A network-configuration type energy storage configuration method and system based on multi-objective optimization

Abstract

This application proposes a multi-objective optimization-based method and system for configuring grid-type energy storage, belonging to the field of power system energy storage configuration. The method includes: acquiring a meteorological parameter distribution sequence and calculating the distribution of meteorological change parameters; randomly configuring grid-type energy storage units within a target area to obtain a first grid-type energy storage configuration scheme; analyzing the first configuration fitness of the first grid-type energy storage configuration scheme based on the meteorological change parameter distribution; and iteratively optimizing the grid-type energy storage configuration scheme to obtain the optimal grid-type energy storage configuration scheme, which is taken as the optimization result. This application solves the technical problem in existing grid-type energy storage configuration methods that only consider meteorological fluctuations, leading to insufficient configuration accuracy and a tendency for local energy storage instability. It achieves the technical effect of improving the accuracy of grid-type energy storage configuration, avoiding local energy storage instability, and optimizing the configuration of energy storage unit location and capacity.

Description

Technical Field

[0001] This invention relates to the field of energy storage configuration in power systems, and in particular to a grid-based energy storage configuration method and system based on multi-objective optimization. Background Technology

[0002] With the rapid development of new energy power generation technologies, the proportion of photovoltaic (PV) and wind power generation in the power system has been increasing year by year. However, PV and wind power generation are greatly affected by weather conditions, and their output power exhibits significant fluctuations and intermittent characteristics, posing a severe challenge to the stable operation of the power grid. To address the instability of new energy power generation, grid-based energy storage technology has been widely used as an effective solution. By rationally configuring grid-based energy storage units within the power grid area, power fluctuations from new energy power generation can be mitigated, maintaining the stable operation of the power grid.

[0003] Existing grid-based energy storage configuration methods primarily rely on meteorological fluctuations in the target area for configuration decisions, determining the layout of energy storage units by analyzing the changing trends of meteorological parameters. However, existing configurations only consider the single factor of meteorological fluctuations, failing to fully account for the compatibility between meteorological parameters at different locations and energy storage capacity. This results in a lack of specificity in the configuration scheme, and in actual operation, situations of insufficient or excessive energy storage capacity in local areas are prone to occur, leading to local energy storage instability and affecting the overall stability of the power grid and the utilization efficiency of energy storage resources. Summary of the Invention

[0004] This invention addresses the technical problem that grid-based energy storage configuration methods, which only consider meteorological fluctuations, lack sufficient configuration accuracy and are prone to local energy storage instability. It provides a grid-based energy storage configuration method and system based on multi-objective optimization to solve this problem.

[0005] The technical solution of the present invention to solve the above-mentioned technical problems is as follows: In a first aspect, the present invention provides a multi-objective optimization-based grid-type energy storage configuration method, comprising: acquiring a meteorological parameter distribution sequence within a target area over a past preset time range, and calculating a meteorological change parameter distribution; acquiring a configuration resource pool for grid-type energy storage configuration in the target area, and randomly configuring grid-type energy storage units within the target area according to the meteorological change parameter distribution to obtain a first grid-type energy storage configuration scheme, wherein the first grid-type energy storage configuration scheme includes multiple first configuration coordinates and multiple first configuration capacities; analyzing a first configuration fitness of the first grid-type energy storage configuration scheme according to the meteorological change parameter distribution, wherein the first configuration fitness is calculated based on the fitness of each first configuration capacity and the meteorological change parameters under the corresponding first configuration coordinates; setting capacity update parameters and coordinate update parameters in each iteration according to the meteorological change parameter distribution, performing iterative optimization of the grid-type energy storage configuration scheme, and obtaining an optimal grid-type energy storage configuration scheme as the grid-type energy storage configuration optimization result.

[0006] Secondly, the present invention provides a multi-objective optimization-based grid-type energy storage configuration system, comprising: a meteorological data acquisition module, used to acquire a sequence of meteorological parameter distributions within a target area over a preset time period and calculate the distribution of meteorological change parameters; a random configuration generation module, used to acquire a configuration resource pool for grid-type energy storage configuration in the target area, and randomly configure grid-type energy storage units within the target area according to the meteorological change parameter distribution to obtain a first grid-type energy storage configuration scheme, wherein the first grid-type energy storage configuration scheme includes multiple first configuration coordinates and multiple first configuration capacities; a fitness analysis module, used to analyze the first configuration fitness of the first grid-type energy storage configuration scheme according to the meteorological change parameter distribution, wherein the first configuration fitness is calculated based on the fitness of each first configuration capacity and the meteorological change parameters under the corresponding first configuration coordinates; and an iterative optimization module, used to set capacity update parameters and coordinate update parameters in each iteration according to the meteorological change parameter distribution, perform iterative optimization of the grid-type energy storage configuration scheme, and obtain an optimal grid-type energy storage configuration scheme as the optimization result of the grid-type energy storage configuration.

[0007] The beneficial effects of this invention are: The process involves obtaining the distribution sequence of meteorological parameters within a preset time range in the target area, calculating the distribution of meteorological change parameters, and analyzing historical meteorological data to understand the changing patterns of meteorological parameters at different locations within the target area, providing a data foundation for subsequent configuration optimization. A configuration resource pool for grid-type energy storage configuration in the target area is obtained. Based on the distribution of meteorological change parameters, grid-type energy storage units are randomly configured within the target area to obtain a first grid-type energy storage configuration scheme. This first grid-type energy storage configuration scheme includes multiple first configuration coordinates and multiple first configuration capacities. Randomly generating initial configuration schemes provides an initial solution space for the iterative optimization algorithm, ensuring the diversity of the optimization process. Based on the distribution of meteorological change parameters, the first configuration fitness of the first grid-type energy storage configuration scheme is analyzed. Specifically, the first configuration fitness is calculated based on the fit between each first configuration capacity and the meteorological change parameters at the corresponding first configuration coordinates. By evaluating the degree of matching between the configuration capacity and the meteorological change parameters at the location, the rationality of the current configuration scheme is quantified, providing an evaluation basis for subsequent optimization. Based on the distribution of meteorological change parameters, capacity update parameters and coordinate update parameters are set in each iteration to iteratively optimize the grid-type energy storage configuration scheme and obtain the optimal grid-type energy storage configuration scheme as the optimization result of the grid-type energy storage configuration. By iteratively adjusting the location and capacity of the energy storage units, the configuration scheme gradually converges to the optimal solution, ensuring that the location and capacity configuration of the energy storage units not only conforms to the meteorological change characteristics, but also achieves local and overall energy storage stability.

[0008] The above technical solution fully considers the compatibility between the distribution of meteorological change parameters and the configuration of energy storage units, realizes the coordinated optimization of the location and capacity of energy storage units, improves the accuracy of grid-type energy storage configuration, and effectively avoids the problem of local energy storage instability. Attached Figure Description

[0009] Figure 1 A flowchart illustrating a multi-objective optimization-based grid-type energy storage configuration method provided by the present invention; Figure 2 This is a schematic diagram of a grid-type energy storage configuration system based on multi-objective optimization, provided by the present invention.

[0010] In the attached diagram, the components represented by each number are as follows: Meteorological data acquisition module 11, random configuration generation module 12, fitness analysis module 13, iterative optimization module 14. Detailed Implementation

[0011] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0012] In the description of this invention, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the stated features. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0013] In the description of this invention, the term "for example" is used to mean "used as an example, illustration, or description." Any embodiment described as "for example" in this invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use the invention. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that the invention can be made without using these specific details. In other instances, well-known structures and processes will not be described in detail to avoid obscuring the description of the invention with unnecessary detail. Therefore, the invention is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed herein.

[0014] Example 1, as Figure 1 As shown, this embodiment of the invention provides a grid-based energy storage configuration method based on multi-objective optimization, including: S1. Obtain the distribution sequence of meteorological parameters within the target area over a preset time period in the past, and calculate the distribution of meteorological change parameters.

[0015] Specifically, the target area refers to the power grid region requiring grid-based energy storage configuration, typically including photovoltaic (PV) or wind power plants. Since the output of PV and wind power generation is significantly affected by meteorological conditions, exhibiting substantial fluctuations and instabilities, grid-based energy storage systems are necessary to achieve stable grid control. The preset time range can be set according to actual needs, such as the past year or the past six months, to ensure sufficient meteorological data samples are collected to reflect the changing patterns of meteorological parameters in the target area. Meteorological parameters differ depending on the type of power generation: for PV power generation areas, meteorological parameters mainly include solar irradiance and irradiance; for wind power generation areas, meteorological parameters mainly include wind speed and wind direction. The meteorological parameter distribution sequence refers to a sequence formed by arranging meteorological parameter data collected at multiple time points in chronological order. This sequence reflects the meteorological parameter values ​​and their changing trends at different locations within the target area at different times.

