Embedded platform-based charging and discharging control method for energy storage system

Abstract

The present invention relates to the technical field of energy storage system control, and disclosed is an embedded platform-based charging and discharging control method for an energy storage system. The method comprises: by means of an embedded platform, acquiring operation characteristic parameter information of a target energy storage system and operation state parameter information of a power grid; performing comparison and balance analysis on the basis of the operation state parameter information of the power grid and power demand parameter information of the power grid, to determine a power deviation regulating parameter of the power grid; performing charging and discharging control analysis using the operation characteristic parameter information and the power deviation regulating parameter of the power grid as constraint conditions, to obtain a charging and discharging control parameter set for charging and discharging control and control effect optimization analysis; and determining a target charging and discharging control optimization parameter for system charging and discharging optimization control. Further, the technical effects of implementing optimization control of the applicability of charging and discharging control parameters of the energy storage system, improving the accuracy of control parameter analysis, effectively improving the timeliness of charging and discharging responses of the system, and further improving the energy utilization efficiency of the energy storage system are achieved.

Description

Energy storage system charge and discharge control method based on embedded platform Technical Field

[0001] This invention relates to the field of energy storage system control technology, and in particular to a charging and discharging control method for energy storage systems based on an embedded platform. Background Technology

[0002] With the growth of global energy demand and the rapid development of renewable energy, energy storage systems, as an important energy conversion and regulation technology, are widely used in power systems. Energy storage can address the volatility and intermittency of renewable energy, improve grid stability and reliability, and reduce dependence on high-polluting energy sources such as traditional coal-fired power generation. The charging and discharging process of energy storage systems has a significant impact on system performance and stability; however, existing energy storage systems lack sufficient precision in charging and discharging control and have low response timeliness, thus affecting the energy utilization efficiency of energy storage systems. Summary of the Invention

[0003] This application provides a charging and discharging control method for energy storage systems based on an embedded platform, which solves the technical problems of insufficient accuracy and low response time of existing energy storage systems, thus affecting the energy utilization efficiency of the energy storage system. It achieves the technical effect of optimizing the applicability of the charging and discharging control parameters of the energy storage system, improving the accuracy of control parameter analysis, effectively improving the system's charging and discharging response time, and thus improving the energy utilization efficiency of the energy storage system.

[0004] In view of the above problems, the present invention provides a charging and discharging control method for energy storage systems based on an embedded platform.

[0005] This application provides a charging and discharging control method for an energy storage system based on an embedded platform. The method includes: S1: acquiring the operating characteristic parameters of the target energy storage system and the operating status parameters of the power grid through the embedded platform, and performing multi-dimensional demand factor analysis on the target power grid to obtain power demand parameter information; S2: performing a comparative balance analysis based on the operating status parameters and the power demand parameters to determine the power deviation adjustment parameters, and using the operating characteristic parameters and the power deviation adjustment parameters as constraints for charging and discharging control analysis to obtain a set of charging and discharging control parameters; S3: performing charging and discharging control on the target energy storage system by optimizing the set of charging and discharging control parameters, and monitoring the charging and discharging process in real time based on the embedded platform to obtain a charging and discharging control feedback data stream of the energy storage system; S4: performing control effect optimization analysis on the set of charging and discharging control parameters based on the charging and discharging control feedback data stream of the energy storage system, determining the target charging and discharging control optimization parameters, and performing charging and discharging optimization control on the target energy storage system based on the target charging and discharging control optimization parameters.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0007] This technical solution employs an embedded platform to acquire operational characteristic parameters of the target energy storage system and grid operational status parameters. It then performs multi-dimensional demand factor analysis on the target grid to obtain grid power demand parameters. Based on this grid operational status parameters and power demand parameters, a comparative balance analysis is conducted to determine grid power deviation adjustment parameters. These parameters are then used as constraints for charge-discharge control analysis, resulting in a set of charge-discharge control parameters. The optimal set of these parameters is then used to control the charge-discharge of the target energy storage system. Furthermore, the system's charge-discharge control feedback data stream is monitored and analyzed to optimize the control effect of the parameter set. Finally, the optimized charge-discharge control parameters are determined for optimal control of the target energy storage system. This achieves the technical effect of optimizing the applicability of the energy storage system's charge-discharge control parameters, improving the accuracy of control parameter analysis, effectively enhancing the system's charge-discharge response timeliness, and ultimately improving the energy utilization efficiency of the energy storage system.

