Wind power plant hybrid energy storage optimization method, system and device and storage medium

Abstract

The invention discloses a wind power plant hybrid energy storage optimization method, system and device and a storage medium, and relates to the technical field of new energy power generation and energy storage optimization, and the method comprises the steps: collecting the historical operation data of a wind power plant, constructing a wind power fluctuation characteristic model, and determining the preliminary energy storage demand of the wind power plant; based on the preliminary energy storage demand, constructing a multi-objective optimization model, and determining an optimal capacity matching scheme of each type of energy storage device in hybrid energy storage; and based on the optimal capacity matching scheme, establishing a dynamic optimization energy storage charging and discharging strategy. According to the method, the historical operation data of the wind power plant are collected, and the wind power fluctuation characteristic model is constructed, so that the energy storage demand is accurately identified, and the pertinence and adaptability of configuration are improved; cooperative configuration of different types of energy storage devices is realized, and the problem of capacity redundancy or insufficient response is avoided. Through a dynamic optimization charging and discharging strategy established based on a capacity matching scheme, the energy storage operation efficiency and the stability of wind power integration are improved.

Description

Technical Field

[0001] This invention relates to the field of new energy power generation and energy storage optimization technology, specifically to a method, system, equipment and storage medium for optimizing hybrid energy storage in wind farms. Background Technology

[0002] With the rapid development of renewable energy, wind power is playing an increasingly important role in the global energy structure, becoming a key force in promoting the low-carbon transformation of energy. However, wind power is inherently an intermittent and highly volatile power source, its output heavily dependent on weather conditions and geographical location, making it difficult to stably participate in grid load balancing and peak shaving tasks. To improve the controllability and availability of wind power, more and more research and engineering practices are introducing energy storage technology to mitigate the impact of wind power fluctuations on the safe operation of the power grid. Energy storage can not only realize the time transfer of electricity, but also be used for peak shaving and valley filling, improving the accuracy of wind power forecasts and the matching degree between actual power, thereby enhancing the flexibility and stability of wind power grid connection.

[0003] Currently, energy storage technologies applied in wind farms mainly include electrochemical energy storage (such as lithium-ion batteries and sodium-sulfur batteries), mechanical energy storage (such as flywheel energy storage), electromagnetic energy storage (such as supercapacitors), and thermal energy storage. Different energy storage technologies exhibit significant differences in charge / discharge rates, cycle life, energy density, and response time. Therefore, under complex wind conditions, a single type of energy storage is insufficient to meet the multi-dimensional regulation needs of wind farms. In recent years, the application of hybrid energy storage in wind power integration has been continuously advancing, and corresponding configuration strategies, capacity optimization, and dispatch control methods have gradually become research hotspots. The rationality of the hybrid energy storage system configuration directly affects the overall operating efficiency and investment benefits of the wind farm. Therefore, optimizing the configuration of hybrid energy storage capacity ratios and formulating operating strategies adapted to wind power characteristics have become important directions for integrated regulation and intelligent optimization in the wind power field.

[0004] Although some research has explored hybrid energy storage configuration strategies, several technical bottlenecks remain, limiting their widespread application in actual wind farms. First, in terms of energy storage demand assessment, most existing technologies rely on empirical configurations based on single statistical indicators (such as maximum wind power fluctuations and prediction bias), lacking the ability to systematically construct wind power fluctuation characteristic models. This makes it difficult to accurately reflect the diversity of energy storage demand across time scales, frequency components, and dynamic response dimensions. Second, existing optimization models typically use cost or a single performance indicator as the objective function, failing to fully consider the synergistic effect of power matching capability and capacity response capability. This leads to unbalanced capacity allocation, with some energy storage devices operating inefficiently or even redundantly. Furthermore, in terms of charging and discharging strategy formulation, most methods employ static settings or fixed-rule-based strategy generation mechanisms, making it difficult to dynamically adapt to real-time changes in wind power. This results in lag in the response of energy storage systems, low regulation efficiency, and severely restricts the realization of the value of energy storage systems. Summary of the Invention

[0005] In view of the above-mentioned problems, the present invention is proposed.

[0006] Therefore, the technical problem solved by this invention is: the existing wind farm hybrid energy storage configuration has problems such as inaccurate energy storage demand assessment, unreasonable capacity ratio and lag in scheduling strategy response, and how to achieve accurate modeling and dynamic optimization of energy storage configuration and scheduling strategy.