[0016] Subsequently, based on the meteorological parameter distribution sequence, the distribution of meteorological change parameters is calculated. These meteorological change parameters reflect the magnitude or degree of change or fluctuation of meteorological parameters at each location coordinate. For example, the maximum magnitude of change in meteorological parameters at each location coordinate can be calculated as the meteorological change parameter for that location. The distribution of meteorological change parameters is the spatial distribution of meteorological change parameters at all location coordinates within the target area. This distribution can intuitively reflect the intensity of meteorological fluctuations at different locations within the target area, providing an important basis for the subsequent location and capacity configuration of grid-type energy storage units.

[0017] S2. Obtain the configuration resource pool for grid-type energy storage configuration in the target area. Based on the distribution of meteorological change parameters, randomly configure grid-type energy storage units in the target area to obtain a first grid-type energy storage configuration scheme. The first grid-type energy storage configuration scheme includes multiple first configuration coordinates and multiple first configuration capacities.

[0018] Specifically, the resource pool refers to the total amount of resources available for grid-based energy storage configuration, including the number of grid-based energy storage units and the total energy storage capacity. The number of grid-based energy storage units determines the number of energy storage units that need to be configured in the target area, while the total energy storage capacity is the sum of the capacities of all energy storage units. The resource pool is typically determined by the power grid planning department based on factors such as the power generation scale, load demand, and grid stability requirements of the target area.

[0019] After obtaining the configuration resource pool, it is necessary to determine the specific configuration location and capacity of each grid-type energy storage unit. Candidate configuration schemes are generated using a random configuration method. Specifically, based on the number of grid-type energy storage units, multiple location coordinates are randomly selected within the target area as multiple candidate first configuration coordinates. Simultaneously, the total energy storage capacity is allocated, assigning a corresponding energy storage capacity to each configuration coordinate, thus obtaining multiple candidate first configuration capacities.

[0020] To ensure the rationality of randomly generated candidate configuration schemes, the schemes are evaluated based on the distribution of meteorological change parameters. Specifically, a generation score is calculated for each candidate configuration scheme, reflecting the degree of matching between the scheme and the meteorological change parameter distribution. If the generation score meets a preset generation score threshold, the candidate configuration scheme is considered to have basic feasibility and is adopted as the first grid-type energy storage configuration scheme. Multiple candidate first configuration coordinates and multiple candidate first configuration capacities are used as multiple first configuration capacities. If the generation score threshold is not met, random configuration is repeated until a suitable scheme is obtained.

[0021] The first grid-type energy storage configuration scheme includes multiple first configuration coordinates and multiple first configuration capacities. Each first configuration coordinate corresponds to the installation location of a grid-type energy storage unit, and each first configuration capacity corresponds to the capacity of the energy storage unit at that location. This first grid-type energy storage configuration scheme serves as the starting point for subsequent iterative optimization. Through iterative optimization, the configuration coordinates and configuration capacities are gradually adjusted to ultimately obtain the optimal grid-type energy storage configuration scheme.

[0022] S3. Based on the distribution of meteorological change parameters, analyze the first configuration fitness of the first grid-type energy storage configuration scheme, wherein the first configuration fitness is calculated based on the fitness of each first configuration capacity and the meteorological change parameters under the corresponding first configuration coordinates.

[0023] Specifically, firstly, based on the distribution of meteorological change parameters, multiple first meteorological change parameters under multiple first configuration coordinates are retrieved. Specifically, the meteorological change parameter distribution includes meteorological change parameters for all location coordinates within the target area. Based on the multiple first configuration coordinates determined in the first grid-type energy storage configuration scheme, the meteorological change parameter values ​​for the corresponding locations are extracted from the meteorological change parameter distribution to obtain multiple first meteorological change parameters.

[0024] Then, based on multiple first meteorological variation parameters and multiple first configuration capacities, the first configuration fitness of the first grid-type energy storage configuration scheme is calculated. The calculation of configuration fitness comprehensively considers two key factors: first, the rationality of the configuration coordinate selection, i.e., whether the energy storage units are configured in locations with significant meteorological fluctuations; and second, the rationality of the configuration capacity allocation, i.e., whether the energy storage capacity at each location matches the meteorological variation parameters at that location. The first configuration fitness reflects the degree of adaptation between each first configuration capacity and the meteorological variation parameters under the corresponding first configuration coordinates. If the meteorological variation parameters at a certain location are large, it indicates that the power generation at that location fluctuates significantly, requiring a relatively large energy storage capacity to achieve effective stability control; conversely, locations with smaller meteorological variation parameters can be configured with smaller energy storage capacities. When the allocation of configuration capacity shows a good match with the meteorological variation parameters at each location, the configuration fitness is high, indicating that the configuration scheme can effectively cope with meteorological fluctuations in the target area and achieve stable grid operation.

[0025] By calculating the fitness of the first configuration, an evaluation benchmark is provided for subsequent iterative optimization. The configuration fitness is continuously improved through the iterative process, and finally the optimal grid-type energy storage configuration scheme with the highest fitness is obtained.

[0026] S4. Based on the distribution of meteorological change parameters, set the capacity update parameters and coordinate update parameters in each iteration, perform iterative optimization of the grid-type energy storage configuration scheme, and obtain the optimal grid-type energy storage configuration scheme as the optimization result of the grid-type energy storage configuration.

[0027] Specifically, iterative optimization refers to adjusting the configuration coordinates and capacity through multiple iterations based on the initial grid-type energy storage configuration scheme, gradually improving the configuration adaptability, and ultimately obtaining the configuration scheme with the highest configuration adaptability as the optimal grid-type energy storage configuration scheme. Capacity update parameters and coordinate update parameters are key parameters controlling the adjustment range in each iteration, and their settings directly affect the efficiency of iterative optimization and the quality of the final result. Capacity update parameters and coordinate update parameters are not fixed but are adaptively set according to the characteristics of meteorological parameter distribution. When the differences in meteorological parameter distribution are large, larger capacity update parameters and coordinate update parameters are used to quickly adjust the configuration scheme; when the differences in meteorological parameter distribution are small, smaller capacity update parameters and coordinate update parameters are used to achieve fine-tuning.

[0028] In each iteration, the current grid-type energy storage configuration scheme is adjusted using capacity update parameters and coordinate update parameters to generate new candidate configuration schemes. Then, the configuration fitness of the new candidate configuration scheme is calculated. If the configuration fitness is improved compared to the previous iteration, it indicates that the adjustment direction is correct, and the configuration scheme is retained and the iteration continues; if the configuration fitness is not improved, the optimization strategy is adjusted or other adjustment directions are tried.

[0029] The iterative optimization process continues until convergence conditions are met, such as the improvement in configuration fitness being less than a preset threshold or reaching the maximum number of iterations. After convergence, the configuration scheme with the highest configuration fitness during the iteration process is selected as the optimal grid-type energy storage configuration scheme. This scheme is the optimized grid-type energy storage configuration, which includes the optimal configuration coordinates and configuration capacity, and can effectively cope with meteorological fluctuations in the target area, ensuring the stable operation of the power grid.

[0030] Through the aforementioned iterative optimization process, the characteristics of meteorological parameter distribution within the target area can be comprehensively considered, and the configuration scheme can be adaptively adjusted, avoiding the problems of slow convergence speed or easy getting trapped in local optima caused by fixed parameter updates. The final optimal grid-type energy storage configuration scheme not only fully considers the spatial distribution characteristics of meteorological fluctuations in terms of configuration location, but also achieves precise matching between the configuration capacity and the meteorological parameters at each location. This effectively avoids local energy storage instability, improves the accuracy and rationality of grid-type energy storage configuration, and ensures the stable operation of the power grid under meteorological fluctuation conditions.

[0031] Furthermore, the distribution sequence of meteorological parameters within the target area over a preset time period is obtained, and the distribution of meteorological change parameters is calculated, including: S11. Obtain the distribution of meteorological parameters for multiple time nodes within a preset time range in the target area, wherein each meteorological parameter distribution includes meteorological parameters for all location coordinates within the target area; S12. Arrange the meteorological parameter distributions at multiple time points according to time to obtain a meteorological parameter distribution sequence; S13. Calculate the distribution of meteorological change parameters based on the meteorological parameter distribution sequence.