[0008] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0009] Figure 1 is a flowchart illustrating the charging and discharging control method for an energy storage system based on an embedded platform according to this application;

[0010] Figure 2 is a flowchart illustrating the process of obtaining the set of charge and discharge control parameters in the energy storage system charge and discharge control method based on the embedded platform of this application. Detailed Implementation

[0011] This application provides a charging and discharging control method for energy storage systems based on an embedded platform, which solves the technical problems of insufficient accuracy and low response time of existing energy storage systems, thus affecting the energy utilization efficiency of the energy storage system. It achieves the technical effect of optimizing the applicability of the charging and discharging control parameters of the energy storage system, improving the accuracy of control parameter analysis, effectively improving the system's charging and discharging response time, and thus improving the energy utilization efficiency of the energy storage system.

[0012] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0013] Example 1

[0014] As shown in Figure 1, this application provides a charging and discharging control method for an energy storage system based on an embedded platform, the method comprising:

[0015] Step S1: Obtain the operating characteristic parameters of the target energy storage system and the operating status parameters of the power grid through the embedded platform, and perform multi-dimensional demand factor analysis on the target power grid to obtain the power demand parameter information of the power grid.

[0016] Furthermore, in obtaining grid power demand parameter information in S1, this application also includes the following steps:

[0017] S11: Obtain grid power demand factor information, which includes load power demand, operational stability, and renewable energy access;

[0018] S12: Based on the power demand factor information of the power grid, perform multi-dimensional demand analysis on the target power grid to obtain the multi-dimensional power demand parameter matrix of the power grid.

[0019] S13: Assign power impact values ​​to the power demand factor information of the power grid to obtain power factor impact factor information, and determine the power impact factor matrix based on the power factor impact factor information;

[0020] S14: Based on the power influencing factor matrix, perform weighted calculation on the power demand parameter matrix of the power grid multidimensional factors to determine the power demand parameter information of the power grid.

[0021] Specifically, to achieve precise and applicable control of the charging and discharging control parameters of the energy storage system, an embedded platform is used to acquire the operating characteristic parameters of the target energy storage system and the grid operating status parameters. The operating characteristic parameters are the operating attribute parameters of the energy storage system, including its energy capacity, power capacity, and energy conversion efficiency. The grid operating status parameters include the current operating voltage, current, and power of the grid. An embedded platform is a computer system integrating a processor, memory, and peripheral interfaces. It features small size, low power consumption, and high performance, and is widely used for its ability to achieve precise control and scheduling of the energy storage system, improving system efficiency and reliability. The target energy storage system is a hardware and software integrated system based on the embedded platform. Through monitoring, control, and optimized scheduling of the energy storage devices, comprehensive management and operational control of the energy storage system are achieved. The energy storage system can adjust its operating mode and strategy by real-time monitoring and analysis of the status and performance of the energy storage devices, thereby improving the system's energy utilization efficiency and operational stability.

