Energy regulation and control method and system of solar energy storage system

Abstract

The invention provides an energy regulation and control method and system for a solar energy storage system, and the method comprises the steps: generating a comprehensive energy management decision basis through employing the data obtained in real time, and carrying out the adjustment of a charging equalization strategy between a plurality of distributed battery units in the solar energy storage system through employing a self-adaptive algorithm, performing personalized customization on the optimized charging and discharging plan based on a historical power consumption mode of a user and current power demand prediction, generating a personalized power consumption scheme, and constructing a virtual power plant model according to the personalized power consumption scheme; performing coordination control on charging and discharging behaviors of the solar energy storage system by using the virtual power plant model, generating a cross-regional energy scheduling scheme, calculating a difference value by using a machine learning algorithm, and performing energy regulation and control on the solar energy storage system based on the difference value; according to the technical scheme provided by the invention, the energy utilization efficiency is improved, the service life of the battery is prolonged, and the solar energy storage system can be continuously self-optimized.

Description

Technical Field

[0001] The embodiments of the present invention relate to the technical field of energy regulation, and in particular, to an energy regulation method for a solar energy storage system. Background Art

[0002] With the wide application of renewable energy, solar energy storage systems play an increasingly important role in stabilizing power supply and improving energy utilization efficiency. Traditional solar energy storage systems usually rely on fixed charge and discharge strategies, lacking effective integration of dynamic factors such as real-time power input, electricity price fluctuations, and weather forecasts. This static management method is difficult to adapt to the complex and changeable actual operating environment, resulting in low energy utilization efficiency and poor user experience. In addition, existing systems also have deficiencies in handling users' personalized electricity consumption needs, unable to fully consider the unique electricity consumption patterns and instant electricity demand forecasts of different users, thus affecting the flexibility and accuracy of overall energy scheduling;

[0003] Although existing solar energy storage systems can achieve automated energy management to a certain extent, when facing cross-regional energy scheduling, their regulation mechanisms often appear not intelligent and flexible enough. Current methods mostly rely on preset rules or simple model predictions, lacking an effective feedback and adjustment mechanism for the differences between the actual and estimated effects during the execution process. This not only may lead to unreasonable resource allocation but also may cause unnecessary economic losses due to failure to respond promptly to external condition changes. Summary of the Invention

[0004] The embodiments of the present invention provide an energy regulation method and system for a solar energy storage system to solve the problems in the prior art that rely on fixed charge and discharge strategies, are difficult to adapt to the complex and changeable actual operating environment, resulting in low energy utilization efficiency and poor user experience, and lack an effective feedback and adjustment mechanism, which may not only lead to unreasonable resource allocation but also may cause unnecessary economic losses due to failure to respond promptly to external condition changes.

[0005] In a first aspect, the embodiments of the present invention provide an energy regulation method for a solar energy storage system, including:

[0006] Generating a basis for comprehensive energy management decision-making for the solar energy storage system by using the real-time obtained solar panel power input data, grid dynamic electricity price information, and illumination condition prediction provided by the weather forecast service;

[0007] According to the basis for comprehensive energy management decision-making, adjusting the charging balance strategy among multiple distributed battery units in the solar energy storage system by using an adaptive algorithm to obtain an optimized charge and discharge plan;

[0008] Based on the prediction of the user's historical power consumption pattern and current power demand, personalize the optimized charge and discharge plan to generate a personalized power consumption plan;

[0009] According to the personalized power consumption plan, construct a virtual power plant model, and use the virtual power plant model to coordinately control the charge and discharge behavior of the solar energy storage system to generate a cross-regional energy scheduling plan;

[0010] Use machine learning algorithms to calculate the difference value between the actual effect and the estimated effect during the implementation of the cross-regional energy scheduling plan, and based on the difference value, perform energy regulation of the solar energy storage system.

[0011] Optionally, according to the comprehensive energy management decision basis, use an adaptive algorithm to adjust the charging balance strategy among multiple distributed battery units in the solar energy storage system to obtain an optimized charge and discharge plan, including:

[0012] Based on the real-time power input data, the current energy storage level of each battery unit in the solar energy storage system, the predicted lighting conditions, and the user's power consumption pattern in the comprehensive energy management decision basis, set the target charging rate and the maximum allowable charging amount for each battery unit to obtain preliminary charging parameters;

[0013] According to the preliminary charging parameters, combine the adaptive control theory and the multi-objective optimization algorithm, calculate the characteristic parameters of each battery unit and the external environmental factors, obtain the optimal charging current and charging timing, and based on the optimal charging current and charging timing, obtain the initial charging balance strategy;

[0014] Based on the initial charging balance strategy, monitor the state changes of each battery unit during the actual charging process, adjust the charging parameters, and introduce an anomaly detection mechanism to identify the charging behavior that affects the safety of the energy storage system to obtain an adjusted charging balance strategy;

[0015] Use the comparison of the state information of each battery unit before and after each charging cycle to evaluate the effectiveness of the adjusted charging balance strategy, update the parameter settings of the adaptive algorithm, analyze the historical charging records through machine learning technology, and generate an optimized charge and discharge plan.

[0016] Optionally, according to the preliminary charging parameters, combine the adaptive control theory and the multi-objective optimization algorithm, calculate the characteristic parameters of each battery unit and the external environmental factors, obtain the optimal charging current and charging timing, and based on the optimal charging current and charging timing, obtain the initial charging balance strategy, including:

[0017] Using the preliminary charging parameters, combining the adaptive control theory and multi-objective optimization algorithm, comprehensively evaluate the characteristic parameters of each battery cell, and introduce a dynamic weight factor to reflect the importance of different parameters under different conditions, so as to obtain the comprehensive evaluation result;

[0018] According to the comprehensive evaluation result, use a machine learning model to predict the performance change trend of each battery cell, combine the real-time power input data and light condition prediction, calculate the optimal charging current and optimal charging timing, and generate the optimal charging parameters;

[0019] Based on the user's historical power consumption pattern, personalize the optimal charging parameters to generate personalized charging parameters;

[0020] Using the personalized charging parameters, calculate the mutual influence between adjacent battery cells, determine the priority and cooperation mode of each battery cell during charging, and form an initial charging balance strategy.

