Wind storage new energy collaborative optimization method

Abstract

The invention provides a wind storage new energy collaborative optimization method, and relates to the technical field of wind storage new energy, and the method comprises the steps: building a grading dynamic quantitative evaluation system for multiple types of wind storage new energy; the method comprises the steps of analyzing transient and steady state active support coupling characteristics between wind storage multi-type new energy and multi-type adjustable and controllable resources, establishing a comprehensive cooperative regulation and control framework of the multi-type adjustable and controllable resources according to an analysis result, and constructing a prediction model oriented to combination of a wind power plant and energy storage according to the comprehensive cooperative regulation and control framework. Carrying out collaborative optimization on active power-frequency and reactive power-voltage to obtain an optimization result; a multi-time-scale active-frequency cooperative control model of inertia response, primary frequency modulation, AGC and the like provided by wind storage combination is established, and collaborative optimization is carried out on the wind storage new energy. According to the wind storage new energy collaborative optimization method provided by the invention, the wind storage new energy is subjected to collaborative optimization, and the stability, flexibility and economical efficiency of a power system are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of wind-storage new energy, and particularly to a method for collaborative optimization of wind-storage new energy. Background Art

[0002] With the adjustment of the global energy structure and the rapid development of clean energy, the proportion of new energy such as wind energy and solar energy in the power system is increasing continuously. New energy has the advantages of being renewable and environmentally friendly, but at the same time, it also has problems such as intermittency, volatility, and uncertainty. In order to cope with these characteristics of new energy power generation, the power system needs to have higher stability and flexibility.

[0003] Intermittency and volatility lead to challenges in grid stability. The power generation output of new energy such as wind energy and solar energy is intermittent and volatile. Traditional power system regulation methods often have difficulty in quickly responding to changes in new energy power generation output, resulting in large fluctuations in grid voltage and frequency; the cost of energy storage technology is high and the utilization rate is low. Energy storage technology is one of the key means to improve the flexibility of the power system, but the current cost of energy storage systems is high, and there is a problem of low utilization rate. Some energy storage projects are idle for a long time due to unreasonable dispatching strategies or imperfect market mechanisms, and cannot give full play to their roles; there is a lack of multi-time scale collaborative control. Traditional new energy regulation methods often only focus on the control effect of a single time scale, such as minute-level or hour-level active-frequency control. The operation of the power system has multi-time scale characteristics, and the control requirements at different time scales need to be considered comprehensively. The lack of multi-time scale collaborative control will lead to a decline in the overall performance of the power system. Summary of the Invention

[0004] The present invention provides a method for collaborative optimization of wind-storage new energy, which collaboratively optimizes wind-storage new energy to improve the stability, flexibility, and economy of the power system.

[0005] The present invention provides a method for collaborative optimization of wind-storage new energy, comprising:

[0006] Establishing a hierarchical dynamic quantitative evaluation system for various types of wind-storage new energy;

[0007] Analyzing the transient and steady-state active support coupling characteristics between various types of wind-storage new energy and various types of controllable resources according to the hierarchical dynamic quantitative evaluation system to obtain an analysis result, wherein the various types of controllable resources include station energy storage, unit energy storage, network-forming wind turbines, and network-following wind turbines;

[0008] Establishing a comprehensive collaborative control architecture for various types of controllable resources according to the analysis result, wherein the comprehensive collaborative control architecture includes between stations, between wind and storage, and between wind turbines for jointly actively supporting frequency and voltage by wind-storage;

[0009] According to the comprehensive collaborative control architecture, a prediction model for the wind farm and energy storage combination is constructed, and the active power - frequency and reactive power - voltage are collaboratively optimized to obtain the optimization results;

[0010] According to the optimization results, a multi - time - scale active power - frequency collaborative control model for the wind - storage combination to provide inertia response, primary frequency regulation, AGC, etc. is established;

[0011] According to the optimization results, a multi - time - scale reactive power - voltage collaborative control model for the wind - storage combination to provide fast voltage regulation, AVC, reactive power regulation, etc. is established;

[0012] According to the active power - frequency collaborative control model and the reactive power - voltage collaborative control model, the wind - storage new energy is collaboratively optimized.

[0013] Furthermore, a hierarchical dynamic quantization evaluation system for various types of wind - storage new energy is established, including:

[0014] Obtain the data of various types of wind - storage new energy and perform pre - processing to obtain the pre - processed data of various types of wind - storage new energy;

[0015] According to the pre - processed data of various types of wind - storage new energy, use Extract the features from the pre - processed data to obtain the key features, where W f (a, b) is the result of wavelet transform, f(t) is the original signal, is the wavelet basis function, a is the scale factor, b is the translation factor, and t is the time variable;

[0016] According to the key features, use Construct an evaluation model, where y i is the output of the i - th neuron, w ij is the weight from the j - th input to the i - th neuron, x j is the j - th input, and c i is the bias of the i - th neuron;

[0017] Use historical data to train the evaluation model and optimize the evaluation model through to obtain the optimized model, where L is the loss function, N represents the number of samples, z m represents the actual value or true label of the m - th sample, represents the predicted value of the m - th sample;

[0018] Use the optimized model to classify various types of wind - storage new energy into different levels, and use to calculate the control boundary values of each level to obtain the hierarchical dynamic quantization evaluation system, where J is the objective function or loss function, K is the number of clusters, and Ck is the index set of the k-th cluster, n is the index variable, and x n is the n-th data point μ k is the center or centroid of the k-th cluster.

[0019] Furthermore, according to the hierarchical dynamic quantization evaluation system, analyze the transient and steady-state active support coupling characteristics between multiple types of new energy sources of wind and energy storage and multiple types of adjustable resources to obtain the analysis results. The multiple types of adjustable resources include substation energy storage, unit energy storage, network-forming wind turbines, and grid-following wind turbines, including:

[0020] Obtain the data of multiple types of adjustable resources and perform preprocessing to obtain the preprocessed data of multiple types of adjustable resources.

[0021] According to the preprocessed data of multiple types of adjustable resources, establish hierarchical evaluation indicators, and the hierarchical evaluation indicators include voltage stability, frequency response speed, and power regulation ability;

[0022] According to the hierarchical evaluation indicators, analyze the transient response characteristics between multiple types of new energy sources of wind and energy storage and multiple types of adjustable resources to obtain the transient response characteristics;

[0023] According to the hierarchical evaluation indicators, analyze the steady-state response characteristics between multiple types of new energy sources of wind and energy storage and multiple types of adjustable resources to obtain the steady-state response characteristics;

[0024] According to the transient response characteristics and the steady-state response characteristics, analyze the active support coupling characteristics between multiple types of new energy sources of wind and energy storage and multiple types of adjustable resources to obtain the analysis results.