[0022] A multi-dimensional power demand analysis is performed on the target power grid to which the target energy storage system is connected. First, power demand factor information is obtained, which includes the types of factors influencing power demand, such as load power demand (the power required for grid load operation), operational stability (the power required to maintain grid stability), and renewable energy access (the power provided by other renewable energy sources such as wind and solar power connected to the grid). Based on this power demand factor information, a multi-dimensional demand analysis is performed on the target power grid to obtain corresponding power demand values, forming a multi-dimensional power demand parameter matrix. This matrix represents the multi-dimensional power demand values ​​of the target power grid. Power impact is assigned to the power demand factor information, i.e., the decision-making proportion of each factor in power demand is determined through grid operation strategies, obtaining power factor impact factor information. This power factor impact factor information is determined as the decision-making impact proportion of each factor in power demand, and a power impact factor matrix is ​​formed based on the specific values ​​of the power factor impact factor information. Finally, a weighted calculation is performed on the multi-dimensional power demand parameter matrix based on the power impact factor matrix to determine the power demand parameter information for multi-factor combined decision-making. This enables a multi-dimensional and comprehensive analysis of power demand in the power grid, improves the accuracy of power parameter analysis, and thus ensures the precision of subsequent charging and discharging control parameters.

[0023] Step S2: Based on the grid operating status parameter information and the grid power demand parameter information, perform a comparison and balance analysis to determine the grid power deviation adjustment parameters. Use the operating characteristic parameter information and the grid power deviation adjustment parameters as constraints to perform charge and discharge control analysis to obtain a set of charge and discharge control parameters.

[0024] As shown in Figure 2, further, in step S2, the set of charge and discharge control parameters is obtained. The steps of this application also include:

[0025] S21: Construct a charging and discharging control parameter space, which includes historical energy storage system operating characteristic data, charging and discharging control parameters, and corresponding charging and discharging control effect data;

[0026] S22: Based on the operating characteristic parameter information and the charging and discharging control parameter space, a matching and partitioning process is performed to obtain a charging and discharging control parameter memory library;

[0027] S23: Perform charge-discharge fusion analysis based on the charge-discharge control parameter memory library to generate a charge-discharge multi-element control power correlation model;

[0028] S24: The power deviation adjustment parameters of the power grid are compensated by the charging and discharging multi-element control power correlation model to determine the adjustment threshold of the charging and discharging control parameters. Based on the adjustment threshold of the charging and discharging control parameters, the charging and discharging control analysis is performed to obtain the set of charging and discharging control parameters.

[0029] Furthermore, the step of generating the charge / discharge multi-element control power correlation model in S23 also includes:

[0030] The charging and discharging control parameter memory is used to extract charging and discharging correlation data to obtain the energy storage system charging and discharging correlation dataset, which includes charging and discharging correlation control parameters and corresponding charging and discharging power data.

[0031] The energy storage system charge-discharge correlation dataset is fitted using a multiple regression function to obtain the charge-discharge correlation power regression coefficient information.

[0032] Based on the charging and discharging power regression coefficient information, a basic multivariate control power correlation model is obtained, and the basic multivariate control power correlation model is fitted and evaluated to obtain the model fitting accuracy.

[0033] When the model fitting accuracy does not meet the standard, the basic multivariate control power correlation model is optimized for loss by the parameter optimizer to generate the charge and discharge multivariate control power correlation model.

[0034] Furthermore, in S24, the charging and discharging control parameter set is obtained. This application further includes the following steps:

[0035] The charging and discharging control parameter space is used to extract and evaluate the charging and discharging effect indexes, obtain a multi-dimensional index set of charging and discharging effect, and obtain the excitation function of charging and discharging effect based on the multi-dimensional index set of charging and discharging effect.

[0036] Within the adjustment threshold of the charge and discharge control parameters, multiple charge and discharge control parameters are randomly selected, and the multiple charge and discharge control parameters are evaluated and calculated using the excitation function of the charge and discharge effect to obtain multiple excitation degrees of charge and discharge effect.

[0037] Multiple charge and discharge parameter cluster centers are selected based on the multiple charge and discharge effect excitation degrees. Based on the multiple charge and discharge parameter cluster centers, cluster optimization analysis is performed on the multiple charge and discharge control parameters to obtain the set of charge and discharge control parameters.

