Optical storage capacity configuration optimization decision-making method based on evolution calculation

Abstract

The invention provides an optical storage capacity configuration optimization decision-making method based on evolution calculation, and the method comprises the steps: constructing an optical storage system simulation model, and enabling the optical storage system simulation model to change according to a simulation output result generated by input data when the capacity ratio and the energy storage configuration capacity of the optical storage system simulation model are changed; a pre-constructed optimization model is utilized to iteratively optimize the capacity ratio and the energy storage configuration capacity of the optical storage system simulation model for multiple times until a stop condition is met, during each iteration, a simulation output result of the optical storage system simulation model at the current time is input into the optimization model, the optimization model outputs a new capacity ratio and energy storage configuration capacity, and the optimization model outputs the new energy storage configuration capacity. And taking the new capacity ratio and the energy storage configuration capacity as the capacity ratio and the energy storage configuration capacity of the optical storage system simulation model of the next iteration. The adaptability to actual operation conditions can be enhanced, and the accuracy of the model can be improved.

Description

Technical Field

[0001] The present application belongs to the field of renewable energy power generation technology, and specifically, relates to a photovoltaic storage capacity configuration optimization decision method based on evolutionary computing. Background Art

[0002] With the transformation of the global energy structure and the rapid development of renewable energy, the photovoltaic storage system (the combination of photovoltaic power generation and energy storage system) has become an important technical means to improve energy utilization efficiency and enhance the stability of the power grid. Photovoltaic power generation depends on natural light conditions and is intermittent and unstable, while the energy storage system can smooth the fluctuations of photovoltaic power generation and improve the reliability of energy supply. The optimized operation of the photovoltaic storage system is of great significance for achieving efficient energy management and reducing costs.

[0003] Photovoltaic power station storage is the main way for the development of photovoltaic power stations in the future. However, for photovoltaic power stations in different regions, with different power restriction rates and different equipment parameters, how to reasonably configure energy storage to achieve the designed utilization hours and maximize the benefits requires scientific technical and economic analysis and capacity optimization research. The optimization of the photovoltaic storage system needs to consider many factors, including the volatility of photovoltaic power generation, the charging and discharging efficiency of the energy storage system, and the dynamic changes in grid demand. Traditional optimization methods may find it difficult to cope with the complexity and variability of these factors. In recent years, the development of artificial intelligence and computational intelligence technologies has provided new ideas and tools for solving these problems. Summary of the invention

[0004] The technical problem solved by the present application is: how to provide a more accurate and adaptable method for optimizing the configuration of photovoltaic storage capacity based on evolutionary computing.

[0005] The present application provides a method for optimizing the configuration of a photovoltaic storage capacity based on evolutionary computing, and the method for optimizing the configuration of a photovoltaic storage capacity includes:

[0006] Constructing a photovoltaic storage system simulation model. When the capacity ratio and energy storage configuration capacity of the photovoltaic storage system simulation model change, the simulation output result generated by the photovoltaic storage system simulation model according to the input data changes.

[0007] The capacity ratio and energy storage configuration capacity of the photovoltaic storage system simulation model are optimized multiple times by using a pre-built optimization model until the stopping condition is met, wherein in each iteration, the simulation output result of the current photovoltaic storage system simulation model is input into the optimization model, and the optimization model outputs a new capacity ratio and energy storage configuration capacity, which are used as the capacity ratio and energy storage configuration capacity of the photovoltaic storage system simulation model of the next iteration.

[0008] Optionally, the input data includes meteorological data, historical output data and system configuration data, and the simulation output results include the output, power generation and utilization hours of the photovoltaic storage system.

[0009] Optionally, the simulation operation mode of the photovoltaic energy storage system simulation model includes an energy storage fixed boundary operation mode and an energy storage peak shaving and valley filling operation mode.

[0010] Optionally, the optical storage capacity configuration optimization decision method further includes:

[0011] The photovoltaic storage system simulation model is calibrated according to the measured data.

[0012] Optionally, the method for calibrating the photovoltaic storage system simulation model according to measured data includes:

[0013] After running the photovoltaic storage system simulation model, the simulation output results of the photovoltaic storage system simulation model are compared and analyzed with the measured data;

[0014] The model parameters of the photovoltaic storage system simulation model are adjusted according to the results of the comparative analysis.