[0021] Optionally, using the preliminary charging parameters, combining the adaptive control theory and multi-objective optimization algorithm, comprehensively evaluate the characteristic parameters of each battery cell, and introduce a dynamic weight factor to reflect the importance of different parameters under different conditions, so as to obtain the comprehensive evaluation result, including:

[0022] Using the preliminary charging parameters, combining the adaptive control theory and multi-objective optimization algorithm, conduct a preliminary analysis on the characteristic parameters of each battery cell and external environmental factors to obtain an initial parameter evaluation;

[0023] According to the initial parameter evaluation, construct a parameter influence model, calculate the interaction between different parameters under different conditions, assign a basic weight to each parameter, and generate a basic weight setting;

[0024] Based on the basic weight setting, introduce a dynamic weight factor, and use the real-time power input data and light condition prediction to adjust the basic weights of each parameter to reflect the actual importance of different parameters under the current conditions, so as to obtain a dynamic weight configuration;

[0025] Using the dynamic weight configuration, re-evaluate the influence of the characteristic parameters of each battery cell and external environmental factors, and generate an updated comprehensive evaluation result.

[0026] Optionally, based on the user's historical power consumption pattern and current power demand prediction, personalize the optimized charge and discharge plan to generate a personalized power consumption plan, including:

[0027] Using the user's historical power consumption data, analyze the user's daily power consumption pattern to obtain the user power consumption pattern analysis result;

[0028] Based on the analysis results of the user's power consumption pattern, combined with the current power demand forecast, evaluate the power demand fluctuation situation and generate a power demand forecast;

[0029] Based on the power demand forecast, adjust the charging priority and discharging strategy in the optimized charging and discharging plan to form an initial personalized power consumption plan;

[0030] Use a machine learning model to optimize the preliminary personalized power consumption plan, calculate the impact of external factors, and adjust the charging and discharging time points and power in the preliminary personalized power consumption plan to obtain the best personalized power consumption plan.

[0031] Optionally, according to the personalized power consumption plan, construct a virtual power plant model, and use the virtual power plant model to coordinately control the charging and discharging behavior of the solar energy storage system to generate a cross-regional energy scheduling plan, including:

[0032] Use the personalized power consumption plan, combined with the data of other renewable energy power generation facilities and user-side flexible loads in the region, to construct a virtual power plant model including the solar energy storage system;

[0033] Based on the virtual power plant model, analyze the mutual relationship and cooperation potential among power generation facilities and loads in the region, determine the role positioning of different facilities at different times, and form an initial role assignment;

[0034] According to the initial role assignment, formulate the charging and discharging coordination rules among facilities to generate a preliminary cross-regional energy scheduling plan;

[0035] Use a machine learning algorithm to evaluate the feasibility and adaptability of the preliminary cross-regional energy scheduling plan, calculate the uncertain factors in actual operation, and adjust the preliminary cross-regional energy scheduling plan to obtain the target cross-regional energy scheduling plan;

[0036] Optionally, use a machine learning algorithm to calculate the difference value between the actual effect and the estimated effect during the implementation of the cross-regional energy scheduling plan, and based on the difference value, perform energy regulation of the solar energy storage system, including:

[0037] Use the real-time obtained solar panel power input data, grid dynamic electricity price information, and the predicted lighting conditions provided by the weather forecast service to generate the basis for comprehensive energy management decision-making of the solar energy storage system;

[0038] According to the comprehensive energy management decision-making basis, use an adaptive algorithm to adjust the charging balance strategy among multiple distributed battery units in the solar energy storage system to obtain an optimized charging and discharging plan;

[0039] Based on the prediction of the user's historical electricity consumption pattern and current electricity demand, personalize the optimized charging and discharging plan to generate a personalized electricity usage plan;

[0040] According to the personalized electricity usage plan, construct a virtual power plant model, and use the virtual power plant model to coordinately control the charging and discharging behavior of the solar energy storage system to generate a cross-regional energy scheduling plan;

[0041] Use a machine learning algorithm to calculate the difference value between the actual effect and the estimated effect during the execution of the cross-regional energy scheduling plan, and based on the difference value, perform energy regulation of the solar energy storage system.

[0042] In a second aspect, an embodiment of the present invention provides an energy regulation system for a solar energy storage system, including:

[0043] An acquisition module, configured to generate a basis for comprehensive energy management decision-making for the solar energy storage system by using the real-time acquired solar panel power input data, grid dynamic electricity price information, and light condition prediction provided by the weather forecast service;

[0044] An adjustment module, configured to adjust the charging balance strategy between multiple distributed battery units in the solar energy storage system by using an adaptive algorithm according to the comprehensive energy management decision-making basis to obtain an optimized charging and discharging plan;

[0045] A customization module, configured to personalize the optimized charging and discharging plan based on the prediction of the user's historical electricity consumption pattern and current electricity demand to generate a personalized electricity usage plan;

[0046] A construction module, configured to construct a virtual power plant model according to the personalized electricity usage plan, and use the virtual power plant model to coordinately control the charging and discharging behavior of the solar energy storage system to generate a cross-regional energy scheduling plan;

[0047] An execution module, configured to use a machine learning algorithm to calculate the difference value between the actual effect and the estimated effect during the execution of the cross-regional energy scheduling plan, and based on the difference value, perform energy regulation of the solar energy storage system.