[0038] Specifically, a comparative balance analysis is performed based on the grid operating status parameters and the grid power demand parameters. The difference between these two parameters is determined as the grid power deviation adjustment parameter, which represents the supplementary or regulating power supplied by the energy storage system to meet grid power supply and demand balance. The operating characteristic parameters and the grid power deviation adjustment parameter are used as constraints for charge-discharge control analysis. First, a charge-discharge control parameter space is constructed, including historical energy storage system operating characteristic data, charge-discharge control parameters, and corresponding charge-discharge control effect data. Then, the operating characteristic parameters are matched and partitioned with the charge-discharge control parameter space to obtain charge-discharge control data that matches the operating characteristic parameters of the energy storage system. This data serves as a charge-discharge control parameter memory for applicability optimization of the charge-discharge control parameters, reducing the parameter optimization range and improving optimization efficiency.

[0039] Based on the aforementioned charge-discharge control parameter memory, charge-discharge fusion analysis is performed. First, historical charge-discharge correlation data is extracted from the memory to obtain a charge-discharge correlation dataset for the energy storage system. This dataset includes historical charge-discharge correlation control parameters and corresponding charge-discharge power data. The dataset is then fitted using a multiple regression function. Each type of charge-discharge correlation control parameter is used as the independent variable, and the corresponding charge-discharge power data is used as the dependent variable. This fitting yields the charge-discharge correlation power regression coefficients for each type of control parameter. Based on these regression coefficients, a multiple regression model is constructed to obtain a basic multiple control power correlation model. The basic model is then fitted and evaluated to obtain its fitting accuracy. If the model's fitting accuracy is below the target, a parameter optimizer is used to optimize the model's loss. Parameter optimizers such as Adam and RMSprop are used to adjust the model's weights to minimize the loss function, thereby improving the model's performance and generating a charge-discharge multiple control power correlation model with the target fitting accuracy. Improve the accuracy of model power prediction, thereby ensuring the precision of energy storage system charge and discharge control parameter analysis.

[0040] The power deviation adjustment parameters of the power grid are compensated and calculated using the aforementioned multi-dimensional charge-discharge control power correlation model to determine the adjustment thresholds for charge-discharge control parameters that meet the power supply regulation requirements of the energy storage system. These adjustment thresholds include the optimal selection thresholds for various types of charge-discharge correlated control parameters. Based on these adjustment thresholds, charge-discharge control analysis is performed. First, charge-discharge control effect indicators are extracted and evaluated from the charge-discharge control effect data in the charge-discharge control parameter space to obtain a multi-dimensional set of charge-discharge effect indicators. This set is used to evaluate the charge-discharge effect of the energy storage system in multiple dimensions, including response time, power control loss, and safety performance. Then, the charge-discharge control parameter space data is fitted using this multi-dimensional set of indicators to obtain a charge-discharge effect excitation function. This excitation function is used to evaluate the charge-discharge effect of the energy storage system in multiple dimensions based on the charge-discharge control parameters. A higher excitation function indicates higher applicability and accuracy of the charge-discharge control parameter, resulting in better control performance.

[0041] Multiple charge-discharge control parameters are randomly selected within the adjustment threshold of the charge-discharge control parameters, and the multiple charge-discharge control parameters are evaluated and calculated using the charge-discharge effect excitation function to obtain the corresponding multiple charge-discharge effect excitation degrees. A preset proportion is selected based on the multiple charge-discharge effect excitation degrees, for example, selecting the top 5% of control parameters as the centers of multiple charge-discharge parameter clusters. The centers of these multiple charge-discharge parameter clusters represent the multiple charge-discharge control parameters with the optimal excitation degree within the preset proportion. Based on the centers of these multiple charge-discharge parameter clusters, parameter clustering and parameter optimization analysis are performed on the multiple charge-discharge control parameters to obtain an optimal set of charge-discharge control parameters. This set includes the optimal charge-discharge control parameters and multiple suboptimal charge-discharge control parameters for use in the charge-discharge control of the energy storage system. This achieves applicability optimization control of the energy storage system's charge-discharge control parameters, improves the accuracy of control parameter analysis, and effectively improves the timeliness of the system's charge-discharge response.