[0032] In one feasible implementation, firstly, the meteorological parameter distributions of multiple time nodes within a preset time range in the target area are acquired. Specifically, multiple time nodes are selected within the preset time range for meteorological parameter collection. The selection of time nodes can be at equal intervals, such as once per hour, day, or week, or at non-equal intervals depending on the characteristics of meteorological changes. Each time node corresponds to a meteorological parameter distribution, which includes meteorological parameters for all location coordinates within the target area. In other words, at each time node, it is necessary to acquire the meteorological parameter values ​​at each location coordinate within the target area to form a complete meteorological parameter distribution for that time node. For example, for a photovoltaic power generation area, the meteorological parameter distribution acquired at a certain time node includes solar irradiance data for all locations within that area; for a wind power generation area, it includes wind speed data for all locations. The location coordinates within the target area are determined using a gridded method. Specifically, the target area is divided into multiple grid cells, with the center point of each grid cell serving as a location coordinate. The grid division precision is set according to actual needs; for example, the target area can be divided into several grids of equal size according to latitude and longitude, or a non-uniform grid division can be performed based on factors such as topography, distribution of power generation equipment, etc. In addition, location coordinates can directly correspond to actual physical locations within the target area, such as the installation locations of existing power generation equipment and the locations of meteorological monitoring stations. Meteorological parameters are obtained by real-time data collection from meteorological monitoring equipment, retrieval of historical data from meteorological databases, or calculation using methods such as meteorological interpolation to obtain meteorological parameter values ​​for each location coordinate.

[0033] Subsequently, the meteorological parameter distributions at multiple time points were arranged chronologically to obtain a meteorological parameter distribution sequence. Since the meteorological parameter distributions at multiple time points were obtained, these distribution data are discrete. To reflect the evolution of meteorological parameters over time, these meteorological parameter distributions were arranged in chronological order to form a meteorological parameter distribution sequence. This meteorological parameter distribution sequence not only contains meteorological parameter information at various locations in the spatial dimension but also includes information on the changes in meteorological parameters in the temporal dimension, comprehensively reflecting the spatiotemporal evolution characteristics of meteorological conditions within the target area.

[0034] Subsequently, based on the meteorological parameter distribution sequence, the distribution of meteorological change parameters is calculated. Specifically, based on the obtained meteorological parameter distribution sequence, the variation pattern of meteorological parameters at each location coordinate over time is analyzed, and meteorological change parameters characterizing the degree of meteorological fluctuations are calculated. For example, the maximum variation amplitude, standard deviation, variance, and other statistical indicators of meteorological parameters at each location coordinate within a preset time range are calculated as the meteorological change parameters for that location. The meteorological change parameters of all location coordinates within the target area are then summarized to generate the meteorological change parameter distribution. This distribution visually reflects the differences in the intensity of meteorological fluctuations at different locations within the target area, providing crucial data support for the subsequent rational configuration of grid-type energy storage units.

[0035] Furthermore, based on the meteorological parameter distribution sequence, the distribution of meteorological change parameters is calculated, including: S131. Based on the meteorological parameter distribution sequence, calculate the maximum variation range of the meteorological parameters at each location coordinate, and use it as the meteorological change parameter; S132. Generate the meteorological change parameter distribution based on the meteorological change parameters of all location coordinates.

[0036] In a preferred embodiment, firstly, based on the meteorological parameter distribution sequence, the maximum variation amplitude of the meteorological parameters at each location coordinate is calculated as the meteorological variation parameter. Specifically, the meteorological parameter distribution sequence includes meteorological parameter distributions at multiple time points. For any location coordinate within the target area, the meteorological parameter values ​​at each time point can be extracted from the meteorological parameter distribution sequence to form a meteorological parameter time series for that location coordinate. Based on the meteorological parameter time series for that location coordinate, the maximum variation amplitude of the meteorological parameters within a preset time range is calculated. The maximum variation amplitude is obtained by calculating the difference between the maximum and minimum values ​​in the meteorological parameter time series for that location coordinate. The maximum variation amplitude can intuitively reflect the intensity of meteorological condition fluctuations at that location coordinate; a larger value indicates more severe meteorological fluctuations at that location. The calculated maximum variation amplitude is then used as the meteorological variation parameter for that location coordinate.

[0037] Next, a meteorological change parameter distribution is generated based on the meteorological change parameters of all location coordinates. After calculating the meteorological change parameters for each location coordinate within the target area in step S131, these meteorological change parameters are organized and summarized according to their corresponding location coordinates to generate the meteorological change parameter distribution. The meteorological change parameter distribution is a spatial distribution map of the intensity of meteorological fluctuations within the target area, showing the differences in meteorological fluctuations at different locations within the target area. Through the meteorological change parameter distribution, areas with large and small meteorological fluctuations can be intuitively identified, thus providing a basis for the location selection and capacity allocation of grid-type energy storage units. Locations with large meteorological fluctuations usually require the configuration of energy storage units or the allocation of larger energy storage capacity to effectively cope with power generation fluctuations at that location; while locations with small meteorological fluctuations can appropriately reduce energy storage configuration or allocate smaller energy storage capacity, achieving optimized allocation of energy storage resources.

[0038] Through the above steps, the meteorological variation parameters at each location coordinate within the target area can be accurately calculated, generating a complete distribution of these parameters. Using the maximum variation amplitude as the meteorological variation parameter effectively captures the meteorological fluctuation characteristics at each location, avoiding the potential omission of extreme fluctuations that might occur when relying solely on average values ​​or other statistical indicators. The generated distribution of meteorological variation parameters provides a precise data foundation for subsequent configuration optimization of grid-based energy storage units. This allows energy storage configurations to specifically address the spatial distribution characteristics of meteorological fluctuations within the target area, improving the relevance of the configuration scheme and effectively enhancing the grid-based energy storage system's ability to cope with meteorological fluctuations, thus ensuring the stable operation of the power grid.

[0039] Furthermore, a configuration resource pool for grid-type energy storage configuration in the target area is obtained. Based on the distribution of meteorological change parameters, grid-type energy storage units are randomly configured within the target area to obtain a first grid-type energy storage configuration scheme, including: S21. Obtain the configuration resource pool for grid-type energy storage configuration in the target area, wherein the configuration resource pool includes the number of grid-type energy storage units and the total energy storage capacity. S22. According to the number of grid-type energy storage units, randomly select multiple candidate first configuration coordinates in the target area, and allocate the total energy storage capacity to obtain multiple candidate first configuration capacities as the first candidate grid-type energy storage configuration scheme. S23. Based on the distribution of meteorological change parameters, calculate the first generation score of the first candidate grid-type energy storage configuration scheme, and determine whether it meets the generation score threshold. If yes, it is adopted as the first grid-type energy storage configuration scheme; otherwise, the grid-type energy storage unit configuration is re-performed.

[0040] In a preferred embodiment, firstly, a configuration resource pool for grid-based energy storage configuration in the target area is obtained. The configuration resource pool defines the overall resource constraints available for grid-based energy storage configuration, including the number of grid-based energy storage units and the total energy storage capacity. The number of grid-based energy storage units determines the number of energy storage units that need to be deployed in the target area, and this number is determined comprehensively based on factors such as the area of ​​the target area, the scale of installed power generation capacity, and the grid topology. The total energy storage capacity is the sum of the capacities of all energy storage units, reflecting the total capacity resources available for energy storage configuration. This capacity is determined comprehensively based on factors such as the power generation fluctuation characteristics, load demand, grid stability requirements, and investment budget of the target area. The parameters of the configuration resource pool are pre-set by the grid planning department or the energy storage configuration decision system as constraints for subsequent configuration optimization.

[0041] Then, based on the number of grid-type energy storage units, multiple candidate first configuration coordinates are randomly selected within the target area, and the total energy storage capacity is allocated to obtain multiple candidate first configuration capacities, which serve as the first candidate grid-type energy storage configuration scheme. Specifically, based on the number of grid-type energy storage units determined in the configuration resource pool, a corresponding number of location coordinates are randomly selected from all location coordinates within the target area as candidate first configuration coordinates. The random selection method can employ uniform random sampling, weighted random sampling, or other methods to ensure a certain degree of diversity in the initial configuration scheme. After determining the candidate first configuration coordinates, the total energy storage capacity is allocated to each configuration coordinate. Capacity allocation can be done using a uniform allocation method, that is, the total energy storage capacity is evenly distributed among all energy storage units; or it can be done using a random allocation method, randomly allocating capacity to each energy storage unit, but the constraint condition that the sum of the capacities of all energy storage units equals the total energy storage capacity must be met. Through the above random configuration process, a first candidate grid-type energy storage configuration scheme containing multiple candidate first configuration coordinates and multiple candidate first configuration capacities is obtained.