[0015] Optionally, the optimization model is a model based on a multi-objective particle swarm optimization algorithm, and the optimization objectives of the optimization model include economic indicators, utilization hours and power generation.

[0016] Optionally, the economic indicators include levelized cost per kilowatt-hour, net present value, internal rate of return and return on investment.

[0017] The present application provides a method for optimizing the configuration of optical storage capacity based on evolutionary computing, which has the following technical effects:

[0018] (1) Technology integration and simulation accuracy: Compared with traditional optimization methods, this application provides a more accurate and comprehensive simulation of the photovoltaic storage system by integrating on-site meteorological data, photovoltaic configuration and equipment operating parameters. This highly data-driven approach not only enhances the adaptability of the model to actual operating conditions, but also through simulation, it can comprehensively evaluate the output, power generation and utilization hours of different configuration schemes throughout the life cycle of the system, thereby providing decision makers with more in-depth performance insights.

[0019] (2) Economic evaluation and multi-objective optimization: This application adopts a comprehensive parameter calculation method for economic evaluation, including levelized cost of electricity (LCOE), net present value (NPV), internal rate of return (IRR) and return on investment (ROI), providing a solid financial analysis basis for investment decisions. In addition, the multi-objective optimization achieved by the multi-objective particle swarm optimization algorithm (MOPSO) can simultaneously consider system performance and economy, balance costs and benefits, and achieve comprehensive optimization, which is unmatched by single-objective optimization methods.

[0020] (3) Model calibration and decision reliability: Compared with the prior art, a prominent advantage of this application is its model calibration mechanism. By comparing with the measured data, this application not only ensures the accuracy and reliability of the simulation model, but also improves the credibility of the optimization decision through this calibration process. This data-centric calibration method significantly improves the predictive ability of the model and ensures the practicality and effectiveness of the optimization results, thereby providing more reliable decision support for the planning and operation of the photovoltaic storage system. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 A flow chart of the main steps of a method for optimizing the configuration of optical storage capacity based on evolutionary computing according to one or more embodiments;

[0022] Figure 2 is a flow chart of a fixed boundary operation mode of energy storage according to one or more embodiments;

[0023] Figure 3 A flowchart of an energy storage peak shaving and valley filling operation mode according to one or more embodiments;

[0024] Figure 4 FIG. 4 is a schematic diagram of a process for updating particle positions and velocities according to one or more embodiments. DETAILED DESCRIPTION

[0025] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0026] Before describing in detail the various embodiments of the present application, the technical concept of the present application is first briefly described: At present, when optimizing the storage configuration of photovoltaic power stations, multiple factors need to be considered. Traditional optimization methods are difficult to cope with the complexity and variability of these factors, so it is difficult to obtain more accurate optimization parameters. To this end, the present application provides a photovoltaic storage capacity configuration optimization decision method based on evolutionary computing, which constructs a photovoltaic storage system simulation model and an optimization model. When the capacity ratio and energy storage configuration capacity of the photovoltaic storage system simulation model change, the simulation output results generated by the photovoltaic storage system simulation model according to the input data change. The photovoltaic storage system simulation model continuously generates simulation output results based on the input data. The optimization model is used to iterate and optimize multiple times to obtain the optimal combination of the capacity ratio and energy storage configuration capacity of the photovoltaic storage system simulation model. This method can enhance the adaptability to actual operating conditions and is conducive to improving the accuracy of the model. The specific principles of the photovoltaic storage capacity configuration optimization decision method based on evolutionary computing of the present application are described below in conjunction with more embodiments.

[0027] Specifically, Figure 1 As shown, the optical storage capacity configuration optimization decision method based on evolutionary computing of the first embodiment includes:

[0028] Step S10: constructing a photovoltaic storage system simulation model. When the capacity ratio and energy storage configuration capacity of the photovoltaic storage system simulation model change, the simulation output result generated by the photovoltaic storage system simulation model according to the input data changes.

[0029] Step S20: Utilize the pre-built optimization model to iteratively optimize the capacity ratio and energy storage configuration capacity of the photovoltaic storage system simulation model multiple times until the stopping condition is met, wherein in each iteration, the simulation output result of the current photovoltaic storage system simulation model is input into the optimization model, and the optimization model outputs a new capacity ratio and energy storage configuration capacity, which are used as the capacity ratio and energy storage configuration capacity of the photovoltaic storage system simulation model of the next iteration.

