present invention are:

[0025] 1. Considering the reality of a large number of renewable energy sources being connected to the grid and participating in dispatch, this invention proposes an environmental and economic dispatch system for wind-powered power systems based on a data-driven agent model, knowledge distillation, and an improved multi-objective slime mold algorithm. This system aims to minimize the power generation cost of generator sets while meeting the electricity load, minimize the emission of pollutants, reduce the use of fossil fuels, and significantly reduce computation time, thus providing timely decision-making support for power companies.

[0026] 2. Based on the fuzzy neural network model, the objective function is reconstructed using a data-driven surrogate assistance method, replacing the original computationally expensive objective function with a computationally fast data-driven fuzzy neural network model. To achieve rapid establishment of the fuzzy neural network surrogate model, knowledge distillation technology and real-time data are used to fine-tune the offline fuzzy neural network surrogate model, thereby saving modeling time.

[0027] 3. This invention improves upon the traditional multi-objective slime mold algorithm, overcoming the drawbacks of traditional weights and methods. To adapt to multi-objective optimization methods, it utilizes sinusoidal chaotic mapping to initialize the population, thereby increasing diversity. Subsequently, it establishes an external archive to store the optimal Pareto front and uses individuals in the Pareto front in the archive to guide the population's optimization, thus improving convergence. This enhances convergence ability and speed, shortens optimization time, and meets the requirements of real-time scheduling.

[0028] Advantages of additional aspects of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0029] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an improper limitation of the invention.

[0030] Figure 1 This is a flowchart of the wind power system dispatching method in Embodiment 1 of this disclosure;

[0031] Figure 2 This is a schematic diagram of the structure in Embodiment 1 of this disclosure, in which a fuzzy neural network model is used to replace the original objective function;

[0032] Figure 3 This is an algorithm flowchart of the data-driven agent model and improved multi-target slime mold algorithm in Embodiment 1 of this disclosure;

[0033] Figure 4 This is a schematic diagram of the IEEE 40-unit test system structure with a fan used in the first embodiment of this disclosure;

[0034] Figure 5 The Pareto optimal frontier generated in Embodiment 1 of this disclosure for an IEEE 40-unit system with a wind turbine (load of 10500MW) considering all the above constraints;

[0035] Figure 6 This is a structural block diagram of the environmental and economic dispatch system for wind power systems in Embodiment 2 of this disclosure. Detailed Implementation

[0036] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0037] It should be noted that the following detailed description is illustrative and intended to provide further explanation of the invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0038] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of exemplary embodiments according to the invention. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Furthermore, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0039] To address the technical problems mentioned in the background section of this invention, this invention employs a data-driven proxy model, knowledge distillation technology, and an improved multi-objective slime mold algorithm. Based on the actual parameters of a wind-powered power grid with arbitrary structure, it aims to simultaneously minimize power generation costs and environmental pollution. Considering the actual power grid operation flow, it replaces the original power generation cost model and environmental pollution model described by mathematical functions with a data-driven fuzzy neural network model. A real-time data-driven fuzzy neural network model is rapidly constructed using knowledge distillation. Based on the improved multi-objective slime mold algorithm, a set of non-dominated solution sets is obtained, forming the Pareto optimal frontier for the two optimization objectives of "power generation cost—environmental pollution." Finally, the membership function method is used to obtain a set of optimal scheduling decision criteria for the current time period. This improves the convergence speed and accuracy of the optimization algorithm and effectively reduces the operation time for scheduling wind-powered power systems.

[0040] Example 1

[0041] Reference Figure 1 This embodiment provides a data-driven environmental economic dispatch method for wind power systems, including the following steps:

[0042] Step 1: Obtain the operating parameters of the wind power system;

[0043] In step 1, the operating parameters of the wind power system include:

[0044] Node parameters; active and reactive loads during the dispatch period; node voltage amplitude, phase angle, and the maximum and minimum voltage that the node can withstand; active and reactive power output of generator nodes, and the maximum and minimum active and reactive power output that the node can withstand; maximum active and reactive power output of each generator; and branch parameters including branch resistance, reactance, per-unit susceptance, per-unit capacity of long / short-distance transmission branches, and the maximum and minimum phase angles allowed for the branch, and system parameters of the wind turbine.

[0045] Step 2: Based on the operating parameters of the wind-powered power system, with the goal of minimizing pollutant emissions and fossil fuel costs, and with constraints such as upper and lower limits of active and reactive power of motors, power balance constraints, node voltage amplitude constraints, and line power flow constraints, an environmental and economic dispatch optimization model for the wind-powered power system is constructed.