[0042] Subsequently, based on the distribution of meteorological change parameters, the first generation score of the first candidate grid-type energy storage configuration scheme is calculated to determine whether it meets the generation score threshold. The first generation score is used to evaluate the initial rationality of the randomly generated first candidate grid-type energy storage configuration scheme, avoiding the generation of completely unreasonable configuration schemes into the subsequent iterative optimization process. Specifically, based on the distribution of meteorological change parameters and the first candidate grid-type energy storage configuration scheme, it is analyzed whether the selection of candidate configuration coordinates and the allocation of candidate configuration capacity have a basic matching relationship with the distribution of meteorological change parameters. For example, it is evaluated whether the candidate configuration coordinates cover areas with large meteorological fluctuations, and whether the capacity allocation shows a certain correlation with the meteorological change parameters at each location. The evaluation results are quantified into a first generation score and compared with a preset generation score threshold. If the first generation score meets the generation score threshold, it indicates that the first candidate grid-type energy storage configuration scheme has basic feasibility, and it is adopted as the first grid-type energy storage configuration scheme. Multiple candidate first configuration coordinates are adopted as multiple first configuration coordinates, and multiple candidate first configuration capacities are adopted as multiple first configuration capacities, entering the subsequent fitness evaluation and iterative optimization process. If the first generated score does not meet the generation score threshold, it means that the first candidate grid-type energy storage configuration scheme is not well matched with the distribution of meteorological change parameters. The grid-type energy storage unit needs to be reconfigured, that is, return to step S22 to randomly select configuration coordinates and allocate configuration capacity until a configuration scheme that meets the generation score threshold is obtained.

[0043] Through the above steps, while randomly generating initial configuration schemes, a generation and scoring mechanism based on the distribution of meteorological change parameters is introduced to initially screen the randomly generated configuration schemes, ensuring that the initial schemes entering the iterative optimization process have a certain degree of rationality. This screening mechanism effectively avoids the problem of slow convergence or getting trapped in poor local optima due to completely unreasonable initial configuration schemes, improving the efficiency of optimization and the quality of the final configuration scheme, thus laying the foundation for obtaining a high-quality, optimal grid-type energy storage configuration scheme.

[0044] Furthermore, based on the distribution of the meteorological change parameters, a first generation score for the first candidate grid-type energy storage configuration scheme is calculated, including: S231. Calculate the dispersion of meteorological changes based on the distribution of the meteorological change parameters. S232. Calculate the dispersion of multiple candidate first configuration capacities to obtain the dispersion of the first candidate capacity; S233. Calculate the similarity between the first candidate capacity dispersion and the meteorological change dispersion, and use it as the first generated score.

[0045] In a preferred embodiment, firstly, the meteorological variation dispersion is calculated based on the distribution of meteorological variation parameters. The meteorological variation dispersion quantifies the degree of dispersion of meteorological variation parameters within the target area. Specifically, the meteorological variation parameter distribution includes meteorological variation parameters for all location coordinates within the target area, and these meteorological variation parameters exhibit spatial differences. The meteorological variation dispersion is calculated using standard deviation. For example, calculating the standard deviation of meteorological variation parameters for all location coordinates indicates that the larger the standard deviation, the more significant the difference in the intensity of meteorological fluctuations at different locations, and the higher the meteorological variation dispersion; conversely, the smaller the standard deviation, the more uniform the intensity of meteorological fluctuations at different locations, and the lower the meteorological variation dispersion. The meteorological variation dispersion reflects the spatial distribution characteristics of meteorological fluctuations within the target area and serves as a reference for evaluating the rationality of the configuration scheme.

[0046] Then, the dispersion of the multiple candidate first configuration capacities is calculated to obtain the first candidate capacity dispersion. The first candidate capacity dispersion is used to quantify the degree of dispersion in the capacity allocation of each energy storage unit in the first candidate grid-type energy storage configuration scheme. Specifically, the first candidate grid-type energy storage configuration scheme includes multiple candidate first configuration capacities, which may differ or be relatively uniform. The first candidate capacity dispersion is also calculated using the standard deviation. For example, the standard deviation of the multiple candidate first configuration capacities is calculated as the first candidate capacity dispersion. The larger the first candidate capacity dispersion, the more significant the difference in capacity allocation between different energy storage units; the smaller the first candidate capacity dispersion, the more uniform the capacity allocation of each energy storage unit.

[0047] Next, the similarity between the dispersion of the first candidate capacity and the dispersion of meteorological changes is calculated, serving as the first generated score. The calculation of the first generated score is based on the matching principle between the dispersion of the first candidate capacity and the dispersion of meteorological changes. In a reasonable energy storage configuration scheme, the dispersion of capacity allocation should be adapted to the dispersion of meteorological changes. Specifically, if the dispersion of meteorological changes within the target area is high, it indicates significant differences in meteorological fluctuations at different locations. In this case, the allocation of energy storage capacity should also exhibit high dispersion, i.e., allocating larger capacities to locations with large meteorological fluctuations and smaller capacities to locations with small meteorological fluctuations, thus adapting the capacity allocation to the characteristics of meteorological fluctuations. Conversely, if the dispersion of meteorological changes is low, it indicates relatively uniform meteorological fluctuations at various locations, and the dispersion of capacity allocation should also be low, allowing for a relatively uniform capacity allocation. Therefore, by calculating the similarity between the dispersion of the first candidate capacity and the dispersion of meteorological changes, it is possible to assess whether the candidate configuration scheme matches the spatial distribution characteristics of meteorological fluctuations in terms of capacity allocation patterns. The similarity is obtained by dividing the smaller value of the first candidate capacity dispersion and the dispersion of meteorological changes by the larger value; this similarity is the first generated score. The similarity score ranges from 0 to 1. A value closer to 1 indicates a closer similarity between the two dispersion scores, and a better match between the capacity allocation pattern and the meteorological fluctuation distribution pattern. For example, if the calculated meteorological variation dispersion is 0.8 and the first candidate capacity dispersion is 0.6, then the first generated score is 0.6 / 0.8 = 0.75; if the first candidate capacity dispersion is 0.85, then the first generated score is 0.8 / 0.85 ≈ 0.94. It can be seen that the closer the capacity allocation dispersion is to the meteorological variation dispersion, the higher the first generated score, indicating a better rationality for the first candidate grid-type energy storage configuration scheme.

[0048] By comparing the similarity between the first candidate capacity dispersion and the meteorological change dispersion through the above steps, the rationality of the candidate configuration scheme is evaluated. This ensures that the randomly generated configuration scheme is consistent with the spatial distribution characteristics of meteorological fluctuations in the target area in terms of capacity allocation pattern, grasps the rationality of the configuration scheme, and avoids configuration schemes with serious mismatch between capacity allocation pattern and meteorological fluctuation distribution from entering the iterative optimization process. This improves the starting quality of the optimization algorithm, speeds up the convergence speed, and enhances the efficiency and quality of finally obtaining the optimal configuration scheme.

[0049] Furthermore, based on the distribution of the meteorological change parameters, the first configuration adaptability of the first grid-type energy storage configuration scheme is analyzed, including: S31. Based on the distribution of meteorological change parameters, retrieve multiple first meteorological change parameters under the multiple first configuration coordinates; S32. Based on multiple first meteorological change parameters and multiple first configuration capacities, calculate the first configuration adaptability of the first grid-type energy storage configuration scheme.

[0050] In a preferred embodiment, firstly, based on the meteorological change parameter distribution, multiple first meteorological change parameters under multiple first configuration coordinates are retrieved. Specifically, the first grid-type energy storage configuration scheme has determined multiple first configuration coordinates, which represent the configuration locations of the energy storage units. The meteorological change parameter distribution includes meteorological change parameters for all location coordinates within the target area; therefore, based on the multiple first configuration coordinates, the meteorological change parameters for the corresponding locations can be extracted from the meteorological change parameter distribution to obtain multiple first meteorological change parameters. Each first configuration coordinate corresponds to one first meteorological change parameter, reflecting the intensity of meteorological fluctuations at that configuration location. Through the retrieval operation, a correlation is established between the configuration coordinates and the corresponding location's meteorological change characteristics, providing the necessary meteorological data foundation for subsequent configuration fitness calculations.