[0048] In a third aspect, an embodiment of the present invention provides a computing device, including a processor and a memory, where a computer program is stored in the memory, and the processor is configured to run the computer program to execute the energy regulation method for a solar energy storage system according to any one of the first aspects.

[0049] In a fourth aspect, an embodiment of the present invention provides a computer storage medium, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the energy regulation method for a solar energy storage system according to any one of the first aspects is implemented.

[0050] In the embodiments of the present invention, based on the real-time obtained solar panel power input data, grid dynamic electricity price information, and the predicted lighting conditions provided by the weather forecast service, a basis for comprehensive energy management decision-making for the solar energy storage system is generated; according to the basis for comprehensive energy management decision-making, an adaptive algorithm is used to adjust the charging balance strategy among multiple distributed battery units in the solar energy storage system to obtain an optimized charging and discharging plan; based on the user's historical electricity consumption pattern and the current electricity demand prediction, the optimized charging and discharging plan is customized to generate a personalized electricity consumption plan; according to the personalized electricity consumption plan, a virtual power plant model is constructed, and the charging and discharging behavior of the solar energy storage system is coordinated and controlled by using the virtual power plant model to generate a cross-regional energy scheduling plan; a machine learning algorithm is used to calculate the difference value between the actual effect and the estimated effect during the execution of the cross-regional energy scheduling plan, and based on the difference value, the energy regulation of the solar energy storage system is executed; the technical solution provided by the present invention improves the energy utilization efficiency, reduces the operation cost, prolongs the battery life, reduces the maintenance requirements, enhances the stability and response ability of the entire power system, ensures that the solar energy storage system can continuously self-optimize, adapt to changing external conditions, and further improves the energy utilization efficiency and economic benefits;

[0051] Furthermore, through the initial analysis of the preliminary charging parameters, considering the characteristic parameters of each battery unit (such as temperature, voltage, internal resistance, health status) and external environmental factors (such as temperature, humidity, light intensity changes), an initial parameter evaluation is generated, providing a solid data basis for the subsequent steps and ensuring that all subsequent operations are based on accurate information; according to the initial parameter evaluation results, a parameter influence model is constructed to calculate the interaction of different parameters under different conditions and assign a basic weight to each parameter. This approach not only considers the influence of individual parameters but also their complex relationships, making the evaluation more comprehensive and detailed; based on the basic weight setting, a dynamic weight factor is introduced, and the real-time power input data and the predicted lighting conditions are used to adjust the basic weights of each parameter. The dynamic weight factor reflects the actual importance of different parameters under the current conditions, making the evaluation results closer to the actual situation and improving the accuracy of decision-making; using the dynamic weight configuration, the influence of the characteristic parameters of each battery unit and the external environmental factors is evaluated again, and finally an updated comprehensive evaluation result is generated. The updated result provides a key basis for formulating a more accurate charging balance strategy, ensuring the efficient operation of the system and the long-term health of the battery units;

[0052] These aspects or other aspects of the present invention will be more clearly understood in the following description of the embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the accompanying drawings required for the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0054] Figure 1 It is a flowchart of an energy regulation method for a solar energy storage system provided by an embodiment of the present invention;

[0055] Figure 2 It is a schematic structural diagram of an energy regulation system for a solar energy storage system provided by an embodiment of the present invention;

[0056] Figure 3 It is a schematic structural diagram of a computing device provided by an embodiment of the present invention. Detailed implementation manners

[0057] In order to enable those skilled in the art to better understand the solution of the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings in the embodiments of the present invention.

[0058] In some processes described in the specification, claims and the above accompanying drawings of the present invention, there are multiple operations that appear in a specific order. However, it should be clearly understood that these operations may not be executed in the order in which they appear herein or may be executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions such as "first" and "second" in this article are used to distinguish different messages, devices, modules, etc., and do not represent a sequence, nor do they limit that "first" and "second" are of different types.

[0059] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present invention.

[0060] Figure 1 An embodiment of the present invention provides a flowchart of an energy regulation method for a solar energy storage system, as Figure 1 shown, the method includes:

[0061] Step 101: Generate the decision-making basis for the integrated energy management of the solar energy storage system by using the real-time obtained solar panel power input data, grid dynamic electricity price information, and the predicted lighting conditions provided by the meteorological forecast service;

[0062] In this step, the solar panel power input data includes parameters such as the hourly power generation and voltage, which are used to evaluate the current power production capacity; the grid dynamic electricity price information covers the electricity price fluctuations in different periods, which is used to optimize the charging and discharging costs; the predicted lighting conditions provided by the meteorological forecast service include the solar radiation intensity, weather conditions, etc. in the next few days, which helps to estimate the future power production potential;

[0063] In this step, by integrating the above three types of data, a comprehensive integrated energy management decision-making framework is constructed. This framework can analyze and predict the energy supply and demand situation in the future for a period of time in real time, providing a scientific basis for the subsequent adjustment of the charging balance strategy. Specifically, the algorithm will calculate the optimal charging and discharging time points and power levels based on these data to ensure the minimization of operating costs while meeting the user's needs;

[0064] In a practical application case, a residential area installed a set of solar energy storage devices (Solar Energy Storage Facility, SESF). The SESF is equipped with intelligence. It receives the predicted lighting data from the local meteorological station every morning, and combines it with the time-of-use electricity price table released by the power grid company, as well as the actual power generation records of its own solar panels on the previous day. Through this information, the best charging and discharging strategies for the current day and the next few days can be planned in advance. For example, increase the charging amount during the predicted sunny days and low electricity price periods, and give priority to using the stored electricity during rainy days or high electricity price periods, so as to maximize the economic benefits.