[0046] In step 2, the optimization objective 1: the fossil fuel cost function is:

[0047]

[0048] Where C(·) represents the cost function, Ng is the number of thermal power units, and N w f is the number of fans i (P iLet P represent the output of the i-th thermal power unit. i The cost of time, a i b i c i d i e i Let g be the fuel cost coefficient for the i-th generator. j (W j The output of the j-th wind turbine is W. j Cost, q j Let C be the cost coefficient of the j-th wind turbine. rw,j C is the overestimated cost coefficient for the j-th wind turbine. rw,j E(Y oe,j Let C be the overestimated cost of the j-th wind turbine. pw,j C is the underestimation cost coefficient for the j-th wind turbine. pw,j E(Y ue,j ) represents the underestimation cost of the j-th wind turbine.

[0049] Optimization Objective 2: The objective function for pollutant gas emissions is:

[0050]

[0051] Where, α i β i γ i ε i , λ i Let be the pollutant emission coefficient of the i-th generator.

[0052] Generator active and reactive power upper and lower limit constraints:

[0053]

[0054]

[0055]

[0056] Power balance constraints:

[0057]

[0058] Node voltage amplitude constraints:

[0059]

[0060] Power flow constraints:

[0061]

[0062] In the formula, This is the lower limit of the output active power of the i-th generator. This is the lower limit of the output active power of the i-th generator. This is the lower limit of the output power of the j-th wind turbine. This represents the upper limit of the output power of the j-th wind turbine. This is the lower limit of the output reactive power of the i-th generator. N represents the lower limit of the reactive power output of the i-th generator. bus V represents the number of nodes in the power grid. k This represents the node voltage of the k-th node. This represents the minimum node voltage at the k-th node. S represents the maximum node voltage at the k-th node. tk This represents the power flow on the path between node t and node k. This represents the maximum power flow between node t and node k.

[0063] Combining the objective function and constraints, the multi-objective optimization model for environmental and economic dispatch of a wind power system can be summarized as follows:

[0064]

[0065] F(P) and E(P) represent optimization objective 1 and optimization objective 2, respectively. g(P) and h(P) are the equality and inequality constraints involved, respectively. M1 and M2 are the number of equality and inequality constraints, respectively.

[0066] Step 3: Obtain historical operating data of the wind power system, and construct an offline data-driven proxy model based on fuzzy neural network based on the historical operating data;

[0067] Based on the possible solutions of the objective function, a data-driven proxy model is constructed, thereby transforming the original computationally expensive objective function into a fuzzy neural network model that is easy to solve.

[0068] The process of constructing an offline data-driven agent model based on a fuzzy neural network according to historical operational data includes:

[0069] Step 301: Obtain historical operating data, i.e., the unit's output power as input data for the input layer;

[0070] Step 302: Use fuzzy mathematics to process the input data through a membership function layer, transforming each dimension of the input data into three fuzzy sets;

[0071] Step 303: Define fuzzy rules in the fuzzy inference layer;

[0072] Step 304: Determine the confidence coefficients of all rules through the normalization layer;

[0073] Step 305: Transform the fuzzy data into output data through the output layer;

[0074] Step 306: Train the network until the minimum root mean square error is less than a first threshold. In this embodiment, the first threshold is 0.003.

[0075] Step 4: Obtain real-time operational data of the wind power system, and establish an online data-driven agent model using real-time data and knowledge distillation techniques. This specifically includes:

[0076] Step 401: Freeze the network structure and network parameters of the established offline fuzzy neural network data-driven surrogate model;

[0077] Step 402: Fine-tune the normalization layer and output layer by adding real-time data;

[0078] Step 403: Train until the convergence condition of the minimum root mean square error being less than the second threshold is met; in this embodiment, the second threshold is 0.003;

[0079] Step 404: Use the trained fuzzy neural network as an online fuzzy neural network data-driven surrogate model.

[0080] Step 5: The improved multi-objective slime mold algorithm is used to solve the data-driven agent model. The global optimal solution of the solved model is obtained through the membership function and used as the basis for optimal scheduling decision to carry out power dispatching, thereby completing the environmental and economic optimization scheduling of the wind power system.

[0081] Under the condition of meeting the current period load requirements, the multi-objective optimization model is solved by using an improved multi-objective slime mold algorithm to obtain a set of non-dominated solutions and obtain the Pareto optimal frontier of the two optimization objectives of environmental economic scheduling.