[0025] Furthermore, according to the analysis results, establish a comprehensive collaborative control architecture for multiple types of adjustable resources. The comprehensive collaborative control architecture includes between substations, between wind and energy storage, and between wind turbines for jointly actively supporting frequency and voltage, including:

[0026] According to the analysis results, determine the levels of the comprehensive collaborative control architecture;

[0027] According to the levels of the comprehensive collaborative control architecture, establish collaborative control strategies between each level;

[0028] According to the levels of the comprehensive collaborative control architecture, establish a data communication network;

[0029] According to the levels of the comprehensive collaborative control architecture, establish a data integration system for each type of adjustable resource;

[0030] According to the collaborative control strategies, communication network, and data integration, obtain the comprehensive collaborative control architecture for multiple types of adjustable resources.

[0031] Furthermore, according to the integrated collaborative control architecture, a prediction model for the wind farm and energy storage combination is constructed, and the active power - frequency and reactive power - voltage are collaboratively optimized to obtain the optimization results, including:

[0032] According to the integrated collaborative control architecture, the data of the wind farm, energy storage system, and power grid are acquired and pre - processed to obtain the pre - processed data;

[0033] According to the pre - processed data, a time - series analysis algorithm is used to establish a prediction model for the wind farm and energy storage combination;

[0034] Using the prediction model for the wind farm and energy storage combination, the active power - frequency is collaboratively optimized, and the active power outputs of the wind farm and energy storage system are adjusted to obtain the optimization result of the active power - frequency;

[0035] Using the prediction model for the wind farm and energy storage combination, the reactive power - voltage is collaboratively optimized, and the reactive power outputs of the wind farm and energy storage system are adjusted to obtain the optimization result of the reactive power - voltage;

[0036] The optimization results of the active power - frequency and the reactive power - voltage are integrated to obtain the integrated collaborative optimization result for the wind farm and energy storage combination.

[0037] Furthermore, according to the optimization results, a multi - time - scale reactive power - voltage collaborative control model for the wind - storage combination to provide rapid voltage regulation, AVC, reactive power regulation, etc. is established, including:

[0038] According to the optimization results, the reactive power output capacity of the wind farm under different wind speeds and active power output conditions is analyzed to obtain the reactive power characteristics of the wind farm.

[0039] According to the optimization results, the reactive power regulation ability and response speed of the energy storage system are analyzed to obtain the reactive power characteristics of the energy storage system;

[0040] According to the optimization results, the reactive power - voltage characteristics during the combined operation of the wind farm and energy storage system are analyzed to obtain the wind - storage combined characteristics;

[0041] According to the reactive power characteristics of the wind farm, the reactive power characteristics of the energy storage system, and the wind - storage combined characteristics, a rapid voltage regulation control system is established, and the rapid voltage regulation control system is used to adjust the grid voltage in real - time;

[0042] According to the reactive power characteristics of the wind farm, the reactive power characteristics of the energy storage system, and the wind - storage combined characteristics, an automatic voltage control system is constructed, and the automatic voltage control system is used to make minute - level adjustments to the reactive power outputs of the wind farm and energy storage system according to the overall trend and preset target of the grid voltage;

[0043] According to the reactive power characteristics of the wind farm, the reactive power characteristics of the energy storage system, and the combined wind-storage characteristics, a reactive power regulation system is established. The reactive power regulation system is used to perform reactive power regulation on an hourly or longer time scale according to the reactive power demand of the power grid and the operating states of the wind farm and the energy storage system;

[0044] Based on the fast voltage regulation control system, the automatic voltage control system, and the reactive power regulation system, a combined wind-storage multi-time scale reactive power-voltage coordinated control model is established.

[0045] Furthermore, according to the active power-frequency coordinated control model and the reactive power-voltage coordinated control model, the combined wind-storage new energy is coordinated and optimized, including:

[0046] Obtain the real-time and historical data of the wind farm, the energy storage system, and the power grid, and perform preprocessing to obtain the preprocessed data;

[0047] According to the response speeds of the wind farm and the energy storage system and the demands of the power grid, integrate the coordinated optimization strategy into the control systems of the wind farm and the energy storage system;

[0048] According to the real-time state of the power grid and the operating conditions of the wind farm and the energy storage system, dynamically adjust the coordinated optimization strategy.

[0049] On the other hand, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, it implements the combined wind-storage new energy coordinated optimization method as described in any one of the above.

[0050] On the other hand, the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. The computer program is characterized in that when it is executed by a processor, it implements the combined wind-storage new energy coordinated optimization method as described in any one of the above.

[0051] The wind-storage new energy collaborative optimization method provided by this application conducts collaborative optimization of wind-storage new energy through an integrated collaborative control architecture and a prediction model, improving the stability, flexibility, and economy of the power system. Through the integrated collaborative control architecture, this application realizes the collaborative optimization of active power-frequency and reactive power-voltage, which can not only improve the stability of the power system, but also optimize the reactive power distribution, reduce reactive power losses, and improve the economy of power grid operation. This application takes into account the multi-time scale characteristics of power system operation and provides active power-frequency and reactive power-voltage collaborative control at the minute level, hour level, and even longer time scales, which can ensure that the power system maintains good performance at different time scales and improve the overall operation efficiency. Through the integrated collaborative control and prediction model, this application can more accurately predict the changes in new energy power generation output and adjust the operating states of wind farms and energy storage systems in advance, enhancing the active support ability of wind-storage new energy to the power grid and improving the stability and flexibility of the power system. By optimizing the collaborative operation strategy of wind farms and energy storage systems, this application improves the utilization rate of new energy power generation and the grid connection capacity of the power grid, contributing to the large-scale access and consumption of renewable energy and promoting the green transformation of the energy structure. This application may adopt more advanced prediction algorithms and technical means to improve the prediction accuracy of new energy power generation output, providing more reliable data support for the regulation of the power system and ensuring the rationality and effectiveness of the regulation strategy. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0053] Figure 1 It is a flowchart of the wind-storage new energy collaborative optimization method provided by an embodiment of the present invention.