[0051] Then, based on multiple first meteorological change parameters and multiple first configuration capacities, the first configuration fitness of the first grid-type energy storage configuration scheme is calculated. The first configuration fitness is a comprehensive index for evaluating the merits of the first grid-type energy storage configuration scheme, and its calculation comprehensively considers the meteorological fluctuation characteristics of the configuration location and the allocation of configuration capacity. Specifically, by analyzing the matching relationship between multiple first meteorological change parameters and multiple first configuration capacities, the configuration location fitness and configuration capacity allocation fitness of the first grid-type energy storage configuration scheme are evaluated. A high-quality configuration scheme should meet two requirements: firstly, the configuration location should preferentially cover areas with large meteorological fluctuations; secondly, the configuration capacity should be proportional to the meteorological change parameters at each location, achieving a match between capacity allocation and the intensity of meteorological fluctuations. The larger the first configuration fitness, the higher the degree of matching between the first grid-type energy storage configuration scheme and the distribution of meteorological change parameters in terms of location selection and capacity allocation, and the better the quality of the configuration scheme; conversely, the smaller the first configuration fitness, the worse the fitness of the first grid-type energy storage configuration scheme. By calculating the fitness of the first configuration, the merits of the first grid-type energy storage configuration scheme are quantitatively evaluated, providing an evaluation benchmark and optimization direction for the subsequent iterative optimization process.

[0052] Through the above steps, a quantitative evaluation mechanism between the configuration scheme and the distribution of meteorological change parameters is established. This mechanism can accurately evaluate the adaptability of the configuration scheme in terms of location selection and capacity allocation, providing clear optimization objectives and quantitative indicators for the iterative optimization process. This ensures that the optimization process can move in the direction of improving the adaptability of the configuration, and ultimately obtain the optimal grid-type energy storage configuration scheme that is highly matched with the meteorological fluctuation characteristics of the target area. This effectively enhances the ability of the energy storage system to cope with meteorological fluctuations and the stability of grid operation.

[0053] Furthermore, based on multiple first meteorological change parameters and multiple first configuration capacities, the first configuration fitness of the first grid-type energy storage configuration scheme is calculated, including: S321. Calculate the ratio of the mean of multiple first meteorological change parameters to the maximum value of the meteorological change parameters, and use it as the first stable configuration score; S322. Based on the ratio of multiple first configuration capacities to the total energy storage capacity, obtain multiple first capacity coefficients; calculate the ratio of each first meteorological change parameter to the sum of multiple first meteorological change parameters to obtain multiple first meteorological change coefficients. S323. Calculate the similarity between multiple first capacity coefficients and multiple first meteorological change coefficients to obtain the first adaptation configuration score; S324. Calculate the ratio of the minimum to the maximum value within the distribution of the meteorological change parameters, use it as the stability weight, and calculate the adaptation weight; S325. Using the stability weight and adaptation weight, the first stable configuration score and the first adapted configuration score are weighted and calculated to obtain the first configuration fitness.

[0054] In a preferred embodiment, firstly, the ratio of the mean of multiple first meteorological change parameters to the maximum value of the meteorological change parameters is calculated as the first stable configuration score. Specifically, the first stable configuration score is used to evaluate the overall stability performance of the first grid-type energy storage configuration scheme. First, the mean of multiple first meteorological change parameters is calculated, which reflects the average meteorological fluctuation intensity at the location of the configured energy storage units. Then, the maximum value of the meteorological change parameters is obtained from the meteorological change parameter distribution, which represents the fluctuation intensity at the location with the most severe meteorological fluctuations in the target area. The mean of multiple first meteorological change parameters is divided by the maximum value of the meteorological change parameters to obtain the first stable configuration score. This score reflects the degree of proximity between the meteorological fluctuation intensity at the configuration location and the maximum meteorological fluctuation intensity in the target area. The higher the first stable configuration score, the more effectively the energy storage units are configured in areas with large meteorological fluctuations and can effectively cope with meteorological fluctuations in the target area, indicating better stability of the configuration scheme; conversely, the lower the first stable configuration score, the more effectively the energy storage units are configured in areas with small meteorological fluctuations and cannot adequately cope with extreme meteorological fluctuations in the target area.

[0055] Then, based on the ratios of multiple first configuration capacities to the total energy storage capacity, multiple first capacity coefficients are obtained. The ratio of each first meteorological change parameter to the sum of multiple first meteorological change parameters is then calculated to obtain multiple first meteorological change coefficients. Specifically, for each first configuration capacity, it is divided by the total energy storage capacity to obtain the corresponding first capacity coefficient. The first capacity coefficient reflects the proportion of the energy storage unit's capacity in the total energy storage capacity, and the sum of all first capacity coefficients equals 1. Similarly, for each first meteorological change parameter, it is divided by the sum of multiple first meteorological change parameters to obtain the corresponding first meteorological change coefficient. The first meteorological change coefficient reflects the proportion of the meteorological fluctuation intensity at that configuration location to the total meteorological fluctuation intensity at all configuration locations, and the sum of all first meteorological change coefficients also equals 1. Through the above normalization process, the configuration capacity and meteorological change parameters are converted into corresponding coefficient forms, facilitating subsequent matching degree analysis.

[0056] Subsequently, the similarity between multiple first capacity coefficients and multiple first meteorological variation coefficients is calculated to obtain the first adaptive configuration score. The first adaptive configuration score is used to evaluate the degree of matching between the allocation of configured capacity and the intensity of meteorological fluctuations at each configuration location. In an ideal configuration scheme, locations with high meteorological fluctuation intensity should be allocated a larger proportion of energy storage capacity, and locations with low meteorological fluctuation intensity should be allocated a smaller proportion of energy storage capacity; that is, the distribution of the first capacity coefficients should match the distribution of the first meteorological variation coefficients. The similarity can be calculated using cosine similarity, with a value ranging from 0 to 1. The closer the value is to 1, the closer the directions of the two vectors are, and the better the matching between the capacity allocation ratio and the meteorological fluctuation intensity ratio. Higher similarity indicates a better match between capacity allocation and meteorological fluctuation intensity, resulting in a higher first adaptive configuration score; lower similarity indicates a larger deviation between capacity allocation and meteorological fluctuation intensity, resulting in a lower first adaptive configuration score. For example, suppose a configuration scheme includes three energy storage units with initial configuration capacities of 30MWh, 40MWh, and 30MWh, respectively, for a total energy storage capacity of 100MWh. Then, the multiple initial capacity coefficients are 0.3, 0.4, and 0.3, forming a capacity coefficient vector (0.3, 0.4, 0.3). The corresponding initial meteorological variation parameters are 0.6, 1.2, and 0.4, summing to 2.2. Therefore, the multiple initial meteorological variation coefficients are 0.27, 0.55, and 0.18, forming a meteorological variation coefficient vector (0.27, 0.55, 0.18). The cosine similarity between the two vectors is approximately 0.953, which is the score of the first suitable configuration, indicating that the capacity allocation of this configuration scheme matches the intensity of meteorological fluctuations well. It can be seen that the meteorological fluctuation coefficient at the second position is relatively large (0.55), and the allocated capacity coefficient is also relatively large (0.4), reflecting a positive correlation between capacity allocation and the intensity of meteorological fluctuations.

[0057] Next, the ratio of the minimum to the maximum value within the meteorological change parameter distribution is calculated as a stability weight, and the adaptation weight is also calculated. Specifically, the minimum and maximum values ​​of the meteorological change parameters are obtained from the meteorological change parameter distribution, and the ratio of the minimum to the maximum value is calculated. This ratio reflects the uniformity of meteorological fluctuations within the target area. When the minimum and maximum values ​​are close, the ratio is close to 1, indicating that meteorological fluctuations are relatively uniform across locations within the target area, and the dispersion of meteorological changes is low. When the minimum value is much smaller than the maximum value, the ratio is close to 0, indicating that meteorological fluctuations differ significantly across locations within the target area, and the dispersion of meteorological changes is high. This ratio is used as a stability weight to adjust the weight of the first stable configuration score in the configuration fitness. The adaptation weight can be calculated based on the stability weight, using the formula Adaptation Weight = 1 - Stability Weight to ensure that the sum of the two weights equals 1. When meteorological fluctuations are relatively uniform, the stability weight is larger, focusing more on assessing whether the configuration location covers the meteorological fluctuation area; when meteorological fluctuations differ significantly, the adaptation weight is larger, focusing more on assessing whether the capacity allocation matches the intensity of meteorological fluctuations.