[0007] To address the aforementioned technical problems, this invention provides the following technical solution: a method for optimizing hybrid energy storage in wind farms, comprising collecting historical operating data of wind farms, constructing a wind power fluctuation characteristic model, and determining the initial energy storage requirements of wind farms; based on the initial energy storage requirements, constructing a multi-objective optimization model, and determining the optimal capacity ratio scheme for each type of energy storage device in hybrid energy storage; and based on the optimal capacity ratio scheme, establishing a dynamic optimization energy storage charging and discharging strategy.

[0008] As a preferred embodiment of the wind farm hybrid energy storage optimization method described in this invention, the historical operating data of the wind farm includes historical power output data of wind turbine generators, operating status data of wind turbine generators, and environmental data of the wind farm.

[0009] As a preferred embodiment of the wind farm hybrid energy storage optimization method described in this invention, the construction of the wind power fluctuation characteristic model includes: preprocessing the historical output power data of the wind turbine generator, and calculating the power fluctuation amplitude and frequency distribution characteristics based on the preprocessed data to obtain the wind farm power fluctuation characteristics.

[0010] As a preferred embodiment of the wind farm hybrid energy storage optimization method described in this invention, the step of determining the preliminary energy storage requirements of the wind farm includes determining the target range of allowable power fluctuations of the wind farm based on the power fluctuation characteristics of the wind farm.

[0011] Based on the target range, the maximum charging and discharging power and continuous discharge time required by the energy storage device under the peak state of wind power fluctuation are calculated to obtain the preliminary energy storage power and capacity requirement range.

[0012] As a preferred embodiment of the wind farm hybrid energy storage optimization method described in this invention, the construction of the multi-objective optimization model includes: extracting the performance parameters of the energy storage device based on the preliminary energy storage power and capacity demand range, taking the power matching capability and capacity coverage capability of the energy storage device as optimization objectives, and establishing a multi-objective optimization model with power satisfaction and capacity satisfaction as objective functions.

[0013] As a preferred embodiment of the wind farm hybrid energy storage optimization method described in this invention, the step of determining the optimal capacity ratio scheme for each type of energy storage device in the hybrid energy storage includes: discretizing the solution space of the multi-objective optimization model, using the capacity ratio of different types of energy storage devices as decision variables, employing a heuristic search algorithm to iteratively calculate the capacity ratio combination of each energy storage type, evaluating the fitness based on the objective functions of power coverage and capacity coverage, and selecting the capacity ratio solution with the best comprehensive fitness as the optimal scheme.

[0014] As a preferred embodiment of the wind farm hybrid energy storage optimization method described in this invention, the establishment of a dynamic optimization energy storage charging and discharging strategy includes: constructing a mathematical model for energy storage power regulation based on the optimal capacity ratio scheme, taking the wind power prediction value and the energy storage response state as input quantities, and outputting charging and discharging power commands for various types of energy storage.

[0015] Based on the model predictive control method, a rolling optimization time window is set, and the charging and discharging power allocation of various energy storage devices is dynamically adjusted according to the wind power prediction error and the actual load deviation in each control cycle, forming a real-time adjustable dynamic charging and discharging strategy.

[0016] Another objective of this invention is to provide a wind farm hybrid energy storage optimization system, which solves the problems of unreasonable energy storage configuration and delayed dispatch response through the coordinated work of an energy storage demand identification module, a capacity optimization calculation module, and a charging and discharging strategy control module.

[0017] As a preferred embodiment of the wind farm hybrid energy storage optimization system described in this invention, it includes: an energy storage demand identification module, a capacity optimization calculation module, and a charging / discharging strategy control module; the energy storage demand identification module includes a wind power data acquisition unit and a power fluctuation modeling unit. The wind power data acquisition unit is used to collect historical output power, operating status, and environmental information of wind turbine generators to provide raw data for subsequent modeling. The power fluctuation modeling unit is used to calculate the amplitude and frequency distribution characteristics of wind power fluctuations based on the collected data, output wind farm power fluctuation parameters, and estimate the preliminary energy storage capacity and power demand range; the capacity optimization calculation module includes an optimization model construction unit and a capacity ratio solution unit. The optimization model construction unit constructs a multi-objective optimization model with power coverage and capacity coverage as objective functions based on the preliminary energy storage requirements and energy storage device performance parameters. The capacity allocation solution unit adopts a heuristic search algorithm to traverse different types of energy storage capacity combinations, calculates the fitness, and outputs the optimal capacity allocation scheme. The charging and discharging strategy control module includes a scheduling model construction unit and a dynamic strategy optimization unit. The scheduling model construction unit constructs a scheduling control model with wind power prediction and energy storage status as inputs and charging and discharging power as outputs. The dynamic strategy optimization unit updates the charging and discharging commands of various types of energy storage in real time based on the rolling prediction mechanism and control feedback, so as to realize the dynamic optimization and adjustment of the strategy.