[0054] Figure 2 It is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0055] To make the objectives, technical solutions, and advantages of the present invention clearer, the following will clearly and completely describe the technical solutions in the present invention in conjunction with the drawings in the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. Based on the embodiments in the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

[0056] Figure 1It is a schematic flow chart of the wind-storage new energy collaborative optimization method provided by an embodiment of the present invention.

[0057] As Figure 1 shown, the wind-storage new energy collaborative optimization method provided by an embodiment of the present invention mainly includes the following steps:

[0058] 11. Establish a hierarchical dynamic quantitative evaluation system for various types of wind-storage new energy;

[0059] 12. Analyze the transient and steady-state active support coupling characteristics between various types of wind-storage new energy and various types of controllable resources according to the hierarchical dynamic quantitative evaluation system to obtain an analysis result, where the various types of controllable resources include station energy storage, unit energy storage, network-forming wind turbines, and network-following wind turbines;

[0060] 13. Establish a comprehensive collaborative control architecture for various types of controllable resources according to the analysis result, and the comprehensive collaborative control architecture includes between stations, between wind and storage, and between wind turbines for jointly actively supporting frequency and voltage by wind and storage;

[0061] 14. Build a prediction model for the combination of wind farms and energy storage according to the comprehensive collaborative control architecture, and perform collaborative optimization on active power-frequency and reactive power-voltage to obtain an optimization result;

[0062] 15. Establish a multi-time scale active power-frequency collaborative control model for wind and storage to jointly provide inertia response, primary frequency modulation, AGC, etc. according to the optimization result;

[0063] 16. Establish a multi-time scale reactive power-voltage collaborative control model for wind and storage to jointly provide fast voltage regulation, AVC, reactive power regulation, etc. according to the optimization result;

[0064] 17. Perform collaborative optimization on wind-storage new energy according to the active power-frequency collaborative control model and the reactive power-voltage collaborative control model.

[0065] In the embodiment of the present invention, the wind-storage new energy collaborative optimization method performs collaborative optimization on wind-storage new energy through an integrated collaborative control architecture and a prediction model to improve the stability, flexibility, and economy of the power system. It can achieve collaborative optimization of active power-frequency and reactive power-voltage, provide multi-time-scale active power-frequency and reactive power-voltage collaborative control, thereby enhancing the active support ability of wind-storage new energy to the power grid and promoting the large-scale access and consumption of renewable energy; conduct hierarchical evaluation on various types of wind-storage new energy, consider factors such as the characteristics, scale, and geographical location of different new energy sources, and establish a dynamic quantitative evaluation system, which helps to comprehensively understand the potential and limitations of wind-storage new energy and provides a basis for subsequent optimization control; according to the hierarchical dynamic quantitative evaluation system, analyze the transient and steady-state active support coupling characteristics between various types of wind-storage new energy and various types of controllable resources, which helps to reveal the interaction and influence between different resources and provides a basis for the establishment of an integrated collaborative control architecture; based on the analysis results, establish an integrated collaborative control architecture for various types of controllable resources. The architecture includes collaborative control mechanisms among stations, between wind and storage, and among wind turbines for jointly actively supporting frequency and voltage, so as to achieve optimal allocation and efficient utilization of resources; according to the integrated collaborative control architecture, construct a prediction model for the combination of wind farms and energy storage, which can predict the output of wind farms and energy storage systems and provide data support for the collaborative optimization of active power-frequency and reactive power-voltage. Through a collaborative optimization algorithm, solve the prediction model to obtain the optimization results; according to the optimization results, respectively establish multi-time-scale active power-frequency collaborative control models such as inertia response, primary frequency regulation, and AGC provided jointly by wind and storage, and multi-time-scale reactive power-voltage collaborative control models such as fast voltage regulation, AVC, and reactive power regulation provided jointly by wind and storage, which can achieve precise control of wind-storage new energy at different time scales and improve the stability and flexibility of the power system; according to the active power-frequency collaborative control model and the reactive power-voltage collaborative control model, perform collaborative optimization on wind-storage new energy, and through real-time adjustment of the output of wind farms and energy storage systems, achieve dynamic response and regulation of the power system and improve the utilization rate of renewable energy and the reliability of the power grid.

[0066] As Figure 1 shown, 11. Establish a hierarchical dynamic quantitative evaluation system for various types of wind-storage new energy, including:

[0067] 111. Obtain data of various types of wind-storage new energy and perform preprocessing to obtain preprocessed data of various types of wind-storage new energy;

[0068] 112. According to the preprocessed data of various types of wind-storage new energy, use to extract features from the preprocessed data to obtain key features, where W f (a, b) is the result of wavelet transform, and f(t) is the original signal. is a wavelet basis function, a is the scaling factor, b is the translation factor, and t is the time variable;

[0069] 113. According to the key features, use to construct an evaluation model, where y i is the output of the i-th neuron, w ij is the weight from the j-th input to the i-th neuron, x j is the j-th input, and c i is the bias of the i-th neuron;

[0070] 114. Use historical data to train the evaluation model and optimize the evaluation model through to obtain an optimized model, where L is the loss function, N represents the number of samples, z m represents the actual value or true label of the m-th sample, represents the predicted value of the m-th sample;

[0071] 115. Use the optimized model to classify multiple types of new energy sources of wind and energy storage into different levels, and use to calculate the control boundary values of each level to obtain a hierarchical dynamic quantization evaluation system, where J is the objective function or loss function, K is the number of clusters, C k is the index set of the k-th cluster or cluster, n is the index variable, x n is the n-th data point, and μ k is the center or centroid of the k-th cluster.