[0030] In one or more embodiments, the input data includes meteorological data, historical output data, and system configuration data. Exemplarily, meteorological data include irradiance, temperature, location, humidity, and wind speed, which are crucial for predicting the power generation of the photovoltaic storage system; historical output data are used to analyze and predict the power generation performance of the photovoltaic system; system configuration data include photovoltaic system configuration, energy storage capacity, capacity ratio (configuration ratio of photovoltaic and inverter), etc., which affect the power generation and operation efficiency of the system, among which the energy storage capacity and capacity ratio have the greatest impact on the simulation model and are the parameters that need to be optimized most in the photovoltaic storage power station. Therefore, the optimization model of this embodiment mainly optimizes these two parameters. The simulation output results include the output, power generation, and utilization hours of the photovoltaic storage system during its life cycle, which can be used to evaluate the system performance of the model.

[0031] In one or more embodiments, the photovoltaic storage capacity configuration optimization decision method further includes: calibrating the photovoltaic storage system simulation model according to the measured data. Specifically, after running the simulation model, the simulation output results of the photovoltaic storage system simulation model are compared and analyzed with the measured data; and the model parameters of the photovoltaic storage system simulation model are adjusted according to the results of the comparative analysis. When using the measured data to calibrate the photovoltaic storage system simulation model, the collected field data include meteorological data, equipment operating parameters, photovoltaic panel output power and other measured data as a benchmark. Then, the photovoltaic storage system simulation model is run based on the initial parameter settings. After running the model, the simulation output is compared with the measured data, and the difference is analyzed by correlation analysis, mean square error and deviation analysis. The model is calibrated according to the comparison results, and the parameters are adjusted to reduce the difference between the simulation and the actual measurement. Multiple iterations may be required to reach an acceptable error range. By comparing with the measured data, not only the accuracy and reliability of the simulation model are ensured, but also the credibility of the optimization decision is improved through this calibration process. This data-centric calibration method significantly improves the predictive ability of the model, ensures the practicality and effectiveness of the optimization results, and thus provides more reliable decision support for the planning and operation of the photovoltaic storage system.

[0032] In one or more embodiments, the simulation operation mode of the photovoltaic energy storage system simulation model includes an energy storage fixed boundary operation mode and an energy storage peak shaving and valley filling operation mode.

[0033] For example, Figure 2 As shown, the energy storage fixed boundary operation mode is as follows:

[0034] First, determine the fixed boundary of energy storage charging and discharging, which is generally set to the AC power multiplied by a coefficient. Determine the relative size of the photovoltaic output power on the DC side and the fixed boundary.

[0035] ① If the photovoltaic output power is greater than the fixed boundary, the energy storage charging judgment is performed. At this time, if the energy storage state of charge SOC is less than 100%, charging is performed to determine whether the absolute value of the difference between the photovoltaic output power and the fixed boundary is less than the maximum charge and discharge power of the energy storage. If it is less than, the energy storage charging power is equal to Pn_inv*r-Ppv (that is, the fixed threshold of energy storage operation minus the photovoltaic output power). Otherwise, the energy storage charging power is equal to the maximum charging power; if the energy storage state of charge SOC is 100%, the energy storage power is 0;

[0036] ② If the photovoltaic output power is less than the fixed boundary, the energy storage discharge judgment is performed. At this time, if the energy storage charge state SOC is greater than 5%, charging is performed to determine whether the absolute value of the difference between the photovoltaic output power and the fixed boundary is less than the maximum charge and discharge power of the energy storage. If it is less than, the energy storage charging power is equal to Pn_inv*r-Ppv, otherwise the energy storage charging power is equal to the maximum discharge power; if the energy storage charge state SOC is 5%, the energy storage power is 0. Figure 3 As shown, the energy storage peak shaving and valley filling operation mode:

[0037] The system receives photovoltaic output data, photovoltaic storage system configuration information and power grid load limit instruction data (which can be replaced by a typical load limit curve). First, the relationship between photovoltaic output power and load limit instruction (Load) is determined.

[0038] If the photovoltaic output power (P PV ) is greater than the power limit instruction (P load ), then perform energy storage charging judgment: if the energy storage state of charge (SOC) is less than 100%, then charge. Determine whether the absolute value of the difference between the photovoltaic output power and the fixed boundary is less than the maximum charge and discharge power (P BESSmax ), if so, the energy storage charging power is P BESS =P load -P PV ; Otherwise, the energy storage charging power is P BESS =-P BESSmax ; If the energy storage SOC is 100%, the energy storage power P BESS =0.