[0065] Step 102: According to the integrated energy management decision-making basis, use an adaptive algorithm to adjust the charging balance strategy among multiple distributed battery units in the solar energy storage system to obtain an optimized charging and discharging plan;

[0066] In this step, the adaptive algorithm is an algorithm that can automatically adjust parameters according to changes in the external environment, and the charging balance strategy refers to how to reasonably allocate the charging current and time of each battery unit to ensure that all batteries can work in the best state;

[0067] The adaptive algorithm will analyze the characteristic parameters of each battery unit (such as temperature, voltage, internal resistance, health status) and their relationship with external environmental factors (such as temperature, humidity, light intensity changes), and dynamically adjust the target charging rate of each battery unit. It not only considers the state of a single battery unit, but also takes into account the mutual influence between them to ensure the efficient operation and long-term stability of the entire solar energy storage facility;

[0068] Continuing with the SESF in the above-mentioned residential area as an example, assume that multiple different types of lithium battery units are configured inside the SESF. As the seasons change, some battery units may exhibit different performances due to temperature differences. The adaptive algorithm can automatically adjust their charging parameters according to the real-time monitored working status of each battery unit. For example, it can increase the charging speed of battery units with poor performance at low temperatures or reduce the charging intensity of battery units prone to overheating in high-temperature environments. In this way, the SESF can maintain optimal performance under various conditions and extend the overall service life.

[0069] Step 103: Based on the user's historical electricity consumption pattern and the current electricity demand forecast, customize the optimized charging and discharging plan to generate a personalized electricity usage plan.

[0070] In this step, the user's historical electricity consumption pattern refers to the electricity consumption behavior rules of the user over a past period, such as the electricity consumption distribution during peak and off-peak hours; the current electricity demand forecast is an estimate of the electricity consumption in the short term in the future. These two together determine the personalized electricity usage plan.

[0071] In this step, the algorithm will analyze the user's daily electricity consumption habits, identify specific time periods and electricity consumption characteristics, and then combine the current electricity demand forecast to adjust the optimized charging and discharging plan to make it more in line with the user's actual needs. This can not only improve the user experience but also further optimize the energy utilization efficiency and reduce unnecessary electricity waste.

[0072] Continuing with the previous example, the SESF will also collect the historical electricity consumption data of each household to understand their daily electricity consumption patterns. For example, it is found that a household usually uses a large amount of electricity between 7 am and 9 am and less electricity between 3 pm and 5 pm. Based on this information, the SESF can pre-charge fully at a lower electricity price at night and release electricity for the household to use during the morning peak hours, while appropriately reducing the external power supply during the afternoon off-peak hours to ensure that the electricity in the SESF is always in an optimal state, meeting the needs of the household and achieving energy-saving effects.

[0073] Step 104: According to the personalized electricity usage plan, construct a virtual power plant model and use the virtual power plant model to coordinately control the charging and discharging behavior of the solar energy storage system to generate a cross-regional energy scheduling plan.

[0074] In this step, the virtual power plant model (VPPM) is a digital platform that integrates dispersed renewable energy generation equipment and load resources and participates in power market transactions and technical regulation as a whole.

[0075] In this step, the virtual power plant model comprehensively considers the personalized electricity consumption plans of all participants in the region and formulates unified charge-discharge coordination rules. In this way, not only can the local power supply and demand be balanced, but it can also work in coordination with similar facilities in other regions to form an energy dispatching network on a larger scale. This cross-regional collaboration helps to make full use of renewable resources in each region and improve the stability and flexibility of the entire power system;

[0076] Suppose the SESF in a residential area joins the local virtual power plant project. This project covers multiple similar residential areas and other types of distributed energy facilities. When the SESF in a certain residential area generates excessive electricity during the day, the VPPM can coordinate to transmit its excess electricity to other areas with insufficient power; conversely, at night or on cloudy days, the VPPM can also allocate power from other places with surplus power to supplement. In addition, the VPPM can also respond to the peak shaving requirements of the power grid company, such as increasing power supply to the outside during peak electricity price periods or charging more during low electricity price periods, so as to optimize the operation efficiency of the entire power system.

[0077] Step 105: Use machine learning algorithms to calculate the difference value between the actual effect and the estimated effect during the implementation of the cross-regional energy dispatching plan, and based on the difference value, perform energy regulation of the solar energy storage system;

[0078] In this step, the difference value here reflects the deviation between the actual operation result and the expected target, and the machine learning algorithm can gradually reduce this deviation through continuous learning and optimization, making the dispatching more accurate and effective;

[0079] In this step, the machine learning algorithm continuously monitors the implementation of the cross-regional energy dispatching plan, collects relevant data and conducts analysis. Once it is found that the actual effect deviates from the estimated effect, the algorithm will automatically adjust the subsequent dispatching strategy to correct the deviation and optimize future performance. This feedback mechanism ensures that the dispatching plan can be continuously improved according to the actual situation, improving the stability and reliability of the operation of the entire solar energy storage facility;

[0080] To ensure the long-term stable operation of the SESF and its virtual power plant project, the effect of cross-regional energy dispatching is regularly evaluated. For example, if the SESF in a certain residential area fails to reach the expected power output target for several consecutive days, the machine learning algorithm will analyze the possible reasons, such as inaccurate weather forecasts or changes in user electricity consumption patterns. Based on these analysis results, the future dispatching strategy will be adjusted accordingly, such as reserving more electricity in advance or adjusting the power exchange plan with other regions. In this way, the SESF can not only better cope with unforeseen changes, but also continuously optimize its own performance and provide more reliable services for users.