[0072] In the embodiments of the present invention, a hierarchical dynamic quantitative evaluation system for multiple types of wind and storage new energy is constructed, which can scientifically and reasonably classify and evaluate new energy based on the characteristics of new energy data, thereby providing strong support for the collaborative optimization of wind and storage new energy; by preprocessing and feature extraction of the original data, noise and redundant information in the data can be eliminated, and key features can be retained, providing high-quality data input for subsequent model construction and training; using machine learning technologies such as neural networks to construct an evaluation model, and training and optimizing the model with historical data, the model can accurately reflect the characteristics of multiple types of wind and storage new energy, providing accurate predictions and judgments for subsequent classification and evaluation; through the optimized model, multiple types of wind and storage new energy are divided into different levels, and the control boundary values of each level are calculated, enabling dynamic and quantitative evaluation of new energy, helping to understand the actual situation and potential of new energy, and providing a scientific basis for the collaborative optimization of wind and storage new energy; the hierarchical dynamic quantitative evaluation system can provide accurate classification and evaluation results for the collaborative optimization of wind and storage new energy, thus helping to formulate more scientific and reasonable collaborative optimization strategies and improving the utilization rate of wind and storage new energy and the stability of the power system; in step 111, original data including wind speed, wind direction, and the charge and discharge status of energy storage devices is obtained from the monitoring system of multiple types of wind and storage new energy, and the original data is preprocessed, such as denoising, normalization, etc., to eliminate outliers and noise in the data and improve data quality; in step 112, signal processing technologies such as wavelet transform are used to extract features from the preprocessed data, select wavelet basis functions, scale factors, and translation factors, perform multi-scale analysis on the signal, and extract key features that can reflect the characteristics of new energy; in step 113, an evaluation model such as a neural network is constructed according to the extracted key features, and parameters such as the number of layers, the number of neurons, and activation functions of the neural network are determined, as well as the weights and biases from input to output; in step 114, historical data is used to train the evaluation model, and the parameters of the model are adjusted through optimization algorithms such as backpropagation, and a loss function is defined, such as mean squared error (MSE), etc., to measure the difference between the predicted value and the actual value of the model. Through iterative training, the model parameters are continuously optimized to make the loss function reach the minimum value, obtaining the optimized model; in step 115, the optimized model is used to classify and evaluate multiple types of wind and storage new energy. According to the output of the model, new energy is divided into different levels, such as high-quality, good, general, etc., and the control boundary values of each level are calculated, such as the threshold of wind speed, the range of the charge and discharge status of energy storage devices, etc., forming a hierarchical dynamic quantitative evaluation system, which can achieve scientific classification and dynamic quantitative evaluation of multiple types of wind and storage new energy and provide strong support for the collaborative optimization of wind and storage new energy.

[0073] Such as Figure 1As shown in the figure, 12. According to the hierarchical dynamic quantization evaluation system, analyze the transient and steady-state active support coupling characteristics between multiple types of new energy sources of wind and energy storage and multiple types of controllable resources, so as to obtain the analysis results. The multiple types of controllable resources include substation energy storage, unit energy storage, network-forming wind turbines and network-following wind turbines, including:

[0074] 121. Obtain the data of multiple types of controllable resources and perform preprocessing to obtain the preprocessed data of multiple types of controllable resources.

[0075] 122. According to the preprocessed data of multiple types of controllable resources, establish hierarchical evaluation indicators, and the hierarchical evaluation indicators include voltage stability, frequency response speed, and power regulation ability;

[0076] 123. According to the hierarchical evaluation indicators, analyze the transient response characteristics between multiple types of new energy sources of wind and energy storage and multiple types of controllable resources to obtain the transient response characteristics;

[0077] 124. According to the hierarchical evaluation indicators, analyze the steady-state response characteristics between multiple types of new energy sources of wind and energy storage and multiple types of controllable resources to obtain the steady-state response characteristics;

[0078] 125. According to the transient response characteristics and the steady-state response characteristics, analyze the active support coupling characteristics between multiple types of new energy sources of wind and energy storage and multiple types of controllable resources to obtain the analysis results.

[0079] In the embodiments of the present invention, the active support coupling characteristics between multiple types of new energy sources of wind power and energy storage and multiple types of adjustable resources can be comprehensively analyzed, providing a scientific basis for the collaborative optimization of wind power and energy storage new energy; by preprocessing the data of multiple types of adjustable resources and establishing hierarchical evaluation indicators, the accuracy and comparability of the data can be ensured, providing a reliable basis for subsequent analysis; by separately analyzing the transient and steady-state response characteristics between multiple types of new energy sources of wind power and energy storage and multiple types of adjustable resources, the interaction and influence between the two under dynamic and static conditions can be deeply understood, providing important information for revealing their active support coupling characteristics; by combining the transient and steady-state response characteristics, comprehensively analyzing the active support coupling characteristics between multiple types of new energy sources of wind power and energy storage and multiple types of adjustable resources, the collaborative relationship and complementary mechanism between the two can be clarified, providing strong support for formulating the collaborative optimization strategy of wind power and energy storage new energy; the analysis results can be used as an important basis for optimization decisions, guiding the reasonable allocation and scheduling of wind power and energy storage new energy and adjustable resources, and improving the stability, flexibility and economy of the power system; in step 121, the original data is obtained from the monitoring systems of multiple types of adjustable resources, including key parameters such as voltage, frequency, power, etc.; the original data is preprocessed, such as denoising, missing value filling, normalization, etc., to eliminate outliers and noise in the data and improve the data quality; in step 122, according to the preprocessed data, hierarchical evaluation indicators are established, including voltage stability, frequency response speed, power regulation ability, etc.; the voltage stability indicator is used to evaluate the stability performance of the system under voltage fluctuations; the frequency response speed indicator is used to measure the response speed of the system to frequency changes; the power regulation ability indicator reflects the system's ability to regulate power demand; in step 123, according to the hierarchical evaluation indicators, the transient response characteristics between multiple types of new energy sources of wind power and energy storage and multiple types of adjustable resources are analyzed; through simulation or measured data, the response speed and stability of new energy and adjustable resources under transient conditions, as well as their interaction and influence, are analyzed; in step 124, according to the hierarchical evaluation indicators, the steady-state response characteristics between multiple types of new energy sources of wind power and energy storage and multiple types of adjustable resources are analyzed; under steady-state conditions, the power output, voltage and frequency stability of new energy and adjustable resources, as well as their influence on the steady-state performance of the system, are analyzed; in step 125, by combining the transient and steady-state response characteristics, the active support coupling characteristics between multiple types of new energy sources of wind power and energy storage and multiple types of adjustable resources are comprehensively analyzed; analyze the complementary mechanism and collaborative relationship between new energy and adjustable resources under transient and steady-state conditions, clarify their active support role in the power system, and how to improve the overall performance of the power system through collaborative optimization; it can comprehensively and deeply analyze the active support coupling characteristics between multiple types of new energy sources of wind power and energy storage and multiple types of adjustable resources, providing a scientific basis and optimization strategy for the collaborative optimization of wind power and energy storage new energy.