[0082] Multi-objective optimization differs from single-objective optimization. While a single-objective optimization can find an optimal solution, multi-objective optimization, such as the environmental and economic objectives involved in this embodiment, involves competing objectives, making it difficult to obtain a single optimal solution. Instead, a trade-off solution between the two objectives can be obtained, resulting in a non-dominated solution set. Figure 3 As shown, the specific solution process is as follows:

[0083] (1) Initialize the population using a sinusoidal chaotic sequence;

[0084] (2) Calculate the initial population fitness values ​​and perform non-dominated sorting; when calculating the fitness values, such as Figure 2 As shown, a proxy model is applied to replace the original objective function for calculation and evaluation.

[0085] (3) Calculate the crowding distance;

[0086] (4) The population with a non-dominant ranking level of 1 is recorded as the initial population of the external elite archive.

[0087] (5) Enter the loop

[0088] (6) Randomly select a position vector from the external elite archive to guide the population optimization;

[0089] (7) Calculate the fitness values ​​of the new population and perform non-dominated sorting;

[0090] (8) Mix the population with non-dominated sorting level 1 and the external elite archive, perform non-dominated sorting, and use the population with non-dominated sorting level 1 as the new external elite archive.

[0091] (9) Determine if the maximum number of iterations has been reached. If it has, output the external elite archive; otherwise, return to step (5) and continue the loop.

[0092] During the implementation of the numerical example, the initialization parameters used in the improved multi-target slime mold algorithm could initially only be assigned values ​​based on experience, but these initial values ​​were clearly not optimal. During algorithm execution, one parameter could be adjusted appropriately while keeping others constant, and the simulation results observed. This method allowed for continuous adjustment of each parameter to achieve the best simulation effect.

[0093] Regarding the obtained non-dominated solutions, in this embodiment, the number of non-dominated solutions is 15;

[0094] All of these solutions are optimal, but the scheduling decision can only select one set from all the current solutions, which requires the power sector to formulate corresponding scheduling strategies based on the actual situation.

[0095] This embodiment presents a discrimination method based on membership function. The non-dominated solution with the largest membership value is selected as the scheduling decision basis for this time period. The specific solution method is as follows:

[0096] (1) For the two optimization objectives of environmental and economic operation, for each objective function, calculate the membership function value corresponding to its non-dominated solution, as follows:

[0097]

[0098] Among them, F i,k For the k-th solution of the i-th optimization objective, and These are the minimum and maximum values ​​of the i-th optimization objective, respectively.

[0099] (2) For each individual nondominated solution, μ i,k Regularization yields μ jThe method is as follows:

[0100]

[0101] Where N1 = 2 is the number of optimization objectives, and M is the number of non-dominated solutions.

[0102] (3) Final solution μ j To obtain the non-dominated solution corresponding to the maximum value, which serves as the basis for scheduling decisions in the current time period.

[0103] The power grid parameters used in the scheduling method employed in this embodiment can be actual power grid operating parameters or any simulation object, such as the IEEE 40-units test system.

[0104] This simulation example uses the IEEE 40-units test system, the system structure diagram of which is shown below. Figure 4 As shown. When using Figure 4 As a case study, the load during the current scheduling period is 10500MW, and the generated Pareto optimal frontier is as follows: Figure 5 As shown.

[0105] Example 2

[0106] like Figure 6 As shown, this embodiment provides a data-driven environmental economic dispatch system for wind power systems, including:

[0107] The objective optimization model construction module is used to construct a multi-objective optimization model for the environmental and economic dispatch of a power system with wind power, based on the acquired operating parameters of the power grid with wind power, with the objectives of simultaneously minimizing power generation costs and minimizing environmental pollution, and taking into account the actual power grid operation flow.

[0108] The data-driven module is used to acquire unit operation data, replaces the multi-objective optimization model with a data-driven fuzzy neural network model, and uses knowledge distillation technology to build an online data-driven agent model.

[0109] The scheduling module is used to solve the online data-driven agent model based on the multi-objective slime mold algorithm. It obtains the global optimal solution of the solved model through the membership function as the basis for optimal scheduling decision to complete the environmental and economic optimization scheduling of the wind power system.

[0110] Example 3

[0111] This embodiment provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps in the data-driven environmental economic dispatch method for wind-powered power systems described in Embodiment 1 above.

[0112] Example 4

[0113] This embodiment provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the steps in the data-driven environmental economic dispatch method for wind-powered power systems described in Embodiment 1 above.

[0114] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of hardware embodiments, software embodiments, or embodiments combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage and optical storage) containing computer-usable program code.