[0081] Since the charging equalization strategies of existing systems are often not refined enough and cannot be adjusted individually according to the specific characteristics of battery cells (such as temperature, voltage, internal resistance, state of health), this one-size-fits-all charging strategy may cause some battery cells to be overcharged or undercharged, thereby affecting the lifespan and performance of the entire energy storage system. At the same time, due to the lack of an effective coordination mechanism, the mutual influence between battery cells is not fully considered, further reducing the overall efficiency of the system. Based on this, the present invention provides a specific embodiment. In step 102, according to the comprehensive energy management decision basis, an adaptive algorithm is used to adjust the charging equalization strategy among multiple distributed battery cells in the solar energy storage system to obtain an optimized charge-discharge plan, which specifically includes the following steps:

[0082] Step 201: Based on the real-time power input data, the current energy storage levels of each battery cell in the solar energy storage system, the predicted lighting conditions, and the user's power consumption pattern in the comprehensive energy management decision basis, set the target charging rate and the maximum allowable charging amount for each battery cell to obtain preliminary charging parameters;

[0083] In this step, the real-time power input data includes parameters such as the hourly power generation and voltage of the solar panels, which are used to evaluate the current power production capacity; the energy storage levels of each battery cell in the SESF reflect the current state of charge (SoC) of the battery, which is the basis for determining the charging strategy; the predicted lighting conditions are information such as the solar radiation intensity and weather conditions in the next few days provided by the meteorological forecast service, which helps to estimate the future power production potential; the user's power consumption pattern refers to the user's daily power consumption habits, such as the power consumption distribution during peak and off-peak hours;

[0084] By integrating these four types of data in this step, a target charging rate and a maximum allowable charging amount are set for each battery cell. This not only considers the current power input capacity and the state of charge of the battery, but also combines the predicted future lighting conditions and the user's power consumption pattern to ensure that the charging plan can make full use of the real-time power input and adapt to future changes in power demand. The preliminary charging parameters provide a basis for subsequent optimization calculations;

[0085] In an example where a solar energy storage facility is installed in a residential area, predictive data on lighting conditions from the local weather station is received every early morning. This is combined with the time-of-use electricity price schedule released by the power grid company and the actual power generation records of the household's solar panels from the previous day. At the same time, the historical electricity consumption data of each household is analyzed to understand their daily electricity usage patterns. For example, it is found that a household typically uses a large amount of electricity between 7 am and 9 am in the morning and less electricity between 3 pm and 5 pm in the afternoon. Based on this information, the optimal charge and discharge strategies for the current day and the next few days can be planned in advance, and appropriate target charging rates and maximum allowable charging amounts can be set for each battery unit to ensure that the battery can be fully charged when the electricity price is low and sufficient power support can be provided during high electricity prices or peak electricity consumption periods.

[0086] Step 202: According to the preliminary charging parameters, combining the adaptive control theory and the multi-objective optimization algorithm, calculate the characteristic parameters of each battery unit and external environmental factors to obtain the optimal charging current and charging timing. Based on the optimal charging current and charging timing, obtain the initial charging equalization strategy;

[0087] In this step, the adaptive control theory is a theoretical framework that can automatically adjust parameters according to changes in the external environment, and the multi-objective optimization method refers to the method of finding the optimal solution among multiple conflicting objectives;

[0088] By analyzing the characteristic parameters of each battery unit and their relationship with external environmental factors, dynamically adjust the target charging current and charging time of each battery unit. Not only consider the state of a single battery unit, but also consider the mutual influence between them to ensure the efficient operation and long-term stability of the entire solar energy storage facility. Based on these calculation results, form the initial charging equalization strategy to guide subsequent charging behaviors;

[0089] Continuing with the example of the solar energy storage facility in the above residential area, assume that there are multiple different types of lithium battery units configured inside the facility. As the seasons change, some battery units may exhibit different performances due to temperature differences. By combining the adaptive control theory and the multi-objective optimization method, the charging parameters of each battery unit can be automatically adjusted according to the real-time monitored working state of each battery unit. For example, in winter under low temperature conditions, the charging speed of those battery units that are more affected by low temperature will be appropriately increased, or in summer under high temperature environments, the charging intensity of battery units that are prone to overheating will be reduced. In this way, the solar energy storage facility can maintain the best performance under various conditions and extend the overall service life.

[0090] Step 203: Based on the initial charging equalization strategy, monitor the state changes of each battery unit during the actual charging process, adjust the charging parameters, and introduce an anomaly detection mechanism to identify charging behaviors that affect the safety of the energy storage system to obtain the adjusted charging equalization strategy;

[0091] In this step, the state changes include, but are not limited to, changes in parameters such as the temperature, voltage, and internal resistance of the battery cells. The anomaly detection mechanism refers to the timely detection of abnormal conditions that may lead to system failures or safety hazards through real-time monitoring and data analysis;

[0092] In this step, by continuously monitoring the state changes of each battery cell during the charging process, once an abnormal condition is detected, the charging parameters are immediately adjusted to avoid potential safety risks. In addition, by introducing an anomaly detection mechanism, charging behaviors that may affect system safety can be identified at an early stage, and corresponding protection measures can be taken to ensure the stable operation of the system;

[0093] Continuing with the previous example, during the charging process, the solar energy storage facility continuously collects the state data of each battery cell, such as temperature, voltage, internal resistance, etc. If the temperature of a certain battery cell suddenly rises above the preset threshold, the charging power of this battery cell will be immediately reduced to prevent safety risks caused by overheating. At the same time, this abnormal event will be recorded and incorporated into subsequent optimization calculations. For example, if it is found that a certain type of battery cell is prone to temperature rise under specific conditions, the charging strategy will be automatically adjusted under similar future conditions to reduce the charging intensity of this type of battery cell, thereby ensuring the safety and reliability of the entire facility.