[0042] Furthermore, the step of obtaining the set of charge and discharge control parameters in this application also includes:

[0043] Based on the multiple excitation degrees of the charging and discharging effect, multiple cluster center parameter excitation degrees are determined. Based on the multiple cluster center parameter excitation degrees, the multiple charging and discharging control parameters are assigned and clustered to the centers of the multiple charging and discharging parameter clusters to obtain multiple source control parameter clusters.

[0044] Based on the multiple charging and discharging effect excitation degrees, the seed number of the multiple source control parameter clusters is calculated to obtain multiple parameter seed generation factors. Based on the multiple parameter seed generation factors, the multiple source control parameter clusters are expanded and optimized to generate multiple control parameter optimization population clusters.

[0045] The sum of the excitation degrees of the multiple control parameter optimization populations is calculated, compared, and optimized using the excitation degree function of the charging and discharging effect to obtain the set of charging and discharging control parameters, which includes the optimal charging and discharging control parameters and multiple suboptimal charging and discharging control parameters.

[0046] Furthermore, the step of generating multiple control parameter optimization population clusters in this application also includes:

[0047] Based on the seed generation factors of the multiple parameters, each control parameter in the multiple source control parameter clusters is randomly seeded according to a normal distribution to obtain multiple offspring control parameter clusters;

[0048] The multiple source control parameter clusters and the multiple offspring control parameter clusters are merged to obtain multiple control parameter population clusters. An upper limit for the population capacity is set, and inferior generation control parameters that exceed the upper limit for the population capacity in the multiple control parameter population clusters are removed to obtain multiple control parameter competing population clusters.

[0049] Based on the learning factor, the multiple control parameter competing populations are iteratively optimized by learning the cluster center until the preset convergence requirement is met, thereby generating the multiple control parameter optimized populations.

[0050] Specifically, the implementation steps for cluster optimization analysis of the multiple charge-discharge control parameters based on the multiple charge-discharge parameter cluster centers include: first, determining the multiple cluster center parameter excitation degrees corresponding to the multiple charge-discharge effect excitation degrees; then, based on the multiple cluster center parameter excitation degrees, proportionally allocating the remaining multiple charge-discharge control parameters to the multiple charge-discharge parameter cluster centers for clustering, with a larger cluster center excitation degree resulting in a larger number of allocated charge-discharge control parameters, thus obtaining multiple source control parameter clusters with the multiple charge-discharge parameter cluster centers as cluster centers. Seed number calculation is performed on the multiple source control parameter clusters based on the multiple charge-discharge effect excitation degrees. The seed number can be calculated proportionally according to the magnitude of the charge-discharge effect excitation degree to obtain multiple parameter seed generation factors corresponding to each control parameter. These multiple parameter seed generation factors represent the number of parameter seeds that each control parameter can generate.

[0051] Based on the multiple parameter seed generation factors, the multiple source control parameter clusters are expanded and optimized. First, based on the multiple parameter seed generation factors, each control parameter in the multiple source control parameter clusters is randomly expanded according to a normal distribution. Each control parameter in the multiple source control parameter clusters is used as a parent parameter solution, and the expanded seed solutions are dispersed around the parent parameter solutions to obtain multiple child control parameter clusters. The multiple source control parameter clusters and the multiple child control parameter clusters are added and merged to obtain multiple control parameter population clusters. Based on the optimization requirements, an upper limit for the population capacity is set. Inferior generation control parameters in the multiple control parameter population clusters that exceed the upper limit are removed. Parameter solutions with poor motivation exceeding the upper limit are eliminated from the population, resulting in multiple control parameter competing population clusters that meet the conditions.