[0080] Such as Figure 1As shown in the figure, 13. According to the analysis results, establish an integrated collaborative control architecture for multi-type adjustable resources. The integrated collaborative control architecture includes the inter-station, inter-wind storage, and inter-wind turbine of the wind storage combined active support for frequency and voltage, including:

[0081] 131. According to the analysis results, determine the levels of the integrated collaborative control architecture;

[0082] 132. According to the levels of the integrated collaborative control architecture, establish the collaborative control strategies between each level;

[0083] 133. According to the levels of the integrated collaborative control architecture, establish a data communication network;

[0084] 134. According to the levels of the integrated collaborative control architecture, establish a data integration system for each type of adjustable resource;

[0085] 135. Based on the collaborative control strategy, communication network, and data integration, obtain the integrated collaborative control architecture for multi-type adjustable resources.

[0086] In the embodiments of the present invention, an integrated collaborative control architecture for multi-type adjustable resources can be constructed, which is efficient, flexible and reliable, and can realize the optimal scheduling and collaborative control of multi-type new energy sources such as wind and energy storage and various adjustable resources, improving the overall performance and stability of the power system; by determining the levels of the integrated collaborative control architecture, the effective management and control of resources at different levels can be realized, ensuring the scientificity and rationality of the control strategies; establishing the collaborative control strategies between different levels can realize the optimal complementarity and coordinated cooperation between resources, improving the utilization efficiency and response speed of resources; establishing a stable and efficient data communication network to ensure the real-time transmission and sharing of information between different levels, providing strong technical support for collaborative control; establishing a data integration system for various types of adjustable resources can realize the comprehensive monitoring and data analysis of resource status, providing accurate information support for control decisions; by integrating the collaborative control strategies, communication network and data integration system, a complete integrated collaborative control architecture for multi-type adjustable resources can be constructed to realize the comprehensive optimization and intelligent control of the power system; in step 131, according to the analysis results, clarify the hierarchical structure of the integrated collaborative control architecture, including the top decision-making layer, the middle coordination layer and the bottom execution layer; the top decision-making layer is responsible for formulating global control strategies and objectives; the middle coordination layer is responsible for coordinating the cooperation and optimization between various resources; the bottom execution layer is responsible for specific resource control and operations; in step 132, according to the levels of the integrated collaborative control architecture, establish the collaborative control strategies between different levels; the top decision-making layer formulates global control objectives and strategies, such as the overall output plan of the wind farm and the energy storage system; the middle coordination layer coordinates the cooperation between various resources according to the top-level strategy, such as adjusting the output ratio of the wind farm and the energy storage system to ensure the stability of the power system; the bottom execution layer controls and operates specific resources according to the instructions of the middle coordination layer, such as adjusting the rotation speed of the fan or the charge and discharge state of the energy storage system; in step 133, according to the levels of the integrated collaborative control architecture, establish a stable and efficient data communication network; determine the topological structure and communication protocol of the communication network to ensure the real-time transmission and sharing of information between different levels; adopt reliable communication equipment and technologies to improve the stability and reliability of the communication network; in step 134, according to the levels of the integrated collaborative control architecture, establish a data integration system for various types of adjustable resources; conduct unified data collection, storage and management of various types of adjustable resources, and establish a data integration platform or database; extract valuable information through data analysis and mining technologies to provide support for control decisions; in step 135, according to the collaborative control strategies, communication network and data integration system, construct an integrated collaborative control architecture for multi-type adjustable resources; organically integrate each level, each resource and each system together to form a complete, coordinated and efficient control system; through real-time monitoring, analysis and optimization, realize the comprehensive optimization and intelligent control of the power system, improving the overall performance and stability of the power system;An efficient, flexible, and reliable integrated collaborative control architecture for multi-type adjustable resources can be constructed to provide strong support for the collaborative optimization of wind-storage new energy.

[0087] As Figure 1 shown, 14. According to the integrated collaborative control architecture, a prediction model for the combination of wind farms and energy storage is constructed, and the active power-frequency and reactive power-voltage are collaboratively optimized to obtain the optimization results, including:

[0088] 141. According to the integrated collaborative control architecture, obtain the data of wind farms, energy storage systems, and power grids, and perform preprocessing to obtain the preprocessed data;

[0089] 142. According to the preprocessed data, use the time series analysis algorithm to establish a prediction model for the combination of wind farms and energy storage;

[0090] 143. Use the prediction model for the combination of wind farms and energy storage to collaboratively optimize the active power-frequency, adjust the active power output of wind farms and energy storage systems, and obtain the optimized result of active power-frequency;

[0091] 144. Use the prediction model for the combination of wind farms and energy storage to collaboratively optimize the reactive power-voltage, adjust the reactive power output of wind farms and energy storage systems, and obtain the optimized result of reactive power-voltage;

[0092] 145. Integrate the optimized results of active power-frequency and reactive power-voltage to obtain the integrated collaborative optimization result for the combination of wind farms and energy storage.

[0093] In the embodiments of the present invention, the joint collaborative optimization of a wind farm and an energy storage system can be realized, significantly improving the operation efficiency and stability of the power system; by preprocessing the data of the wind farm, the energy storage system, and the power grid, and establishing a prediction model for the wind farm and energy storage joint, an accurate data basis and reliable prediction support can be provided for subsequent collaborative optimization; by adjusting the active power output of the wind farm and the energy storage system, the collaborative optimization of active power-frequency can be realized, ensuring the frequency stability of the power system, improving the active power regulation ability and response speed of the system; by adjusting the reactive power output of the wind farm and the energy storage system, the collaborative optimization of reactive power-voltage can be realized, ensuring the voltage stability of the power system, improving the reactive power compensation ability and voltage quality of the system; by integrating the active power-frequency optimization results and the reactive power-voltage optimization results, the comprehensive collaborative optimization results for the wind farm and energy storage joint can be obtained, comprehensively improving the operation efficiency, stability, and economy of the power system, and realizing the efficient utilization of wind and storage new energy; in step 141, the original data is obtained from data sources such as the wind farm, the energy storage system, and the power grid, including key parameters such as wind speed, fan status, energy storage device status, power grid voltage, and frequency; the original data is preprocessed, such as data cleaning, data normalization, data synchronization, etc., to obtain the preprocessed data; in step 142, according to the preprocessed data, a prediction model for the wind farm and energy storage joint is established using time series analysis algorithms; the wind speed and fan output of the wind farm, as well as the charge and discharge status and output of the energy storage system, can be accurately predicted, providing reliable prediction support for subsequent collaborative optimization; in step 143, the prediction model for the wind farm and energy storage joint is used to conduct collaborative optimization of the active power-frequency of the power system; according to the prediction results and the actual requirements of the power system, the active power output of the wind farm and the energy storage system is adjusted to ensure that the frequency of the power system is stable within the qualified range of active power-frequency response; through iterative optimization algorithms, the optimal active power output combination is found to obtain the active power-frequency optimization results; in step 144, the prediction model for the wind farm and energy storage joint is used to conduct collaborative optimization of the reactive power-voltage of the power system; according to the prediction results and the actual requirements of the power system, the reactive power output of the wind farm and the energy storage system is adjusted to ensure that the voltage of the power system is stable within the qualified range of reactive power-voltage response; the same iterative optimization algorithm is also used to find the optimal reactive power output combination to obtain the reactive power-voltage optimization results; in step 145, the active power-frequency optimization results and the reactive power-voltage optimization results are integrated to obtain the comprehensive collaborative optimization results for the wind farm and energy storage joint; considering the collaborative optimization effects of active power and reactive power, as well as the overall operation efficiency and stability of the power system, the optimal control strategy is formulated; the control strategy is sent to the wind farm and the energy storage system to guide their actual output adjustment and control, realizing the efficient utilization of wind and storage new energy and the optimized operation of the power system;It can achieve the joint and collaborative optimization of the wind farm and the energy storage system, improve the operation efficiency and stability of the power system, and provide strong support for the wide application of wind-storage new energy and the sustainable development of the power system.