[0094] Step 204: Use the comparison of the state information of each battery cell before and after each charging cycle to evaluate the effectiveness of the adjusted charging equalization strategy, update the parameter settings of the adaptive algorithm, analyze the historical charging records through machine learning techniques, and generate an optimized charge-discharge plan;

[0095] In this step, the comparison of state information refers to comparing various indicators of the battery cells before and after charging, such as the state of charge, temperature, voltage, etc., to evaluate the effect of the charging equalization strategy; machine learning techniques refer to training through a large amount of historical data so that the model can automatically learn and optimize future behaviors;

[0096] In this step, by comparing the state information of each battery cell before and after each charging cycle, it is evaluated whether the adjusted charging equalization strategy is effective. If it is found that the strategy fails to achieve the expected effect, the parameter settings of the adaptive control theory will be updated according to the actual situation. In addition, by analyzing the historical charging records through machine learning techniques, rules are found and improvement plans are proposed, and finally a more optimized charge-discharge plan is generated to further improve the operation efficiency of the solar energy storage facility;

[0097] To ensure the long-term stable operation of solar energy storage facilities and the virtual power plant projects where they are located, the effectiveness of cross-regional energy dispatching is regularly evaluated. For example, if the solar energy storage facilities in a certain residential area fail to meet the expected power output targets for several consecutive days, possible reasons will be analyzed, such as inaccurate weather forecasts or changes in user electricity consumption patterns. Based on these analysis results, future dispatching strategies will be adjusted accordingly, such as storing more electricity in advance or adjusting the power exchange plan with other regions. In this way, the solar energy storage facilities can not only better cope with unforeseen changes but also continuously optimize their own performance and provide more reliable services to users.

[0098] Based on this, the present invention also provides a specific embodiment. In step 202, according to the preliminary charging parameters, combining the adaptive control theory and the multi-objective optimization algorithm, the characteristic parameters of each battery unit and external environmental factors are calculated to obtain the optimal charging current and charging timing. Based on the optimal charging current and charging timing, an initial charging equalization strategy is obtained, which specifically includes the following steps:

[0099] Step 301: Using the preliminary charging parameters, combining the adaptive control theory and the multi-objective optimization algorithm, comprehensively evaluate the characteristic parameters of each battery unit, and introduce a dynamic weight factor to reflect the importance of different parameters under different conditions, so as to obtain a comprehensive evaluation result;

[0100] In this step, the characteristic parameters include temperature, voltage, internal resistance, and health status, etc., which are used to describe the working conditions of each battery unit; while the external environmental factors cover information such as temperature, humidity, and changes in light intensity, which affect the performance of the battery unit. The dynamic weight factor is a method that can adjust the weight value according to real-time data to ensure that the importance of different parameters can be flexibly adjusted with the change of external conditions;

[0101] This step integrates the preliminary charging parameters, applies the adaptive control theory and the multi-objective optimization method, analyzes the characteristic parameters of each battery unit in the SESF and their relationship with external environmental factors, assigns a basic weight to each parameter, and introduces a dynamic weight factor to reflect the actual importance of different parameters under the current conditions. A comprehensive evaluation result is generated, providing a scientific basis for the subsequent calculation of the optimal charging current and the optimal charging timing;

[0102] In an example where a SESF is installed in a residential area, predictive data on lighting conditions from a local weather station is received every early morning. This is combined with the time-of-use electricity price schedule issued by the power grid company and the actual power generation records of the home's solar panels from the previous day. Meanwhile, the characteristic parameters of each battery cell within the SESF, such as temperature, voltage, internal resistance, and health status, are analyzed. By introducing a dynamic weight factor, the importance of these parameters can be flexibly adjusted based on real-time power input data and lighting condition predictions. For example, under low-temperature conditions in winter, the weight of the temperature parameter is increased to ensure that the battery cells do not experience performance degradation due to low temperature. This lays a solid foundation for subsequent personalized adjustments.

[0103] Step 302: According to the comprehensive evaluation results, use a machine learning model to predict the performance change trend of each battery cell. Combine the real-time power input data and lighting condition predictions to calculate the optimal charging current and optimal charging timing, and generate the optimal charging parameters.

[0104] In this step, the machine learning model refers to a mathematical model trained with a large amount of historical data that can predict performance changes over a period of time in the future; the real-time power input data includes parameters such as the hourly power generation and voltage of the solar panels; the lighting condition prediction consists of information such as the solar radiation intensity and weather conditions in the next few days provided by the weather forecast service.

[0105] This step is based on the comprehensive evaluation results and uses a machine learning model to predict the performance change trend of each battery cell over a period of time in the future. Combining the real-time power input data and lighting condition predictions, the optimal charging current and optimal charging timing for each battery cell are calculated. This not only considers the state of a single battery cell but also combines future power production and demand situations, ensuring that the charging plan can make full use of real-time power input and adapt to future changes in power demand.

[0106] Continuing with the example of the SESF in the above-mentioned residential area, assume that there are multiple different types of lithium battery cells configured inside the facility. Use a machine learning model to predict the performance change trend of each battery cell in the next few days. Combine the real-time power input data and lighting condition predictions to calculate the optimal charging current and optimal charging timing for each battery cell. For example, if it is predicted that there will be consecutive cloudy days in the next few days, the charging amount during the day will be increased in advance to ensure that the SESF has enough power to cope with possible power shortages. In addition, if the historical data of a certain battery cell shows that it is prone to performance fluctuations under specific conditions, the charging strategy of this battery cell will be appropriately adjusted under similar conditions to ensure the stable operation of the entire SESF.

[0107] Step 303: Based on the user's historical electricity consumption pattern, make personalized adjustments to the optimal charging parameters to generate personalized charging parameters.

[0108] In this step, the user's historical electricity consumption pattern refers to the electricity consumption behavior pattern of the user over a period of time in the past, such as the electricity consumption distribution during peak and off-peak hours. By analyzing these patterns, the user's daily electricity consumption habits can be identified, and the optimal charging parameters can be adjusted accordingly to better meet the actual needs of the user;

[0109] In this step, the user's daily electricity consumption habits will be analyzed to identify specific time periods and electricity consumption characteristics, and then combined with the current electricity demand forecast, the optimized charge and discharge plan will be adjusted to better meet the actual needs of the user. This can not only improve the user experience, but also further optimize the energy utilization efficiency and reduce unnecessary electricity waste;

[0110] Continuing with the previous example, SESF will also collect the historical electricity consumption data of each household to understand their daily electricity consumption patterns. For example, it is found that a household usually uses a large amount of electricity between 7 am and 9 am in the morning, and less electricity between 3 pm and 5 pm in the afternoon. Based on this information, the battery can be pre-charged when the electricity price is low at night, and the electricity can be released during the morning peak hours for the household to use, while the external power supply can be appropriately reduced during the afternoon off-peak hours to ensure that the electricity in SESF is always in an optimal state, meeting the needs of the household and achieving energy-saving effects.