[0018] A computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement a method for optimizing hybrid energy storage in wind farms.

[0019] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of a method for optimizing hybrid energy storage in wind farms.

[0020] The beneficial effects of this invention are as follows: By collecting historical operating data of wind farms and constructing a wind power fluctuation characteristic model, accurate identification of energy storage demand is achieved, avoiding errors caused by traditional empirical configuration methods and improving the pertinence and adaptability of configuration; by constructing a multi-objective optimization model based on power matching degree and capacity coverage, collaborative configuration of different types of energy storage devices is realized, improving system regulation efficiency and avoiding problems of capacity redundancy or insufficient response; by establishing a dynamic optimization charging and discharging strategy based on the capacity matching scheme, real-time response and intelligent control of the energy storage system to wind power fluctuations are realized, improving energy storage operation efficiency and the stability of wind power grid connection. Attached Figure Description

[0021] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 The first embodiment of the present invention provides an overall flowchart of a wind farm hybrid energy storage optimization method.

[0023] Figure 2 The following is an overall flowchart of a wind farm hybrid energy storage optimization system provided for the second embodiment of the present invention. Detailed Implementation

[0024] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0025] Example 1, referring to Figure 1 As an embodiment of the present invention, a method for optimizing hybrid energy storage in wind farms is provided, comprising: S1: Collect historical operating data of wind farms, construct a wind power fluctuation characteristic model, and determine the preliminary energy storage requirements of wind farms.

[0026] Furthermore, historical operating data of wind farms includes historical power output data of wind turbine units, operating status data of wind turbine units, and environmental data of wind farms.

[0027] Furthermore, constructing a wind power fluctuation characteristic model includes preprocessing historical power output data of wind turbine units, and calculating the power fluctuation amplitude and frequency distribution characteristics based on the preprocessed data to obtain the wind farm power fluctuation characteristics.

[0028] It should be noted that the collected historical power output data of wind turbines were preprocessed to remove outliers and missing values, and the time step and unit were standardized to obtain a cleaned effective power data sequence. .

[0029] Normalized power sequences were analyzed using a sliding window. The local maximum fluctuation amplitude is obtained by expressing the fluctuation amplitude function as follows: , in, Indicates time The local fluctuation amplitude of the power output per unit capacity of the wind farm. This indicates the wind turbine unit at time point after normalization preprocessing. The active power output value, This represents the half-width of the sliding window, used to limit the length of the local analysis interval.

[0030] The frequency distribution characteristics are represented as follows: , in, For frequency Complex spectral values ​​on To analyze the total number of sampling points within the interval, For the first The normalized power value at each moment. For the first One frequency component, The imaginary unit is used to represent the amplitude of the spectrum. It can identify the main cycle of power changes, frequency modulation response characteristics, and high-frequency disturbance components.

[0031] Furthermore, determining the initial energy storage requirements of a wind farm includes identifying the target range for permissible power fluctuations based on the characteristics of wind farm power fluctuations.

[0032] Based on the target range, the maximum charging and discharging power and continuous discharge time required by the energy storage device under the peak state of wind power fluctuation are calculated to obtain the preliminary energy storage power and capacity requirement range.

[0033] It should also be noted that, from Extract the satisfying High volatility period set Used to identify the response window that the energy storage system should focus on covering, based on complex spectral values. Extracting satisfaction The main disturbance frequency band set Estimate the cumulative energy disturbance intensity under the main disturbance frequency band set, and calculate the preliminary required maximum charge and discharge power of energy storage as follows: , in, This indicates the maximum charging and discharging power of the energy storage system initially required for a wind farm during periods of high volatility. This indicates the maximum permissible fluctuation threshold. The threshold value representing the energy of frequency domain perturbation. This represents the set of main disturbance frequency bands. The modulus of the complex number's spectrum value.

[0034] The initial energy storage capacity requirement considering frequency disturbance energy compensation is expressed as: , in, This indicates the initial energy storage capacity requirement considering frequency domain disturbance energy compensation. Indicates the target smooth output power. Represents the frequency domain energy correction coefficient. Indicates frequency interval.