[0094] As Figure 1 shown, 15. According to the optimization results, establish a multi-time scale reactive power-voltage collaborative control model for the wind-storage joint to provide rapid voltage regulation, AVC, reactive power regulation, etc., including:

[0095] 151. According to the optimization results, analyze the reactive power output capacity of the wind farm under different wind speeds and active power output conditions to obtain the reactive power characteristics of the wind farm.

[0096] 152. According to the optimization results, analyze the reactive power regulation ability and response speed of the energy storage system to obtain the reactive power characteristics of the energy storage system;

[0097] 153. According to the optimization results, analyze the reactive power-voltage characteristics during the joint operation of the wind farm and the energy storage system to obtain the wind-storage joint characteristics;

[0098] 154. According to the reactive power characteristics of the wind farm, the reactive power characteristics of the energy storage system, and the wind-storage joint characteristics, establish a rapid voltage regulation control system, and the rapid voltage regulation control system is used to adjust the grid voltage in real time;

[0099] 155. According to the reactive power characteristics of the wind farm, the reactive power characteristics of the energy storage system, and the wind-storage joint characteristics, construct an automatic voltage control system, and the automatic voltage control system is used to make minute-level adjustments to the reactive power output of the wind farm and the energy storage system according to the overall trend and preset target of the grid voltage;

[0100] 156. According to the reactive power characteristics of the wind farm, the reactive power characteristics of the energy storage system, and the wind-storage joint characteristics, establish a reactive power regulation system, and the reactive power regulation system is used to perform reactive power regulation on an hourly or longer time scale according to the reactive power demand of the grid and the operating states of the wind farm and the energy storage system;

[0101] 157. According to the rapid voltage regulation control system, the automatic voltage control system, and the reactive power regulation system, establish a wind-storage joint multi-time scale reactive power-voltage collaborative control model.

[0102] In the embodiment of the present invention, the effect

[0103] By performing this series of steps, a complete wind-storage integrated multi-time scale reactive power-voltage coordinated control model can be established, which can give full play to the advantages of wind farms and energy storage systems in reactive power regulation, achieve precise control and optimization of the grid voltage, and improve the stability and operation efficiency of the power system; through in-depth analysis of the reactive power-voltage characteristics of wind farms, energy storage systems, and during combined operation, the reactive power output capacity and response speed under different conditions can be accurately grasped, providing a scientific basis for the subsequent design of the control system; the established fast voltage regulation control system can monitor the grid voltage in real time and respond quickly to adjust the voltage in real time, effectively coping with the instantaneous fluctuations of the grid voltage and ensuring voltage stability; the automatic voltage control system can adjust the reactive power output of wind farms and energy storage systems at the minute level according to the overall trend and preset goals of the grid voltage, achieving fine control of the voltage and improving the voltage quality; the reactive power regulation system can perform reactive power regulation at the hour level or longer time scale according to the reactive power demand of the grid and the operating status of wind farms and energy storage systems, optimize the reactive power distribution, reduce reactive power losses, and improve the economy of the power system; the finally established wind-storage integrated multi-time scale reactive power-voltage coordinated control model can integrate the functions of each control system, realize multi-time scale reactive power-voltage coordinated control, and improve the overall stability and operation efficiency of the power system; in step 151, according to the optimization results, analyze the reactive power output capacity of the wind farm under different wind speeds and active power output conditions to obtain the reactive power characteristics of the wind farm.This includes analyzing the impact of wind speed changes on the reactive power output of the wind farm and the variation law of reactive power output during active power adjustment; in step 152, according to the optimization results, analyze the reactive power regulation ability and response speed of the energy storage system to obtain the reactive power characteristics of the energy storage system, including evaluating indicators such as the reactive power regulation range, regulation speed, and accuracy of the energy storage system; in step 153, according to the optimization results, analyze the reactive power-voltage characteristics during the combined operation of the wind farm and the energy storage system to obtain the wind-storage combined characteristics, including studying the reactive power output and voltage response characteristics of the wind farm and the energy storage system under different combination modes, as well as their mutual influence and coordination mechanism; in step 154, based on the reactive power characteristics of the wind farm, the reactive power characteristics of the energy storage system, and the wind-storage combined characteristics, establish a fast voltage regulation control system that can monitor the grid voltage in real time and quickly adjust the reactive power output of the wind farm and the energy storage system according to the voltage fluctuation situation to stabilize the voltage; in step 155, construct an automatic voltage control system that can formulate a minute-level reactive power regulation plan according to the overall trend and preset target of the grid voltage and achieve fine voltage regulation through the control of the wind farm and the energy storage system; in step 156, establish a reactive power regulation system that can formulate a reactive power regulation strategy on an hourly or longer time scale according to the reactive power demand of the grid and the operating status of the wind farm and the energy storage system to optimize the reactive power distribution and reduce the reactive power loss; in step 157, a wind-storage combined multi-time scale reactive power-voltage coordinated control model that can integrate the functions of each control system to achieve multi-time scale reactive power-voltage coordinated control. The specific steps include: formulating a coordinated control strategy to clarify the responsibilities and coordination mechanism of each control system; establishing an information sharing platform to realize data exchange and information sharing among each control system; conducting simulation tests and verification to ensure the effectiveness and reliability of the coordinated control model. A complete set of wind-storage combined multi-time scale reactive power-voltage coordinated control models can be established to provide strong support for the stable operation and optimization of the power system.