[0111] Step 304: Use the personalized charging parameters to calculate the mutual influence between adjacent battery cells, determine the priority and cooperation method of each battery cell during the charging process, and form an initial charging balance strategy

[0112] In this step, the mutual influence between adjacent battery cells refers to the physical connection relationship and electrical characteristics between battery cells, which affect each other's charging efficiency and safety; the charging priority refers to determining which battery cells should be charged first according to the current state and future needs of the battery cells; the cooperation method refers to how to coordinate the charging behaviors of each battery cell to ensure the efficient operation of the overall energy storage system;

[0113] In this step, the personalized charging parameters will be used to consider the mutual influence between adjacent battery cells, and determine the priority and cooperation method of each battery cell during the charging process. In this way, not only the efficient charging of a single battery cell is ensured, but also the stability and reliability of the entire SESF are ensured. The formed initial charging balance strategy guides the subsequent charging behavior, making the charging process more intelligent and optimized;

[0114] To ensure the efficient operation of the SESF, after setting personalized charging parameters, the mutual influence between adjacent battery cells is further considered. For example, if some battery cells are in the same string, it is ensured that the charging currents between them are consistent, avoiding problems such as overheating or uneven charging caused by current differences. In addition, the charging priority is determined according to the current state of charge and future demand of the battery cells. For example, those battery cells that need to be charged faster to support the upcoming power peak will be charged first. In this way, the SESF can maintain optimal performance under various conditions, extend the overall service life, and provide more reliable services for users.

[0115] Based on this, the present invention also provides a specific embodiment. In step 301, using the preliminary charging parameters, combining the adaptive control theory and the multi-objective optimization algorithm, comprehensively evaluate the characteristic parameters of each battery cell, and introduce a dynamic weight factor to reflect the importance of different parameters under different conditions, and obtain the comprehensive evaluation result, which specifically includes the following steps:

[0116] Step 401: Using the preliminary charging parameters, combining the adaptive control theory and the multi-objective optimization algorithm, conduct a preliminary analysis of the characteristic parameters of each battery cell and external environmental factors to obtain an initial parameter evaluation;

[0117] In this step, the characteristic parameters include temperature, voltage, internal resistance, and health status, etc., which are used to describe the working conditions of each battery cell; while the external environmental factors cover information such as temperature, humidity, and light intensity changes, which affect the performance of the battery cell. The adaptive control theory is a theoretical framework that can automatically adjust parameters according to changes in external conditions, and the multi-objective optimization method refers to a method of finding the optimal solution among multiple conflicting objectives;

[0118] In this step, by integrating the preliminary charging parameters, applying the adaptive control theory and the multi-objective optimization method, analyzing the characteristic parameters of each battery cell in the SESF and their relationship with external environmental factors, an initial parameter evaluation is generated, providing a scientific basis for the subsequent construction of the parameter influence model;

[0119] In an example where a set of SESF is installed in a residential area, it receives the predicted data of the lighting conditions from the local meteorological station every morning, combines it with the time-of-use electricity price table released by the power grid company, and the actual power generation record of its own solar panels the previous day. At the same time, it analyzes the characteristic parameters of each battery cell in the SESF, such as temperature, voltage, internal resistance, and health status. Through the preliminary analysis, it can be identified which parameters have a greater impact on the performance of the battery cell under the current conditions. For example, in a high-temperature environment, the temperature parameter may be particularly important, laying a solid foundation for the subsequent construction of the parameter influence model.

[0120] Step 402: Based on the initial parameter evaluation, construct a parameter influence model, calculate the interactions between different parameters under different conditions, assign a basic weight to each parameter, and generate a basic weight setting;

[0121] In this step, the parameter influence model is a mathematical model used to quantify the relationships between different parameters and their responses to changes in external conditions; the basic weight refers to the initial weight value assigned to different parameters according to their importance, reflecting their relative importance in the comprehensive evaluation;

[0122] This step constructs a parameter influence model based on the initial parameter evaluation results and calculates the interactions between different parameters under different conditions. By analyzing these interactions, a basic weight is assigned to each parameter to ensure that the unique contribution of each parameter is fully considered during the evaluation process, generating a basic weight setting that provides the necessary basis for introducing dynamic weight factors in the subsequent steps;

[0123] Continuing with the SESF of the above residential area as an example, assume that multiple different types of lithium battery units are configured inside the facility. Through the initial analysis, the importance and interactions of each parameter are determined. For example, it is found that the temperature has a significantly greater impact on certain types of battery units than other parameters. Based on this information, a parameter influence model is constructed, and the interactions between different parameters under different conditions are calculated. Then, a basic weight is assigned to each parameter. For example, the basic weight of the temperature parameter is set to a relatively high value to reflect its importance under the current conditions, preparing for the introduction of dynamic weight factors in the subsequent steps.