[0035] It should also be noted that the time domain threshold A preferred approach is to set the time-domain threshold as the 90th percentile of the historical fluctuation amplitude distribution of the wind farm. This preserves the fluctuations under typical system operating conditions while effectively identifying high-fluctuation windows that require key coverage by energy storage, serving as a preferred threshold for energy storage power configuration.

[0036] Frequency domain threshold The frequency component threshold representing the significant level of perturbation energy in the power spectrum is used to screen the set of dominant high-frequency perturbations. A preferred scheme for the frequency domain threshold is to set it as a spectral amplitude sequence. The mean plus a standard deviation ensures the statistical significance of the identified frequency bands in terms of disturbance contribution, thus avoiding the introduction of noise interference in frequency domain energy estimation.

[0037] S2: Based on the initial energy storage demand, construct a multi-objective optimization model to determine the optimal capacity ratio of various types of energy storage devices in hybrid energy storage.

[0038] Furthermore, the construction of a multi-objective optimization model includes extracting the performance parameters of the energy storage device based on the initial energy storage power and capacity demand range, taking the power matching capability and capacity coverage capability of the energy storage device as optimization objectives, and establishing a multi-objective optimization model with power satisfaction and capacity satisfaction as objective functions.

[0039] It should be noted that, based on the initial energy storage power and capacity requirements, and combined with the performance parameters of various energy storage devices, a hybrid energy storage configuration optimization model is constructed with power matching capability and capacity coverage capability as dual objectives. Technical parameters for each type of energy storage device are extracted, including maximum charge / discharge power, minimum power response time, efficiency, upper limit of energy storage capacity, lifespan, unit capacity ratio, and charge / discharge rate matching factor. The capacity ratio of each type of energy storage device is then considered. As decision variables, a dual objective function is constructed using the power matching capability and capacity response capability of the hybrid system.

[0040] The objective function for power satisfaction is expressed as: , in, Represents the power deviation function. Indicates the first The rated maximum charge and discharge power of the energy storage device.

[0041] , in, Represents the capacity deviation function. Indicates the first The upper limit of the rated capacity of energy storage devices.

[0042] The multi-objective optimization model is represented as follows: , in, This indicates that the total capacity ratio is 1, meaning that the sum of the proportions of various types of energy storage in the hybrid energy storage system is 100%, ensuring that the overall configuration ratio is reasonable.

[0043] Furthermore, determining the optimal capacity ratio scheme for each type of energy storage device in hybrid energy storage includes: discretizing the solution space of the multi-objective optimization model; using the capacity ratio of different types of energy storage devices as decision variables; employing a heuristic search algorithm to iteratively calculate the capacity ratio combination of each energy storage type; evaluating the fitness based on the objective functions of power coverage and capacity coverage; and selecting the capacity ratio solution with the best overall fitness as the optimal scheme.

[0044] It should also be noted that the capacity percentage of all energy storage types... The mapping is a fixed-precision coding structure. In each search generation, the capacity combinations are randomly initialized, and a comprehensive evaluation is performed based on the fitness function, represented as follows: , in, Represents the fitness function. , which are the weighting coefficients of the two objective functions, set according to the energy storage system's focus on response rate and sustainability.

[0045] An elite retention mechanism is employed during the optimization process, preserving individuals with the current optimal capacity ratio for the next generation to avoid information loss during the search process. A constraint correction strategy is also used to ensure... The total capacity constraint is maintained throughout the encoding and mutation operations. To address the energy storage response requirements with high perturbation frequency but weak energy intensity, a capacity fine-tuning mechanism is introduced to avoid redundancy caused by excessive configuration of high-response devices (such as supercapacitors) in the total capacity. Ultimately, the optimal capacity allocation solution with the best overall fitness is obtained. This serves as the structural input for the design of subsequent energy storage scheduling strategies.

[0046] in, Indicates the first The optimal capacity ratio solution for energy storage devices. Indicates the first The optimal capacity ratio for energy storage devices.

[0047] S3: Based on the optimal capacity ratio scheme, establish a dynamic optimization energy storage charging and discharging strategy.

[0048] Furthermore, establishing a dynamic optimization energy storage charging and discharging strategy includes constructing a mathematical model for energy storage power regulation based on the optimal capacity allocation scheme, taking the wind power prediction value and the energy storage response state as input quantities, and outputting charging and discharging power commands for various types of energy storage.