[0058] Next, using stability weights and adaptation weights, the scores of the first stable configuration and the first adapted configuration are weighted and calculated to obtain the first configuration fitness. Specifically, the first stable configuration score is multiplied by the stability weight, the first adapted configuration score is multiplied by the adaptation weight, and then the two are added together to obtain the first configuration fitness. The calculation formula is: First Configuration Fitness = First Stable Configuration Score × Stability Weight + First Adaptive Configuration Score × Adaptation Weight. Through weighted calculation, the performance of the configuration scheme in both stability and adaptability dimensions is comprehensively considered, and the importance of the two dimensions is adaptively adjusted according to the distribution characteristics of meteorological fluctuations in the target area, so that the configuration fitness can comprehensively and accurately evaluate the merits of the configuration scheme.

[0059] Through the above steps, not only was the stability of the configuration location evaluated, but also the adaptability of the configuration capacity allocation was assessed. The weights of the two evaluation dimensions were adaptively adjusted according to the distribution characteristics of meteorological fluctuations in the target area, ensuring that the configuration adaptability can accurately reflect the comprehensive performance of the configuration scheme under different meteorological fluctuation scenarios. This avoids the one-sidedness of evaluation by a single indicator. The adaptive weight mechanism improves the pertinence and accuracy of the evaluation, provides a reliable evaluation benchmark for the iterative optimization process, and ultimately ensures that a high-quality optimal grid-type energy storage configuration scheme is obtained, effectively improving the ability of the energy storage system to cope with complex meteorological fluctuations and the stability of grid operation.

[0060] Furthermore, based on the distribution of meteorological change parameters, capacity update parameters and coordinate update parameters are set for each iteration to iteratively optimize the grid-type energy storage configuration scheme, obtaining the optimal grid-type energy storage configuration scheme as the optimization result, including: S41. Based on the dispersion of meteorological changes in the distribution of meteorological change parameters, configure the location optimization step size and the capacity optimization step size; S42. Using the location optimization step size and capacity optimization step size, adjust the first grid-type energy storage configuration scheme, calculate and generate a score and discrimination, and obtain a second grid-type energy storage configuration scheme that meets the score generation threshold. S43. Process and obtain the second configuration fitness of the second grid-type energy storage configuration scheme; S44. Continue to iteratively optimize the grid-type energy storage configuration scheme. After convergence, obtain the optimal grid-type energy storage configuration scheme with the greatest configuration fitness, which is taken as the optimization result of the grid-type energy storage configuration.

[0061] In a preferred embodiment, the capacity update parameter is specifically the capacity optimization step size, and the coordinate update parameter is specifically the location optimization step size. First, the location optimization step size and capacity optimization step size are configured based on the dispersion of meteorological change parameters. The location optimization step size controls the adjustment range of the configured coordinates in each iteration, and the capacity optimization step size controls the adjustment range of the configured capacity in each iteration. Specifically, the dispersion of meteorological change is calculated based on the distribution of meteorological change parameters. This dispersion reflects the degree of spatial distribution difference of meteorological fluctuations within the target area. When the dispersion is large, it indicates significant differences in meteorological fluctuations at different locations, and the optimization space for the configuration scheme is large. In this case, a larger location optimization step size and capacity optimization step size should be used to accelerate the optimization process. When the dispersion is small, it indicates that meteorological fluctuations at each location are relatively uniform, and the adjustment of the configuration scheme needs to be more refined. In this case, a smaller location optimization step size and capacity optimization step size should be used to achieve refined optimization. Through this adaptive step size setting method, the optimization strategy can be dynamically adjusted according to the meteorological fluctuation characteristics of the target area, improving the efficiency and effectiveness of iterative optimization.

[0062] Subsequently, using location optimization step size and capacity optimization step size, the first grid-type energy storage configuration scheme is adjusted, and a score is calculated and judged to obtain a second grid-type energy storage configuration scheme that meets the score generation threshold. Specifically, based on the location optimization step size, multiple first configuration coordinates in the first grid-type energy storage configuration scheme are adjusted, for example, by selecting new configuration coordinates within the neighborhood of the current configuration coordinates, the size of which is determined by the location optimization step size. Simultaneously, based on the capacity optimization step size, the capacities of multiple first configurations are adjusted, for example, by redistributing capacity among the energy storage units, the adjustment magnitude controlled by the capacity optimization step size, but ensuring that the sum of the capacities of all energy storage units after adjustment still equals the total energy storage capacity. Through these adjustment operations, a new candidate configuration scheme is generated. To ensure that the adjusted configuration scheme still has basic rationality, the generation score of the candidate configuration scheme needs to be calculated based on the distribution of meteorological change parameters, and it needs to be determined whether it meets the score generation threshold. If the scoring threshold is met, the candidate configuration scheme is adopted as the second grid-type energy storage configuration scheme; if the scoring threshold is not met, the optimization strategy is adjusted or the configuration is readjusted until a configuration scheme that meets the scoring threshold is obtained. The second grid-type energy storage configuration scheme includes multiple second configuration coordinates and multiple second configuration capacities.

[0063] Next, the second configuration fitness of the second grid-type energy storage configuration scheme is obtained. Specifically, using the same method as calculating the first configuration fitness, multiple second meteorological change parameters are retrieved based on the distribution of meteorological change parameters under multiple second configuration coordinates. Then, based on the multiple second meteorological change parameters and multiple second configuration capacities, the second configuration fitness of the second grid-type energy storage configuration scheme is calculated. The second configuration fitness is used to evaluate the merits of the configuration scheme after one iteration of adjustment. By comparing the second configuration fitness with the first configuration fitness, the effectiveness of this iteration of optimization can be determined. If the second configuration fitness is greater than the first configuration fitness, it indicates that the performance of the configuration scheme has improved after adjustment, and the optimization direction is correct; if the second configuration fitness is less than or equal to the first configuration fitness, it indicates that this adjustment has failed to improve the configuration scheme, and the optimization strategy needs to be adjusted.

[0064] Subsequently, iterative optimization of the grid-based energy storage configuration scheme continues. After convergence, the optimal grid-based energy storage configuration scheme with the highest configuration fitness is obtained as the optimization result. Specifically, the second grid-based energy storage configuration scheme is used as the new current configuration scheme, and the iterative optimization process from steps S41 to S43 is repeated. The configuration coordinates and configuration capacity are continuously adjusted, and the configuration fitness of the configuration scheme is calculated after each iteration. During the iteration process, the configuration scheme with the highest configuration fitness is recorded. Iterative optimization continues until the convergence condition is met. The convergence condition can be set as follows: the improvement in configuration fitness is less than a preset threshold, the configuration fitness does not improve after multiple consecutive iterations, or the maximum number of iterations is reached. When the convergence condition is met, the iterative optimization process ends, and the configuration scheme with the highest configuration fitness during the iteration process is selected as the optimal grid-based energy storage configuration scheme. This optimal grid-based energy storage configuration scheme is the optimization result of the grid-based energy storage configuration. It contains the optimal configuration coordinates and configuration capacity, can adapt to the meteorological fluctuation characteristics of the target area to the greatest extent, effectively cope with the impact of meteorological changes on power generation, and ensure the stable operation of the power grid.

[0065] Through the aforementioned iterative optimization process, continuous improvement and optimization of the grid-based energy storage configuration scheme were achieved. The adaptive step-size setting mechanism dynamically adjusts optimization parameters based on meteorological fluctuation characteristics, improving optimization efficiency; the generation scoring and screening mechanism ensures that the configuration schemes generated in each iteration are basically reasonable, avoiding ineffective iterations; and the configuration fitness evaluation mechanism provides clear quantitative targets and evaluation standards for optimization. Multiple iterative optimizations gradually converge the configuration scheme to the optimal state. The final optimal grid-based energy storage configuration scheme achieves the best match between the configuration location and capacity and the distribution of meteorological change parameters, enhancing the grid-based energy storage system's ability to cope with meteorological fluctuations, effectively avoiding local energy storage instability, and improving the accuracy of configuration and the stability of grid operation.

[0066] Furthermore, based on the dispersion of meteorological changes in the distribution of meteorological change parameters, the location optimization step size and capacity optimization step size are configured, including: S411. Obtain the preset position step size and preset capacity step size; S412. Obtain the average dispersion of meteorological changes over historical periods; S413. Based on the ratio of the average meteorological variation dispersion to the meteorological variation dispersion, adjust the preset position step size and preset capacity step size to obtain the optimized position step size and optimized capacity step size.