[0052] Based on a learning factor, the remaining control parameters in the multiple competing control parameter populations are iteratively optimized towards the parameter cluster center. The learning factor is the parameter fine-tuning step size, which can be empirically set according to the required optimization accuracy. Then, the activation degree of the optimized population parameters is evaluated using the charging / discharging effect activation degree function. The control parameter with the highest activation degree in the population is replaced as the center of the charging / discharging parameter cluster until a preset convergence requirement is met, such as reaching a preset number of iterations or reaching the optimal parameter solution, generating multiple optimized control parameter populations after iterative optimization. Finally, the sum of activation degrees of the multiple optimized control parameter populations is calculated and compared using the charging / discharging effect activation degree function, and the population cluster with the largest sum of activation degrees is selected as the charging / discharging control parameter set. This set includes the optimal charging / discharging control parameter and multiple suboptimal charging / discharging control parameters. This achieves global search optimization of charging / discharging control parameters, ensuring rapid convergence of parameter optimization, thereby improving the accuracy of control parameter optimization and the efficiency of parameter optimization analysis.

[0053] Step S3: The target energy storage system is charged and discharged by optimizing the set of charging and discharging control parameters, and the charging and discharging process is monitored in real time based on the embedded platform to obtain the energy storage system charging and discharging control feedback data stream;

[0054] Specifically, the target energy storage system is charged and discharged by selecting the optimal charging and discharging control parameters from the set of charging and discharging control parameters. The charging and discharging control process is monitored in real time based on the embedded platform to obtain the corresponding energy storage system charging and discharging control feedback data stream. The energy storage system charging and discharging control feedback data stream is the control effect feedback data of the target energy storage system, including charging and discharging regulation power, response time, and power control loss, etc., which serves as the basis for subsequent parameter optimization of energy storage system charging and discharging control, thereby improving the accuracy and practical applicability of control parameter analysis.

[0055] Step S4: Based on the charging and discharging control feedback data stream of the energy storage system, perform control effect optimization analysis on the charging and discharging control parameter set, determine the target charging and discharging control optimization parameters, and perform charging and discharging optimization control on the target energy storage system based on the target charging and discharging control optimization parameters.

[0056] Furthermore, in step S4, determining the target charge / discharge control optimization parameters, this application also includes the following steps:

[0057] S41: Perform correlation parameter compensation analysis on the energy storage system charge and discharge control feedback data stream to obtain the correlation charge and discharge control parameter characteristics, and determine the parameter evolution direction based on the correlation charge and discharge control parameter characteristics;

[0058] S42: Based on the parameter evolution direction and the charging / discharging effect excitation function, the charging / discharging control parameter set is updated and optimized to determine the target charging / discharging control optimization parameters.

[0059] Specifically, based on the charging and discharging control feedback data stream of the energy storage system, a control effect optimization analysis is performed on the charging and discharging control parameter set. First, a correlation parameter compensation analysis is performed on the charging and discharging control feedback data stream to obtain the charging and discharging control parameter characteristics associated with substandard charging and discharging control effects. These correlated charging and discharging control parameter characteristics are the charging and discharging control parameters to be optimized, including the type of correlated charging and discharging control parameters and the degree of optimization required. Based on these correlated charging and discharging control parameter characteristics, parameter optimization analysis is performed to determine the parameter evolution direction. This parameter evolution direction is the optimization direction of the charging and discharging control parameters. For example, if the energy supply power of the energy storage system is insufficient, control parameters such as charging and discharging voltage and current need to be added.

[0060] Based on the parameter evolution direction, each control parameter in the charge / discharge control parameter set is updated through evolution. The updated set of charge / discharge control parameters is then evaluated and compared using the charge / discharge effect excitation function to determine the control parameter with the highest excitation degree as the target charge / discharge control optimization parameter. Based on this target charge / discharge control optimization parameter, the target energy storage system is subjected to optimized charge / discharge control. This achieves applicability optimization control of the energy storage system's charge / discharge control parameters, improves the accuracy of control parameter analysis, effectively enhances the system's charge / discharge response timeliness, and ultimately improves the energy utilization efficiency of the energy storage system.