[0104] As Figure 1 shown, 16. According to the active power-frequency coordinated control model and the reactive power-voltage coordinated control model, conduct coordinated optimization of the wind-storage new energy, including:

[0105] 161. Obtain the real-time and historical data of the wind farm, the energy storage system, and the power grid, and perform preprocessing to obtain the preprocessed data;

[0106] 162. Integrate the coordinated optimization strategy into the control systems of the wind farm and the energy storage system according to the response speeds of the wind farm and the energy storage system and the requirements of the power grid;

[0107] 163. Dynamically adjust the coordinated optimization strategy according to the real-time state of the power grid and the operating conditions of the wind farm and the energy storage system.

[0108] In the embodiments of the present invention, efficient collaborative optimization operation among a wind farm, an energy storage system, and a power grid can be achieved to improve the overall performance of the power system. By preprocessing the real-time and historical data of the wind farm, the energy storage system, and the power grid, noise and outliers in the data can be eliminated, improving the accuracy and reliability of the data. At the same time, integrating these data into a unified platform provides a solid foundation for subsequent analysis and optimization. According to the response speeds of the wind farm and the energy storage system and the demands of the power grid, integrating the collaborative optimization strategy into the control systems of the wind farm and the energy storage system can achieve coordinated cooperation between the wind farm and the energy storage system, improving their response speeds and accuracies to the demands of the power grid, thereby optimizing the operation of the power system. By real-time monitoring the state of the power grid and the operation conditions of the wind farm and the energy storage system, dynamically adjusting the collaborative optimization strategy can ensure that the strategy always matches the actual situation of the power system, promptly responds to various changes and challenges, and improves the stability and flexibility of the power system. In step 161, real-time and historical data are obtained from data sources such as the wind farm, the energy storage system, and the power grid. These data include key parameters such as wind speed, fan status, energy storage device status, power grid voltage, current, and frequency. The obtained data is preprocessed, including data cleaning, data normalization, and data synchronization. The preprocessed data will be used for subsequent analysis and optimization. In step 162, analyze the response speeds of the wind farm and the energy storage system to understand their regulation capabilities and limiting conditions. At the same time, evaluate the demands of the power grid, including aspects such as load changes, voltage stability, and frequency control. According to the response speeds of the wind farm and the energy storage system and the demands of the power grid, design a collaborative optimization strategy that can give full play to the advantages of the wind farm and the energy storage system, achieve coordinated cooperation between them, and meet the demands of the power grid. Integrate the designed collaborative optimization strategy into the control systems of the wind farm and the energy storage system, including modifying the algorithms, parameter settings, and interfaces of the control systems to ensure that the strategy can be effectively implemented in actual operation. In step 163, real-time monitor the state of the power grid and the operation conditions of the wind farm and the energy storage system. This includes monitoring key parameters such as the voltage, current, and frequency of the power grid, as well as the wind speed, fan output, and charge-discharge status of the energy storage system of the wind farm. According to the monitored real-time data, analyze the current state and trends of the power system, including evaluating aspects such as the load changes, voltage stability, and frequency deviation of the power grid, as well as the operation conditions and regulation capabilities of the wind farm and the energy storage system. According to the analysis results, dynamically adjust the collaborative optimization strategy, including adjusting the output plans of the wind farm and the energy storage system, modifying the parameter settings of the control system, and optimizing the coordinated cooperation mechanism. By dynamically adjusting the strategy, it can be ensured that the power system always operates in an optimal state, improving the overall performance and stability. Efficient collaborative optimization operation among the wind farm, the energy storage system, and the power grid can be achieved, providing strong support for the sustainable development of the power system and the efficient utilization of new energy.

[0109] Figure 2 It is a schematic structural diagram of an electronic device provided by an embodiment of the present invention.

[0110] As Figure 2 shown, the electronic device may include: a processor 610, a communications interface 620, a memory 630, and a communication bus 640. Among them, the processor 610, the communications interface 620, and the memory 630 complete mutual communication through the communication bus 640. The processor 610 may call the logical instructions in the memory 630 to execute the wind-storage new energy collaborative optimization method.

[0111] In addition, when the logical instructions in the above-mentioned memory 630 are implemented in the form of software function units and sold or used as an independent product, they may be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, may be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The foregoing storage medium includes: USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs, and other various media that can store program codes.

[0112] On the other hand, the present invention also provides a computer program product. The computer program product includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the wind-storage new energy collaborative optimization method provided by the above-mentioned various methods.

[0113] On yet another aspect, the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it is implemented to execute the wind-storage new energy collaborative optimization method provided by the above-mentioned various methods.

[0114] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated. The components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative labor.

[0115] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0116] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A wind energy storage new energy collaborative optimization method, characterized in that: include: Establish a hierarchical dynamic quantitative evaluation system for wind and storage multi-type renewable energy; According to the hierarchical dynamic quantitative evaluation system, the transient and steady-state active support coupling characteristics between multiple types of wind energy storage and multiple types of adjustable resources are analyzed to obtain analysis results. The multiple types of adjustable resources include station energy storage, unit energy storage, grid-type wind turbines and grid-following wind turbines. According to the analysis results, a comprehensive coordinated control framework for multiple types of controllable resources is established, including the sites, wind and storage, and wind turbines that jointly actively support the frequency and voltage of wind and storage resources; Based on the comprehensive coordinated control framework, a prediction model for the combination of wind farms and energy storage is constructed, and active power-frequency and reactive power-voltage are coordinated to obtain the optimized results; According to the optimization results, a multi-time scale active power-frequency coordinated control model is established in which wind and storage jointly provide inertia response, primary frequency regulation, AGC, etc. According to the optimization results, a multi-time scale reactive power-voltage coordinated control model is established to jointly provide rapid voltage regulation, AVC, reactive power regulation, etc. Based on the active power-frequency coordinated control model and the reactive power-voltage coordinated control model, wind energy storage and renewable energy are coordinated and optimized.