[0049] Based on the model predictive control method, a rolling optimization time window is set, and the charging and discharging power allocation of various energy storage devices is dynamically adjusted according to the wind power prediction error and the actual load deviation in each control cycle, forming a real-time adjustable dynamic charging and discharging strategy.

[0050] It should also be noted that the mathematical model for energy storage power regulation is expressed as follows: , in, Indicates the first Energy storage devices in time Charge and discharge power commands, Indicates the first Energy storage devices in time The dynamic participation coefficient, This represents the weighted total adjustable capacity of all energy storage types at the current moment. This indicates the wind power deviation during the current control cycle. Indicates the first The optimal capacity ratio for energy storage devices, Indicates the first Energy storage devices in time The dynamic participation coefficient.

[0051] The energy storage power regulation mathematical model outputs charging and discharging power commands. This represents the regulation power value that each type of energy storage should undertake during the control cycle, satisfying the following conditions: To achieve overall power compensation, each item Automatically combine capacity percentage and current energy storage status Adjust the proportions to allow for on-demand regulation.

[0052] In actual implementation, the above input data is updated once every control cycle (such as every minute or every 5 minutes), and the output is adjusted through a sliding prediction or feedback mechanism to form a time-continuous sequence of energy storage power commands, which drives the energy storage device to actually respond to wind power disturbances and achieve system-level dynamic balance.

[0053] Example 2, refer to Figure 2 As an embodiment of the present invention, a wind farm hybrid energy storage optimization system is provided, including an energy storage demand identification module 100, a capacity optimization calculation module 200, and a charging and discharging strategy control module 300.

[0054] S4: Energy storage demand identification module 100 includes a wind power data acquisition unit 101 and a power fluctuation modeling unit 102. The wind power data acquisition unit 101 is used to collect the historical output power, operating status and environmental information of wind turbine units to provide raw data for subsequent modeling. The power fluctuation modeling unit 102 is used to calculate the amplitude and frequency distribution characteristics of wind power fluctuations based on the collected data, output the power fluctuation parameters of the wind farm, and estimate the preliminary energy storage capacity and power demand range.

[0055] It should also be noted that the wind power data acquisition unit 101 transmits the collected historical operating power and status information to the power fluctuation modeling unit 102, and the fluctuation analysis results output by the power fluctuation modeling unit 102 are transmitted as input to the optimization model construction unit 201 of the capacity optimization calculation module.

[0056] S5: The capacity optimization calculation module 200 includes an optimization model construction unit 201 and a capacity ratio solution unit 202. The optimization model construction unit 201 constructs a multi-objective optimization model with power coverage and capacity coverage as objective functions based on the preliminary energy storage requirements and energy storage device performance parameters. The capacity ratio solution unit 202 adopts a heuristic search algorithm to traverse different types of energy storage capacity combinations, calculates the fitness, and outputs the optimal capacity ratio scheme.

[0057] It should also be noted that the optimization objective function constructed by the optimization model construction unit 201 is passed as input to the capacity ratio solution unit 202, and the optimal solution output by the capacity ratio solution unit 202 is passed as parameter input to the charging and discharging strategy control module 300.

[0058] S6: The charging and discharging strategy control module 300 includes a scheduling model construction unit 301 and a dynamic strategy optimization unit 302. The scheduling model construction unit 301 constructs a scheduling control model with wind power prediction and energy storage status as input and charging and discharging power as output. The dynamic strategy optimization unit 302 updates the charging and discharging commands of various types of energy storage in real time based on the rolling prediction mechanism and control feedback, so as to realize the dynamic optimization and adjustment of the strategy.

[0059] It should also be noted that the scheduling model construction unit 301 uses the wind power prediction value and capacity matching parameters to calculate the power command of each energy storage as input and transmits it to the dynamic strategy optimization unit 302. The dynamic strategy optimization unit 302 dynamically corrects the control command based on the energy storage status feedback.