[0061] In summary, the energy storage system charging and discharging control method based on an embedded platform provided in this application has the following technical advantages:

[0062] This technical solution employs an embedded platform to acquire operational characteristic parameters of the target energy storage system and grid operational status parameters. It then performs multi-dimensional demand factor analysis on the target grid to obtain grid power demand parameters. Based on this grid operational status parameters and power demand parameters, a comparative balance analysis is conducted to determine grid power deviation adjustment parameters. These parameters are then used as constraints for charge-discharge control analysis, resulting in a set of charge-discharge control parameters. The optimal set of these parameters is then used to control the charge-discharge of the target energy storage system. Furthermore, the system's charge-discharge control feedback data stream is monitored and analyzed to optimize the control effect of the parameter set. Finally, the optimized charge-discharge control parameters are determined for optimal control of the target energy storage system. This achieves the technical effect of optimizing the applicability of the energy storage system's charge-discharge control parameters, improving the accuracy of control parameter analysis, effectively enhancing the system's charge-discharge response timeliness, and ultimately improving the energy utilization efficiency of the energy storage system.

[0063] This specification and accompanying drawings are merely illustrative examples of this application, but the scope of protection of this application is not limited thereto. It should be noted that any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.

Claims

1. A method for charge and discharge control of an energy storage system based on an embedded platform, characterized in that, The method comprises: S1: obtaining the operation characteristic parameter information and the grid operation state parameter information of the target energy storage system through an embedded platform, and performing multi-dimensional demand factor analysis on the target grid to obtain grid power demand parameter information; S2: comparing and balancing analysis based on the grid operation state parameter information and the grid power demand parameter information to determine the grid power deviation adjustment parameter, and performing charge and discharge control analysis based on the operation characteristic parameter information and the grid power deviation adjustment parameter as the constraint condition to obtain a set of charge and discharge control parameters; S3: performing charge and discharge control on the target energy storage system by optimizing the set of charge and discharge control parameters, and monitoring the charge and discharge process in real time based on the embedded platform to obtain energy storage system charge and discharge control feedback data stream; S4: based on the energy storage system charge and discharge control feedback data stream, the control effect optimization analysis is performed on the set of charge and discharge control parameters to determine the target charge and discharge control optimization parameter, and the target energy storage system is controlled based on the target charge and discharge control optimization parameter.

2. The method of claim 1, wherein, In S1, the grid power demand parameter information is obtained, comprising: S11: obtaining grid power demand factor information, including load power demand, operation stability, and renewable energy access; S12: based on the grid power demand factor information, performing multi-dimensional demand analysis on the target grid to obtain a grid multi-dimensional factor power demand parameter matrix; S13: power impact assignment is performed on the grid power demand factor information to obtain power factor impact factor information, and a power impact factor matrix is determined according to the power factor impact factor information; S14: based on the power impact factor matrix, the grid multi-dimensional factor power demand parameter matrix is weighted calculated to determine the grid power demand parameter information.

3. The method of claim 1, wherein, In S2, the set of charge and discharge control parameters is obtained, comprising: S21: constructing a charge and discharge control parameter space, which includes the operation characteristic data of the historical energy storage system, the charge and discharge control parameters, and the corresponding charge and discharge control effect data; S22: based on the operation characteristic parameter information and the charge and discharge control parameter space, the charge and discharge control parameter memory bank is obtained by matching and dividing; S23: based on the charge and discharge control parameter memory bank, charge and discharge fusion analysis is performed to generate a charge and discharge multi-element control power correlation model; S24: through the charge and discharge multi-element control power correlation model, the grid power deviation adjustment parameter is compensated and calculated to determine the charge and discharge control parameter adjustment threshold, and based on the charge and discharge control parameter adjustment threshold, the charge and discharge control analysis is performed to obtain the set of charge and discharge control parameters.