[0067] In a preferred embodiment, firstly, a preset location step size and a preset capacity step size are obtained. These preset location and capacity step sizes are pre-defined baseline step size values ​​that serve as the basis for adaptive adjustment. The preset location step size defines the baseline range for adjusting the configuration coordinates; for example, it is set to twice the grid spacing of the target area. When the target area is divided into 1 km × 1 km grids, the preset location step size can be set to 2 km. The preset capacity step size defines the baseline range for adjusting the configuration capacity; for example, it is set to 5% of the total energy storage capacity. When the total energy storage capacity is 100 MWh, the preset capacity step size is 5 MWh. The preset location and capacity step sizes can be set by experts according to the actual situation of the target area, providing a reference baseline for subsequent adaptive adjustment.

[0068] Subsequently, the average meteorological variation dispersion over historical periods is obtained. This historical average meteorological variation dispersion reflects the historical average level of meteorological fluctuation distribution in the target area, serving as a benchmark for assessing the current meteorological variation dispersion. Specifically, the meteorological variation dispersion over multiple historical periods, such as the past year or several months, is statistically analyzed, and the average of these historical meteorological variation dispersions is calculated to obtain the average meteorological variation dispersion. The average meteorological variation dispersion reflects the typical characteristics of meteorological fluctuation distribution in the target area, providing a basis for determining whether the current meteorological variation dispersion is higher or lower than normal.

[0069] Next, based on the ratio of the average meteorological variation dispersion to the total meteorological variation dispersion, the preset location step size and preset capacity step size are adjusted to obtain the optimized location step size and optimized capacity step size. Specifically, the ratio of the current meteorological variation dispersion to the average meteorological variation dispersion is calculated, and this ratio serves as the step size adjustment coefficient. When the meteorological variation dispersion is greater than the average meteorological variation dispersion, the ratio is greater than 1, indicating that the current meteorological fluctuation distribution in the target area is more volatile than the historical average, and the optimization space for the configuration scheme is larger, requiring a larger optimization step size. When the meteorological variation dispersion is less than the average meteorological variation dispersion, the ratio is less than 1, indicating that the current meteorological fluctuation distribution is less volatile than the historical average, and the configuration scheme requires fine adjustment, requiring a smaller optimization step size. Multiplying the step size adjustment coefficient by the preset location step size and preset capacity step size respectively yields the optimized location step size and optimized capacity step size. For example, the optimized location step size = preset location step size × (meteorological variation dispersion / average meteorological variation dispersion), and the optimized capacity step size = preset capacity step size × (meteorological variation dispersion / average meteorological variation dispersion). Through an adaptive adjustment mechanism, the optimization step size can be dynamically changed according to the current meteorological fluctuation distribution characteristics. When the differences in meteorological fluctuation distribution are significant, the optimization speed is accelerated, and when the meteorological fluctuation distribution is relatively uniform, fine optimization is performed, which improves the pertinence and efficiency of iterative optimization.

[0070] Through the above steps, an adaptive step-size adjustment mechanism based on historical average levels was established. This mechanism considers not only the absolute value of the current meteorological variation dispersion but also its deviation from the historical average level, thereby setting the optimization step-size. Compared to a fixed step-size, the adaptive step-size can be flexibly adjusted according to different meteorological fluctuation scenarios. It accelerates convergence speed in scenarios with large meteorological fluctuation differences and improves optimization accuracy in scenarios with small meteorological fluctuation differences, effectively balancing optimization efficiency and optimization quality. This ensures that the iterative optimization process can quickly and accurately converge to the optimal grid-type energy storage configuration scheme, improving the overall performance of configuration optimization.

[0071] Example 2, as Figure 2 As shown, based on the same inventive concept as the multi-objective optimization-based grid-type energy storage configuration method provided in Embodiment 1, this embodiment of the invention also provides a multi-objective optimization-based grid-type energy storage configuration system, including: Meteorological data acquisition module 11 is used to acquire the distribution sequence of meteorological parameters within a preset time range in the target area and calculate the distribution of meteorological change parameters. The random configuration generation module 12 is used to obtain the configuration resource pool for grid-type energy storage configuration in the target area, and randomly configure grid-type energy storage units in the target area according to the distribution of meteorological change parameters to obtain a first grid-type energy storage configuration scheme, wherein the first grid-type energy storage configuration scheme includes multiple first configuration coordinates and multiple first configuration capacities. The fitness analysis module 13 is used to analyze the first configuration fitness of the first grid-type energy storage configuration scheme according to the distribution of meteorological change parameters, wherein the first configuration fitness is calculated according to the fitness of each first configuration capacity and the meteorological change parameters under the corresponding first configuration coordinates; The iterative optimization module 14 is used to set the capacity update parameters and coordinate update parameters in each iteration according to the distribution of the meteorological change parameters, and to perform iterative optimization of the grid-type energy storage configuration scheme to obtain the optimal grid-type energy storage configuration scheme as the grid-type energy storage configuration optimization result.

[0072] Furthermore, the execution steps of the meteorological data acquisition module 11 include: Obtain the distribution of meteorological parameters for multiple time points within a preset time range in the target area. Each meteorological parameter distribution includes meteorological parameters for all location coordinates within the target area. The meteorological parameter distributions at multiple time points are arranged according to time to obtain a meteorological parameter distribution sequence; The distribution of meteorological change parameters is calculated based on the meteorological parameter distribution sequence.

[0073] Furthermore, the execution steps of the meteorological data acquisition module 11 also include: Based on the meteorological parameter distribution sequence, the maximum variation range of the meteorological parameters at each location coordinate is calculated and used as the meteorological change parameter; A distribution of meteorological change parameters is generated based on meteorological change parameters of all location coordinates.

[0074] Furthermore, the execution steps of the random configuration generation module 12 include: Obtain the configuration resource pool for grid-type energy storage configuration in the target area, wherein the configuration resource pool includes the number of grid-type energy storage units and the total energy storage capacity; According to the number of grid-type energy storage units, multiple candidate first configuration coordinates are randomly selected within the target area, and the total energy storage capacity is allocated to obtain multiple candidate first configuration capacities, which are used as the first candidate grid-type energy storage configuration schemes. Based on the distribution of meteorological change parameters, calculate the first generation score of the first candidate grid-type energy storage configuration scheme, and determine whether it meets the generation score threshold. If it does, it is adopted as the first grid-type energy storage configuration scheme; otherwise, the grid-type energy storage unit configuration is re-performed.

[0075] Furthermore, the execution steps of the random configuration generation module 12 also include: The dispersion of meteorological changes is calculated based on the distribution of the meteorological change parameters. Calculate the dispersion of multiple candidate first configuration capacities to obtain the dispersion of the first candidate capacity; Calculate the similarity between the dispersion of the first candidate capacity and the dispersion of meteorological changes, and use it as the first generated score.

[0076] Furthermore, the execution steps of the fitness analysis module 13 include: Based on the distribution of meteorological change parameters, retrieve multiple first meteorological change parameters under the multiple first configuration coordinates; Based on multiple first meteorological change parameters and multiple first configuration capacities, the first configuration adaptability of the first grid-type energy storage configuration scheme is calculated.

[0077] Furthermore, the execution steps of the fitness analysis module 13 also include: The ratio of the mean of multiple first meteorological change parameters to the maximum value of the meteorological change parameters is calculated as the first stable configuration score; Based on the ratio of multiple first configuration capacities to the total energy storage capacity, multiple first capacity coefficients are obtained. The ratio of each first meteorological change parameter to the sum of multiple first meteorological change parameters is calculated to obtain multiple first meteorological change coefficients. Calculate the similarity between multiple first capacity coefficients and multiple first meteorological change coefficients to obtain the first adaptation configuration score; Calculate the ratio of the minimum to the maximum value within the distribution of the meteorological change parameters, using it as a stability weight, and then calculate the adaptation weight; The first stable configuration score and the first adapted configuration score are weighted and calculated using the stability weight and the adaptation weight to obtain the first configuration fitness.

[0078] Furthermore, the execution steps of the iterative optimization module 14 include: Based on the dispersion of meteorological changes in the distribution of meteorological change parameters, configure the location optimization step size and the capacity optimization step size; Using the aforementioned location optimization step size and capacity optimization step size, the first grid-type energy storage configuration scheme is adjusted, and a score and discrimination are calculated to obtain a second grid-type energy storage configuration scheme that meets the score generation threshold. Process and obtain the second configuration fitness of the second grid-type energy storage configuration scheme; Continue iterative optimization of the grid-type energy storage configuration scheme. After convergence, obtain the optimal grid-type energy storage configuration scheme with the greatest configuration fitness, which is taken as the optimization result of the grid-type energy storage configuration.