[0060] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0061] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-including system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0062] More specific examples (a non-exhaustive list) of computer-readable media include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which programs can be printed, because programs can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0063] It should be understood that various parts of the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc. 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 it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for optimizing hybrid energy storage in wind farms, characterized in that, include: Collect historical operation data of wind farms, construct a wind power fluctuation characteristic model, and determine the preliminary energy storage requirements of wind farms; Based on the initial energy storage demand, a multi-objective optimization model is constructed to determine the optimal capacity ratio of various types of energy storage devices in hybrid energy storage. Based on the optimal capacity allocation scheme, a dynamic optimization energy storage charging and discharging strategy is established; The construction of a multi-objective optimization model includes extracting the performance parameters of the energy storage device based on the initial energy storage power and capacity demand range, taking the power matching capability and capacity coverage capability of the energy storage device as optimization objectives, and establishing a multi-objective optimization model with power satisfaction and capacity satisfaction as objective functions.

2. The wind farm hybrid energy storage optimization method as described in claim 1, characterized in that: The historical operating data of the wind farm includes historical power output data of wind turbine units, operating status data of wind turbine units, and environmental data of the wind farm.

3. The wind farm hybrid energy storage optimization method as described in claim 1 or 2, characterized in that: The construction of the wind power fluctuation characteristic model includes preprocessing the historical output power data of wind turbine units, and calculating the power fluctuation amplitude and frequency distribution characteristics based on the preprocessed data to obtain the wind farm power fluctuation characteristics.

4. The wind farm hybrid energy storage optimization method as described in claim 3, characterized in that: The determination of the initial energy storage requirements of the wind farm includes determining the target range of allowable power fluctuations of the wind farm based on the power fluctuation characteristics of the wind farm. Based on the target range, the maximum charging and discharging power and continuous discharge time required by the energy storage device under the peak state of wind power fluctuation are calculated to obtain the preliminary energy storage power and capacity requirement range.

5. The wind farm hybrid energy storage optimization method as described in claim 4, characterized in that: The process of determining the optimal capacity ratio scheme for each type of energy storage device in hybrid energy storage includes: discretizing the solution space of the multi-objective optimization model; using the capacity ratio of different types of energy storage devices as decision variables; employing a heuristic search algorithm to iteratively calculate the capacity ratio combination of each energy storage type; evaluating the fitness based on the objective functions of power coverage and capacity coverage; and selecting the capacity ratio solution with the best overall fitness as the optimal scheme.

6. The wind farm hybrid energy storage optimization method as described in any one of claims 1, 2, 4 or 5, characterized in that: The establishment of a dynamic optimization energy storage charging and discharging strategy includes: based on the optimal capacity ratio scheme, constructing a mathematical model for energy storage power regulation, taking the wind power prediction value and the energy storage response state as inputs, and outputting charging and discharging power commands for various types of energy storage. Based on the model predictive control method, a rolling optimization time window is set, and the charging and discharging power allocation of various energy storage devices is dynamically adjusted according to the wind power prediction error and the actual load deviation in each control cycle, forming a real-time adjustable dynamic charging and discharging strategy.

7. A system employing the wind farm hybrid energy storage optimization method as described in any one of claims 1 to 6, characterized in that: It includes an energy storage demand identification module (100), a capacity optimization calculation module (200), and a charging and discharging strategy control module (300). The energy storage demand identification module (100) includes a wind power data acquisition unit (101) and a power fluctuation modeling unit (102). The wind power data acquisition unit (101) is used to collect the historical output power, operating status and environmental information of the wind turbine generator, and provide raw data for subsequent modeling. The power fluctuation modeling unit (102) is used to calculate the amplitude and frequency distribution characteristics of wind power fluctuation based on the collected data, output the power fluctuation parameters of the wind farm, and estimate the preliminary energy storage capacity and power demand range. The capacity optimization calculation module (200) includes an optimization model construction unit (201) and a capacity ratio solution unit (202). The optimization model construction unit (201) constructs a multi-objective optimization model with power coverage and capacity coverage as objective functions based on the preliminary energy storage requirements and energy storage device performance parameters. The capacity ratio solution unit (202) adopts a heuristic search algorithm to traverse different types of energy storage capacity combinations, calculates the fitness, and outputs the optimal capacity ratio scheme. The charging and discharging strategy control module (300) includes a scheduling model construction unit (301) and a dynamic strategy optimization unit (302). The scheduling model construction unit (301) constructs a scheduling control model with wind power prediction and energy storage status as input and charging and discharging power as output. The dynamic strategy optimization unit (302) updates the charging and discharging commands of various types of energy storage in real time based on the rolling prediction mechanism and control feedback, so as to realize the dynamic optimization and adjustment of the strategy.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the wind farm hybrid energy storage optimization method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the wind farm hybrid energy storage optimization method as described in any one of claims 1 to 6.

Images