[0039] If the PV output power is less than the power limit instruction (P load ), then the energy storage discharge judgment is performed: if the energy storage SOC is greater than 5%, discharge is performed. Determine whether the absolute value of the difference between the photovoltaic output power and the fixed boundary is less than the maximum charge and discharge power of the energy storage. If so, the energy storage discharge power is P BESS =P load -P PV ; If not, the energy storage discharge power is P BESSmax If the energy storage SOC is 5%, the energy storage power P BESS =0.

[0040] Next, calculate the output power: If the energy storage system is charging, the system output power P system =P load If the energy storage system is discharging or not charging or discharging, the system output power is equal to the sum of the photovoltaic power generation power and the energy storage system power: P system =PV output =P PV +P BESS .

[0041] By integrating on-site meteorological data, photovoltaic configuration and equipment operating parameters, a more accurate and comprehensive simulation is provided for the photovoltaic storage system. This highly data-driven approach not only enhances the adaptability of the model to actual operating conditions, but also through simulation, it can comprehensively evaluate the output, power generation and utilization hours of different configuration schemes throughout the life cycle of the system, thus providing decision makers with more in-depth performance insights.

[0042] In one or more embodiments, the optimization model is a model based on a multi-objective particle swarm optimization algorithm, and the optimization objectives of the optimization model include economic indicators, utilization hours, and power generation. The economic indicators include levelized cost of electricity, net present value, internal rate of return, and return on investment.

[0043] Specifically, the levelized cost of electricity (LCOE) is a standardized method to measure the cost per unit of electricity of a photovoltaic storage system over its entire life cycle. It comprehensively considers factors such as photovoltaic equipment cost, energy storage equipment cost, photovoltaic operation and maintenance costs, energy storage operation and maintenance costs, capital cost, tax costs, and operating years. i is the discount rate, E n is the total power generation of the project. LCOE provides a standardized unit electricity cost indicator, which allows the economics of different energy projects to be directly compared. It not only takes into account capital costs and operation and maintenance costs, but also takes into account the time value, making it a core tool for measuring the economics of power projects. The lower the LCOE, the lower the power production cost of the project and the better the economics. The calculation formula is as follows:

[0044]

[0045] Among them, the cost of photovoltaic equipment C PV 、Energy storage equipment cost C ES , Photovoltaic operation and maintenance costs PV , Energy storage operation and maintenance costs ES , Capital cost C F , Tax cost C tax , Equipment attenuation cost C d , operation year n, N is the life of the power plant, i is the discount rate, E n is the total power generation of the project, V R It is the residual value at the end of the project, that is, the estimated value of the project at the end of its life.

[0046] For example, Net Present Value (NPV) is an important indicator in project financial analysis. It evaluates the overall profitability of a project by discounting all expected future cash flows to current value and comparing it with the initial investment. A positive NPV value indicates that the project is expected to bring positive economic returns, that is, the project is profitable at the current discount rate. The size of NPV directly reflects the financial health of the project. A higher NPV value usually means a better potential for return on investment. The calculation formula is as follows:

[0047]

[0048] Among them, C t is the net cash flow in year t, i is the discount rate, n represents the year, and C0 is the initial investment cost.

[0049] For example, the internal rate of return (IRR) is the discount rate that makes the net present value (NPV) of the project equal to zero, reflecting the potential profitability of the project. IRR indicates the annualized rate of return of the project. If the IRR is higher than the capital cost or the minimum acceptable rate of return of the project, it means that the project has good investment value. IRR higher than the capital cost means that the project has a higher profit potential. Investors usually choose projects with high IRR. The calculation formula is as follows:

[0050]

[0051] Where IRR is the discount rate that makes the project's net present value (NPV) equal to zero. i1 and i2 are two different discount rates; NPV1 is the net present value calculated at discount rate i1; NPV2 is the net present value calculated at discount rate i2.

[0052] For example, ROI (Return on Investment) is a ratio used to measure the return on a project relative to the investment cost, reflecting the overall profitability of the investment. ROI directly shows the profitability of an investment, usually expressed as a percentage. A high ROI indicates that the project investment is highly profitable, and is an indicator that investors pay close attention to when making investment decisions. Investors can judge the relative value of different investment options by comparing ROIs.