[0115] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0116] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0117] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0118] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0119] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A data-driven environmental and economic dispatch method for wind power systems, characterized in that, Includes the following steps: Based on the obtained operating parameters of the power grid with wind power, and with the objectives of simultaneously minimizing power generation costs and minimizing environmental pollution, a multi-objective optimization model for the environmental and economic dispatch of the power system with wind power is constructed, taking into account the actual power grid operation flow. Acquire unit operation data, replace the multi-objective optimization model with a data-driven fuzzy neural network model, and construct an online data-driven agent model using knowledge distillation technology; The online data-driven agent model is solved based on a multi-objective slime mold algorithm. The global optimal solution of the solved model is obtained through the membership function, which serves as the basis for optimal scheduling decisions to achieve environmental and economic optimization of wind power systems. In the data-driven fuzzy neural network model solved based on the multi-objective slime mold algorithm, the population is initialized using a sinusoidal chaotic mapping. An external archive is established to store the optimal Pareto front, and individuals in the Pareto front in the archive guide the population to find the best solution. Finally, the membership values ​​of all non-dominated solutions are calculated, and the non-dominated solution with the largest membership value is the basis for the optimal scheduling decision in this time period. Among them, based on the historical operating data of the units, the offline data-driven proxy model is obtained by replacing the multi-objective optimization model of power system environmental economic dispatch described by mathematical functions with a data-driven fuzzy neural network model, including: using the historical output power of the units as the input data of the input layer; Fuzzy mathematics is used to process the input data through a membership function layer, transforming each dimension of the input data into three fuzzy sets; based on the fuzzy sets, fuzzy rules are defined in the fuzzy inference layer; the confidence coefficients of all rules are determined through a normalization layer; the data of the fuzzy sets are transformed into output data through an output layer; the network is trained until the minimum root mean square error is less than a first threshold.

2. The data-driven environmental and economic dispatch method for wind power systems as described in claim 1, characterized in that, The method of replacing the multi-objective optimization model with a data-driven fuzzy neural network model and constructing an online data-driven agent model using knowledge distillation technology includes: Based on historical unit operation data, an offline data-driven proxy model is obtained by replacing the power system environmental economic dispatch multi-objective optimization model described by mathematical functions with a data-driven fuzzy neural network model. Based on the offline data-driven agent model, an online data-driven agent model based on a data-driven fuzzy neural network model is constructed according to the real-time operation data of the unit.

3. The data-driven environmental and economic dispatch method for wind power systems as described in claim 2, characterized in that, The offline data-driven agent model, based on real-time unit operation data, constructs an online data-driven fuzzy neural network model, including: Freeze the network structure and network parameters of the already established offline data-driven agent model; The output power of the real-time unit is added to fine-tune the normalization layer and the output layer; The online data-driven surrogate model is obtained by training until the convergence condition that the minimum root mean square error is less than the second threshold is met.

4. The data-driven environmental and economic dispatch method for wind power systems as described in claim 1, characterized in that, The process of obtaining the global optimal solution of the solved model through the membership function includes: Calculate the membership function values ​​corresponding to the non-dominated solutions of the objective function of a multi-objective optimization model; Regularization calculation is performed on the obtained membership function values; Find the non-dominated solution corresponding to the maximum value of the membership function after regularization, which is the global optimal solution.

5. The data-driven environmental and economic dispatch method for wind power systems as described in claim 1, characterized in that, The acquired wind power grid operating parameters include: node parameters; active and reactive loads during the dispatch period; node voltage amplitude, phase angle, and the maximum and minimum voltage that the node can withstand; active and reactive power output of generator nodes, and the maximum and minimum active and reactive power output that the node can withstand; the maximum active and reactive power output allowed by each generator; and branch parameters including branch resistance, reactance, per-unit susceptance, the allowable capacity of long / short distance transmission branches, and the maximum and minimum phase angles allowed by the branch, as well as the system parameters of the wind turbines.

6. A data-driven environmental economic dispatch system for wind-powered power systems, employing the data-driven environmental economic dispatch method for wind-powered power systems as described in any one of claims 1-5, characterized in that, include: The objective optimization model construction module is used to construct a multi-objective optimization model for the environmental and economic dispatch of a power system with wind power, based on the acquired operating parameters of the power grid with wind power, with the objectives of simultaneously minimizing power generation costs and minimizing environmental pollution, and taking into account the actual power grid operation flow. The data-driven module is used to acquire unit operation data, replaces the multi-objective optimization model with a data-driven fuzzy neural network model, and uses knowledge distillation technology to build an online data-driven agent model. The scheduling module is used to solve the online data-driven agent model based on the multi-objective slime mold algorithm. It obtains the global optimal solution of the solved model through the membership function as the basis for optimal scheduling decision to complete the environmental and economic optimization scheduling of the wind power system.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the steps in the data-driven environmental economic dispatch method for wind power systems as described in any one of claims 1-5.

8. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps in the data-driven environmental economic dispatch method for wind power systems as described in any one of claims 1-5.

Images