4. The method of claim 3, wherein, In S23, the charge and discharge multi-element control power correlation model is generated, comprising: charge and discharge correlation data extraction is performed on the charge and discharge control parameter memory bank to obtain an energy storage system charge and discharge correlation data set, which includes charge and discharge correlation control parameters and corresponding charge and discharge power data; The charging and discharging correlation data set of the energy storage system is fitted by a multiple regression function to obtain charging and discharging correlation power regression coefficient information; A basic multiple control power correlation model is obtained based on the charging and discharging correlation power regression coefficient information, and the model fitting accuracy is obtained by fitting and evaluating the basic multiple control power correlation model; When the model fitting accuracy does not meet the standard, the basic multiple control power correlation model is loss-optimized by a parameter optimizer to generate the charging and discharging multiple control power correlation model.

5. The method of claim 3, wherein, The charging and discharging control parameter set obtained in S24 includes: The charging and discharging effect multi-dimensional index set is obtained by extracting and evaluating the charging and discharging effect index of the charging and discharging control parameter space, and a charging and discharging effect incentive degree function is fitted based on the charging and discharging effect multi-dimensional index set; A plurality of charging and discharging control parameters are randomly selected within the charging and discharging control parameter adjustment threshold, and the plurality of charging and discharging control parameters are evaluated and calculated by using the charging and discharging effect incentive degree function to obtain a plurality of charging and discharging effect incentives; According to the plurality of charging and discharging effect incentives, a plurality of charging and discharging parameter cluster centers are selected, and the plurality of charging and discharging control parameters are analyzed by clustering optimization based on the plurality of charging and discharging parameter cluster centers to obtain the charging and discharging control parameter set.

6. The method of claim 5, wherein, The charging and discharging control parameter set obtained in S24 includes: A plurality of cluster center parameter incentives are determined according to the plurality of charging and discharging effect incentives, and the plurality of charging and discharging control parameters are parameter-distributed and clustered to the plurality of charging and discharging parameter cluster centers based on the plurality of cluster center parameter incentives to obtain a plurality of source control parameter clusters; A plurality of parameter seed generation factors are obtained by calculating the number of seeds of the plurality of source control parameter clusters based on the plurality of charging and discharging effect incentives, and a plurality of control parameter optimization population clusters are generated by population expansion optimization of the plurality of source control parameter clusters according to the plurality of parameter seed generation factors; The sum of the incentives of the plurality of control parameter optimization population clusters is calculated and compared by the charging and discharging effect incentive degree function to obtain the charging and discharging control parameter set, and the charging and discharging control parameter set includes optimal charging and discharging control parameters and a plurality of suboptimal charging and discharging control parameters.

7. The method of claim 6, wherein, The plurality of control parameter optimization population clusters are generated by: The plurality of source control parameter clusters are randomly expanded according to the normal distribution mode based on the plurality of parameter seed generation factors to obtain a plurality of child control parameter clusters; The plurality of source control parameter clusters and the plurality of child control parameter clusters are fused to obtain a plurality of control parameter population clusters, and the population capacity upper limit is set to remove the inferior generation control parameters that exceed the population capacity upper limit in the plurality of control parameter population clusters to obtain a plurality of control parameter competitive population clusters; The plurality of control parameter competitive population clusters are iteratively optimized by parameter cluster center learning based on a learning factor until a preset convergence requirement is met to generate the plurality of control parameter optimization population clusters.

8. The method of claim 5, wherein, The target charging and discharging control optimization parameter determined in S4 includes: S41: Perform associated parameter compensation analysis on the charge and discharge control feedback data stream of the energy storage system, obtain associated charge and discharge control parameter characteristics, and determine the parameter evolution direction according to the associated charge and discharge control parameter characteristics; S42: Perform evolution update optimization on the charge and discharge control parameter set based on the parameter evolution direction and the charge and discharge effect incentive degree function, and determine the target charge and discharge control optimization parameter.

Images