[0053] Furthermore, the particle swarm optimization algorithm (PSO) is a method for solving optimization problems, which simulates the social behavior of bird flocks to find the optimal solution. The multi-objective particle swarm optimization algorithm (MOPSO) is based on PSO and uses the basic principles of external archiving and Pareto dominance to handle multiple objectives. It has the characteristics of wide application range, few setting parameters, and simple optimization structure, and has been widely used in many fields. In MOPSO, each particle represents a potential solution, the position of the particle represents the parameters of the solution, and the speed represents the trend of the parameter change. The solution process of the multi-objective particle swarm optimization algorithm includes the following parts:

[0054] (1) Set decision variables. DC / AC ratio: the ratio of the installed capacity of the DC side to the AC side of the photovoltaic system. Energy storage configuration capacity: the configuration capacity of the energy storage system, which affects the energy storage capacity and flexibility of the system.

[0055] (2) Update and test model convergence:

[0056] ① Initialization parameters: In the multi-objective particle swarm optimization algorithm (MOPSO), the position and velocity of the particles are initialized, and the parameters of the algorithm are set, such as the number of particles, inertia weight, learning factor, etc.

[0057] Initialize the particle position: where the particle position x 0 0,i Initialize to a two-dimensional array composed of random sampling of the above two decision variables within a certain range. The value range of the capacity ratio is [1,2], and the value range of the energy storage configuration capacity is [1,10000].

[0058] Initialize particle speed: Set the speed of each particle v 0 0,i Initialized to 0.

[0059] Initialize the number of particles: The number of particles n is initialized to 100.

[0060] Initialize inertia vector: The inertia vectors c1 and c2 are both initialized to 0.5.

[0061] Initialize learning factors: learning factors r1 and r2 are random numbers between 0 and 1

[0062] ② Update of particle position and velocity:

[0063] Each iteration uses the calculated individual optimal P t best and the globally optimal P t bestglobal Generate and guide new sampling particles P t iThe optimized direction uses the formula to update the particle position and velocity. Figure 4 shown.

[0064] ③Multi-objective optimization:

[0065] Each particle updated above represents a possible solution, that is, a decision variable formed by the capacity ratio and energy storage configuration capacity combination. The position of the particle is updated according to the current position and speed. The fitness value of each particle is calculated, that is, the system performance index, such as power generation, utilization hours and economic evaluation parameters. Then, the multi-objective particle swarm optimization algorithm (MOPSO) is used to continuously calculate the multi-objective function with the updated particles to find the particle with the greatest contribution, thereby determining the individual optimal P best And the global optimal P bestglobal Then update the particles to achieve the optimization purpose.

[0066] ④Convergence test:

[0067] Monitor the iteration process of the algorithm and check whether the average position of the particle swarm tends to be stable. Check the change range of the fitness value. If the change range is small or within a certain threshold, the algorithm can be considered to have converged. After the algorithm determines that it has converged, it will terminate the program and obtain the Pareto solution set and the results calculated by the corresponding objective function. Due to the anisotropy between multi-objective functions, there is no definite pair of solutions that can meet the optimal conditions of multiple objectives, so Pareto optimization is required later. In multi-objective optimization, if a solution does not improve other objectives without making any objective worse, this solution is considered to be Pareto optimal. The Pareto Front is the set of all Pareto optimal solutions, which represents the best trade-off between multiple objectives. This Pareto Front is the optimal solution set.

[0068] In the PV-storage configuration decision-making process, through the mechanism of the Pareto optimal solution set, decision makers are faced with not a single solution, but a set of solutions. Each solution in this set is optimal to some extent because they all represent a trade-off between different objectives. This mechanism significantly improves the flexibility and freedom of decision-making because it allows decision makers to choose the most appropriate solution from multiple feasible optimal solutions based on their specific needs, constraints, and predictions and preferences for the future.