[0079] Furthermore, the execution steps of the iterative optimization module 14 also include: Obtain the preset position step size and preset capacity step size; Obtain the average dispersion of meteorological changes over a historical period; Based on the ratio of the average meteorological variation dispersion to the meteorological variation dispersion, the preset location step size and preset capacity step size are adjusted to obtain the location optimization step size and capacity optimization step size.

[0080] It should be noted that the descriptions of each embodiment in the above embodiments have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0081] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0082] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0083] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0084] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0085] Although preferred embodiments of the invention have been described, those skilled in the art, once they have learned the basic inventive concept, can make other changes and modifications to these embodiments.

[0086] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of this invention and its equivalents, this invention also intends to include these modifications and variations.

Claims

1. A grid-based energy storage configuration method based on multi-objective optimization, characterized in that, The method includes: Obtain the distribution sequence of meteorological parameters within a preset time range in the target area, and calculate the distribution of meteorological change parameters; A configuration resource pool for grid-type energy storage configuration in the target area is obtained. Based on the distribution of meteorological change parameters, grid-type energy storage units are randomly configured in the target area to obtain a first grid-type energy storage configuration scheme, wherein the first grid-type energy storage configuration scheme includes multiple first configuration coordinates and multiple first configuration capacities. Based on the distribution of meteorological change parameters, the first configuration fitness of the first grid-type energy storage configuration scheme is analyzed, wherein the first configuration fitness is calculated based on the fitness of each first configuration capacity and the meteorological change parameters under the corresponding first configuration coordinates; Based on the distribution of meteorological change parameters, the capacity update parameters and coordinate update parameters are set in each iteration to iteratively optimize the grid-type energy storage configuration scheme and obtain the optimal grid-type energy storage configuration scheme as the optimization result of the grid-type energy storage configuration.

2. The grid-based energy storage configuration method based on multi-objective optimization according to claim 1, characterized in that, Obtain the distribution sequence of meteorological parameters within a preset time range in the target area, and calculate the distribution of meteorological change parameters, including: Obtain the distribution of meteorological parameters for multiple time points within a preset time range in the target area. Each meteorological parameter distribution includes meteorological parameters for all location coordinates within the target area. The meteorological parameter distributions at multiple time points are arranged according to time to obtain a meteorological parameter distribution sequence; The distribution of meteorological change parameters is calculated based on the meteorological parameter distribution sequence.

3. The grid-based energy storage configuration method based on multi-objective optimization according to claim 2, characterized in that, Based on the meteorological parameter distribution sequence, the distribution of meteorological change parameters is calculated, including: Based on the meteorological parameter distribution sequence, the maximum variation range of the meteorological parameters at each location coordinate is calculated and used as the meteorological change parameter; A distribution of meteorological change parameters is generated based on meteorological change parameters of all location coordinates.

4. The grid-type energy storage configuration method based on multi-objective optimization according to claim 1, characterized in that, Obtain a configuration resource pool for grid-type energy storage configuration in the target area. Based on the distribution of meteorological change parameters, randomly configure grid-type energy storage units within the target area to obtain a first grid-type energy storage configuration scheme, including: Obtain the configuration resource pool for grid-type energy storage configuration in the target area, wherein the configuration resource pool includes the number of grid-type energy storage units and the total energy storage capacity; According to the number of grid-type energy storage units, multiple candidate first configuration coordinates are randomly selected within the target area, and the total energy storage capacity is allocated to obtain multiple candidate first configuration capacities, which are used as the first candidate grid-type energy storage configuration scheme. Based on the distribution of meteorological change parameters, calculate the first generation score of the first candidate grid-type energy storage configuration scheme, and determine whether it meets the generation score threshold. If it does, it is adopted as the first grid-type energy storage configuration scheme; otherwise, the grid-type energy storage unit configuration is re-performed.

5. The grid-based energy storage configuration method based on multi-objective optimization according to claim 4, characterized in that, Based on the distribution of meteorological change parameters, the first generation score of the first candidate grid-type energy storage configuration scheme is calculated, including: The dispersion of meteorological changes is calculated based on the distribution of the meteorological change parameters. Calculate the dispersion of multiple candidate first configuration capacities to obtain the dispersion of the first candidate capacity; Calculate the similarity between the dispersion of the first candidate capacity and the dispersion of meteorological changes, and use it as the first generated score.

6. The grid-based energy storage configuration method based on multi-objective optimization according to claim 1, characterized in that, Based on the distribution of the meteorological change parameters, the first configuration fitness of the first grid-type energy storage configuration scheme is analyzed, including: Based on the distribution of meteorological change parameters, retrieve multiple first meteorological change parameters under the multiple first configuration coordinates; Based on multiple first meteorological change parameters and multiple first configuration capacities, the first configuration adaptability of the first grid-type energy storage configuration scheme is calculated.

7. The grid-based energy storage configuration method based on multi-objective optimization according to claim 6, characterized in that, Based on multiple first meteorological change parameters and multiple first configuration capacities, the first configuration fitness of the first grid-type energy storage configuration scheme is calculated, including: The ratio of the mean of multiple first meteorological change parameters to the maximum value of the meteorological change parameters is calculated as the first stable configuration score; Based on the ratio of multiple first configuration capacities to the total energy storage capacity, multiple first capacity coefficients are obtained. The ratio of each first meteorological change parameter to the sum of multiple first meteorological change parameters is calculated to obtain multiple first meteorological change coefficients. Calculate the similarity between multiple first capacity coefficients and multiple first meteorological change coefficients to obtain the first adaptation configuration score; Calculate the ratio of the minimum to the maximum value within the distribution of the meteorological change parameters, using it as a stability weight, and then calculate the adaptation weight; The first stable configuration score and the first adapted configuration score are weighted and calculated using the stability weight and the adaptation weight to obtain the first configuration fitness.

8. The grid-based energy storage configuration method based on multi-objective optimization according to claim 1, characterized in that, Based on the distribution of meteorological change parameters, capacity update parameters and coordinate update parameters are set for each iteration to iteratively optimize the grid-type energy storage configuration scheme, obtaining the optimal grid-type energy storage configuration scheme as the optimization result, including: Based on the dispersion of meteorological changes in the distribution of meteorological change parameters, configure the location optimization step size and the capacity optimization step size; Using the aforementioned location optimization step size and capacity optimization step size, the first grid-type energy storage configuration scheme is adjusted, and a score and discrimination are calculated to obtain a second grid-type energy storage configuration scheme that meets the score generation threshold. Process and obtain the second configuration fitness of the second grid-type energy storage configuration scheme; Continue iterative optimization of the grid-type energy storage configuration scheme. After convergence, obtain the optimal grid-type energy storage configuration scheme with the greatest configuration fitness, which is taken as the optimization result of the grid-type energy storage configuration.

9. The grid-based energy storage configuration method based on multi-objective optimization according to claim 8, characterized in that, Based on the dispersion of meteorological changes in the distribution of meteorological change parameters, configure the location optimization step size and capacity optimization step size, including: Obtain the preset position step size and preset capacity step size; Obtain the average dispersion of meteorological changes over a historical period; Based on the ratio of the average meteorological variation dispersion to the meteorological variation dispersion, the preset location step size and preset capacity step size are adjusted to obtain the location optimization step size and capacity optimization step size.

10. A grid-based energy storage configuration system based on multi-objective optimization, characterized in that, For implementing the multi-objective optimization-based grid-type energy storage configuration method as described in any one of claims 1 to 9, the system comprises: The meteorological data acquisition module is used to acquire the distribution sequence of meteorological parameters within a preset time range in the target area and calculate the distribution of meteorological change parameters. A random configuration generation module is used to obtain a configuration resource pool for grid-type energy storage configuration in a target area. Based on the distribution of meteorological change parameters, grid-type energy storage units are randomly configured in the target area to obtain a first grid-type energy storage configuration scheme. The first grid-type energy storage configuration scheme includes multiple first configuration coordinates and multiple first configuration capacities. The fitness analysis module is used to analyze the first configuration fitness of the first grid-type energy storage configuration scheme according to the distribution of meteorological change parameters, wherein the first configuration fitness is calculated based on the fitness of each first configuration capacity and the meteorological change parameters under the corresponding first configuration coordinates; The iterative optimization module is used to set the capacity update parameters and coordinate update parameters in each iteration according to the distribution of meteorological change parameters, and to perform iterative optimization of the grid-type energy storage configuration scheme to obtain the optimal grid-type energy storage configuration scheme as the grid-type energy storage configuration optimization result.

Images