2. The wind energy storage and new energy collaborative optimization method according to claim 1 is characterized in that: Establish a hierarchical dynamic quantitative evaluation system for wind and energy storage and other types of renewable energy, including: Acquire data of wind-storage multi-type renewable energy, and perform preprocessing to obtain preprocessed wind-storage multi-type renewable energy data; According to the pre-processed wind and storage multi-type renewable energy data, use Feature extraction is performed on the preprocessed data to obtain key features, where: is the result of wavelet transform, is the original signal, is the wavelet basis function, is the scale factor, is the translation factor, is a time variable; According to the key characteristics, use Construct an evaluation model, where For the The output of a neuron, It is from Input to the The weight of a neuron, It is Inputs, It is The bias of each neuron; Use historical data to train the evaluation model, The evaluation model is optimized to obtain an optimized model, where: is the loss function, represents the number of samples, Indicates The actual value or true label of the samples, Indicates The predicted value of samples; Using the optimized model, wind and storage multi-type renewable energy are divided into different levels, and Calculate the control boundary values ​​of each level to obtain a hierarchical dynamic quantitative evaluation system, where: is the objective function or loss function, is the number of clusters, It is A set of indices of clusters or clusters, is the index variable, It is Data points It is The center or centroid of a cluster.

3. The wind energy storage and new energy collaborative optimization method according to claim 1 is characterized in that: According to the hierarchical dynamic quantitative evaluation system, the transient and steady-state active support coupling characteristics between wind energy storage multi-type new energy and multi-type adjustable resources are analyzed to obtain the analysis results. The multi-type adjustable resources include station energy storage, unit energy storage, grid-type wind turbines and grid-following wind turbines, including: Acquire data of multiple types of adjustable resources, and perform preprocessing to obtain preprocessed data of multiple types of adjustable resources; Establishing hierarchical evaluation indicators based on the preprocessed multi-type controllable resource data, wherein the hierarchical evaluation indicators include voltage stability, frequency response speed, and power regulation capability; According to the hierarchical evaluation indicators, the transient response characteristics between wind and storage multi-type new energy and multi-type adjustable resources are analyzed to obtain the transient response characteristics; According to the hierarchical evaluation indicators, the steady-state response characteristics between wind and storage multi-type new energy and multi-type adjustable resources are analyzed to obtain the steady-state response characteristics; According to the transient response characteristics and steady-state response characteristics, the active support coupling characteristics between multiple types of new energy sources such as wind and storage and multiple types of adjustable resources are analyzed to obtain the analysis results.

4. The wind energy storage and new energy collaborative optimization method according to claim 1 is characterized in that: According to the analysis results, a comprehensive coordinated control framework for multiple types of controllable resources is established. The comprehensive coordinated control framework includes the stations, wind storage rooms, and wind turbine rooms that actively support the frequency and voltage of wind and storage units, including: According to the analysis results, determine the level of the comprehensive coordinated control framework; According to the levels of the comprehensive collaborative control framework, establish collaborative control strategies among different levels; Establish a data communication network according to the level of the comprehensive collaborative control architecture; According to the level of the comprehensive collaborative control framework, establish a data integration system for various types of controllable resources; Based on collaborative control strategies, communication networks and data integration, a comprehensive collaborative control architecture for multiple types of controllable resources is obtained.

5. The wind energy storage and new energy collaborative optimization method according to claim 1 is characterized in that: Based on the comprehensive coordinated control framework, a prediction model for the combination of wind farms and energy storage is constructed, and active power-frequency and reactive power-voltage are coordinated optimized to obtain the optimization results, including: According to the comprehensive coordinated control framework, wind farm, energy storage system and power grid data are acquired and preprocessed to obtain preprocessed data; Based on the preprocessed data, a prediction model for the combination of wind farms and energy storage is established using a time series analysis algorithm; Use a prediction model for the combination of wind farms and energy storage to coordinately optimize active power and frequency, and adjust the active power output of wind farms and energy storage systems to obtain an optimized active power and frequency result; Use a forecasting model for wind farms and energy storage systems to coordinate reactive power and voltage optimization, adjust the reactive power output of wind farms and energy storage systems, and obtain the optimal reactive power and voltage results. The active-frequency optimization results and reactive-voltage optimization results are integrated to obtain a comprehensive collaborative optimization result for the combination of wind farms and energy storage.

6. The wind energy storage and new energy collaborative optimization method according to claim 1 is characterized in that: According to the optimization results, a multi-time scale reactive power-voltage coordinated control model is established in which wind and storage jointly provide rapid voltage regulation, AVC, reactive power regulation, etc., including: According to the optimization results, the reactive output capacity of the wind farm under different wind speeds and active output conditions is analyzed to obtain the reactive characteristics of the wind farm; According to the optimization results, the reactive power regulation capability and response speed of the energy storage system are analyzed to obtain the reactive power characteristics of the energy storage system; According to the optimization results, the reactive power-voltage characteristics of the wind farm and energy storage system when they are operated together are analyzed to obtain the wind-storage joint characteristics; According to the reactive characteristics of the wind farm, the reactive characteristics of the energy storage system, and the wind-storage joint characteristics, a rapid voltage regulation control system is established, and the rapid voltage regulation control system is used to adjust the grid voltage in real time; According to the reactive characteristics of the wind farm, the reactive characteristics of the energy storage system, and the wind-storage joint characteristics, an automatic voltage control system is constructed. The automatic voltage control system is used to adjust the reactive output of the wind farm and the energy storage system in minutes according to the overall trend of the grid voltage and the preset target; According to the reactive characteristics of the wind farm, the reactive characteristics of the energy storage system, and the wind-storage joint characteristics, a reactive regulation system is established, wherein the reactive regulation system is used to perform reactive regulation on an hourly or longer time scale according to the reactive demand of the power grid and the operating status of the wind farm and the energy storage system; According to the rapid voltage regulation control system, automatic voltage control system and reactive power regulation system, a wind-storage joint multi-time scale reactive power-voltage coordinated control model is established.

7. The wind energy storage and new energy collaborative optimization method according to claim 1 is characterized in that: According to the active-frequency coordinated control model and reactive-voltage coordinated control model, wind-storage renewable energy is coordinated and optimized, including: Acquire real-time and historical data of wind farms, energy storage systems, and power grids, and preprocess them to obtain preprocessed data; Integrate collaborative optimization strategies into the control systems of wind farms and energy storage systems based on their response speed and the needs of the power grid; Dynamically adjust the collaborative optimization strategy based on the real-time status of the power grid and the operating conditions of wind farms and energy storage systems.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the wind energy storage and new energy collaborative optimization method as described in any one of claims 1 to 7 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the wind energy storage and new energy collaborative optimization method as described in any one of claims 1 to 7 is implemented.

Images