[0069] This system includes two optimization objectives, namely, maximizing economic efficiency (maximizing the net present value of the system's entire life cycle) and maximizing the number of utilization hours. Multi-objective optimization and Pareto optimization are needed to find the optimal solution set. Specifically, decision makers can preliminarily screen the solutions in the solution set based on their own economic goals and expectations for system operation efficiency. For example, if economic efficiency is the main concern, decision makers may tend to choose solutions with lower costs; if system reliability and high utilization are more important, they may choose solutions that are more expensive but can bring higher power generation and stability. Secondly, sensitivity analysis provides decision makers with insights into the robustness of the solutions, helping them understand the performance of the solutions under different circumstances and make more thoughtful decisions. The economic evaluation of the optimal solution includes calculating the levelized cost of electricity (LCOE), net present value (NPV), internal rate of return (IRR) and return on investment (ROI) to evaluate the long-term economic benefits of each solution, which is particularly important for projects that need to attract investment. The quantitative method based on performance-price ratio provides decision makers with an additional dimension to evaluate the value of the solution and help them find the best balance between cost and performance.

[0070] In summary, the mechanism of Pareto optimal solution set not only provides a variety of choices, but also enhances the ability and confidence of decision makers in the face of complex decisions through various analytical tools and methods, enabling them to make more comprehensive and balanced decisions based on multiple factors. The optimization results, simulation verification results and economic evaluation results are visualized and analyzed to facilitate solution selection and decision support.

[0071] Therefore, a comprehensive parameter calculation method is adopted in the economic evaluation, including levelized cost of electricity (LCOE), net present value (NPV), internal rate of return (IRR) and return on investment (ROI), which provides a solid financial analysis basis for investment decisions. In addition, through the multi-objective optimization achieved by the multi-objective particle swarm optimization algorithm (MOPSO), this embodiment can simultaneously consider system performance and economy, balance costs and benefits, and achieve comprehensive optimization, which is unmatched by single-objective optimization methods.

[0072] The specific implementation methods of the present application are described in detail above. Although some embodiments have been shown and described, those skilled in the art should understand that these embodiments can be modified and improved without departing from the principles and spirit of the present application whose scope is defined by the claims and their equivalents. These modifications and improvements should also be within the scope of protection of the present application.

Claims

1. A method for optimizing the configuration of optical storage capacity based on evolutionary computing, characterized in that: The optical storage capacity configuration optimization decision method comprises: Constructing a photovoltaic storage system simulation model. When the capacity ratio and energy storage configuration capacity of the photovoltaic storage system simulation model change, the simulation output result generated by the photovoltaic storage system simulation model according to the input data changes. The capacity ratio and energy storage configuration capacity of the photovoltaic storage system simulation model are optimized multiple times by using a pre-built optimization model until the stopping condition is met, wherein in each iteration, the simulation output result of the current photovoltaic storage system simulation model is input into the optimization model, and the optimization model outputs a new capacity ratio and energy storage configuration capacity, which are used as the capacity ratio and energy storage configuration capacity of the photovoltaic storage system simulation model of the next iteration.

2. The method for optimizing the configuration of optical storage capacity based on evolutionary computing according to claim 1 is characterized in that: The input data includes meteorological data, historical output data and system configuration data, and the simulation output results include the output, power generation and utilization hours of the photovoltaic storage system.

3. The method for optimizing the configuration of optical storage capacity based on evolutionary computing according to claim 2 is characterized in that: The simulation operation modes of the photovoltaic energy storage system simulation model include an energy storage fixed boundary operation mode and an energy storage peak shaving and valley filling operation mode.

4. The method for optimizing the configuration of optical storage capacity based on evolutionary computing according to claim 1 is characterized in that: The optical storage capacity configuration optimization decision method further includes: The photovoltaic storage system simulation model is calibrated according to the measured data.

5. The method for optimizing the configuration of optical storage capacity based on evolutionary computing according to claim 4 is characterized in that: The method for calibrating the photovoltaic storage system simulation model according to measured data comprises: After running the photovoltaic storage system simulation model, the simulation output results of the photovoltaic storage system simulation model are compared and analyzed with the measured data; The model parameters of the photovoltaic storage system simulation model are adjusted according to the results of the comparative analysis.

6. The method for optimizing the configuration of optical storage capacity based on evolutionary computing according to claim 1 is characterized in that: The optimization model is a model based on a multi-objective particle swarm optimization algorithm, and the optimization objectives of the optimization model include economic indicators, utilization hours and power generation.

7. The method for optimizing the configuration of optical storage capacity based on evolutionary computing according to claim 6 is characterized in that: The economic indicators include levelized cost of electricity, net present value, internal rate of return and return on investment.

Images