[0124] Step 403: Based on the basic weight setting, introduce a dynamic weight factor, and use real-time power input data and predicted light conditions to adjust the basic weights of each parameter, reflecting the actual importance of different parameters under the current conditions, and obtaining a dynamic weight configuration;

[0125] In this step, the dynamic weight factor is a method that can adjust the weight value according to real-time data, ensuring that the importance of different parameters can be flexibly adjusted with changes in external conditions; the real-time power input data includes parameters such as the hourly power generation and voltage of the solar panels; the predicted light conditions are information such as the solar radiation intensity and weather conditions in the next few days provided by the meteorological forecast service;

[0126] This step introduces a dynamic weight factor and uses real-time power input data and predicted light conditions to dynamically adjust the basic weights of each parameter, ensuring that the evaluation results can accurately reflect the current and future operating conditions, improving the flexibility and accuracy of decision-making. The dynamic weight configuration provides more accurate data support for the subsequent comprehensive evaluation;

[0127] Continuing with the previous example, the SESF continuously monitors real-time power input data and light condition predictions, combines the user's historical electricity consumption patterns, and dynamically adjusts the base weights of various parameters. For example, if continuous cloudy days are predicted in the next few days, the weight of the light condition prediction parameter will be increased to reserve more electricity in advance to cope with possible power shortages. In addition, if the historical data of a certain battery cell shows that it is prone to performance fluctuations under specific conditions, the weights of the relevant parameters of this battery cell will be appropriately adjusted under similar conditions to ensure the stable operation of the entire SESF. This provides a more accurate weight configuration for the final comprehensive evaluation.

[0128] Step 404: Using the dynamic weight configuration, re-evaluate the influence of the characteristic parameters of each battery cell and external environmental factors, and generate an updated comprehensive evaluation result;

[0129] In this step, using the dynamic weight configuration, re-evaluate the influence of the characteristic parameters of each battery cell and external environmental factors, and generate an updated comprehensive evaluation result to ensure that the evaluation result can accurately reflect the current and future operating conditions, providing a solid scientific basis for subsequent adjustment of the charging balance strategy, enabling the SESF to maintain the best performance under various conditions;

[0130] To ensure the efficient operation of the SESF, after setting the dynamic weight configuration, re-evaluate the influence of the characteristic parameters of each battery cell and external environmental factors. For example, if it is found that the performance of a certain battery cell drops significantly under low-temperature conditions, it will correspondingly adjust the weight of the relevant parameters of this battery cell to ensure its priority charging under low-temperature conditions. In this way, the SESF can maintain the best performance under various conditions, extend the overall service life, and provide more reliable services to users. Finally, an updated comprehensive evaluation result is generated.

[0131] Since most current energy management decisions are based on historical data and fixed rules, and do not fully utilize the real-time solar panel power input data, grid dynamic electricity price information, and light condition predictions provided by weather forecast services, it is difficult for solar energy storage systems to make optimal real-time responses, especially when facing rapidly changing external conditions such as sudden weather conditions or sudden power demand peaks. Based on this, the present invention provides a specific embodiment. In step 103, based on the user's historical electricity consumption pattern and current power demand prediction, personalize the optimized charge and discharge plan to generate a personalized electricity usage plan, which specifically includes the following steps:

[0132] Step 501: Analyze the user's daily electricity consumption pattern using the user's historical electricity consumption data to obtain the user electricity consumption pattern analysis result;

[0133] In this step, the user's historical electricity consumption data refers to the electricity usage records of the user over a past period, including the electricity consumption per hour or per day, the electricity usage characteristics during peak and off-peak hours, etc. Through in-depth analysis of this data, the user's electricity usage habits and patterns can be identified, such as which time periods have higher electricity consumption, which time periods have lower electricity consumption, and whether there are periodic electricity usage behaviors;

[0134] In this step, by analyzing the user's historical electricity consumption data, the user's daily electricity usage patterns are identified, classified and sorted to form the analysis results of the user's electricity usage patterns. Not only the average electricity consumption of the user is considered, but also the time distribution and change trend of electricity usage are concerned, providing detailed data support for subsequent personalized adjustments;

[0135] Collect the historical electricity consumption data of each household to understand their daily electricity usage patterns. For example, it is found that a household usually uses a large amount of electricity between 7 am and 9 am in the morning, and has less electricity consumption between 3 pm and 5 pm. Based on this information, the optimal charging and discharging strategies for the current day and the next few days can be planned in advance to ensure that the electricity in the SESF can be fully charged when the electricity price is low and can provide sufficient power support during high electricity price periods or peak electricity usage times.

[0136] Step 502: According to the analysis results of the user's electricity usage patterns, combined with the current electricity demand forecast, evaluate the electricity demand fluctuation situation and generate an electricity demand forecast;

[0137] In this step, the electricity demand forecast refers to the estimation of the electricity demand in the future for a period of time, considering external conditions such as weather changes and seasonal factors, and predicting the possible future peak and off-peak electricity usage periods. By combining the user's historical electricity usage patterns, the future electricity demand can be estimated more accurately, improving the accuracy of the forecast;

[0138] In this step, based on the analysis results of the user's electricity usage patterns, combined with the current electricity demand forecast, evaluate the electricity demand fluctuation situation in the future for a period of time. By analyzing these fluctuations, a detailed electricity demand forecast is generated, providing a basis for the subsequent adjusted and optimized charging and discharging plan. Ensuring that the charging and discharging strategies can better adapt to the actual needs of users;

[0139] Assume that the daily electricity usage patterns of each household have been mastered. On this basis, the electricity demand fluctuation situation in the next few days will also be evaluated by combining the light condition forecast provided by the local meteorological forecast service and the time-of-use electricity price table released by the power grid company. For example, if it is predicted that there will be a large community event on a certain weekend, resulting in a significant increase in electricity demand, more electricity will be stored before the event to meet the demand during peak hours. In addition, according to the weather forecast, solar power generation can be preferentially used on sunny days, and the battery discharge amount can be appropriately increased on cloudy days to ensure the stability of power supply.

[0140] Step 503: Based on the power demand prediction, adjust the charging priorities and discharging strategies in the optimized charging and discharging plan to form an initial personalized power usage plan;

[0141] In this step, the charging priority refers to determining which battery units should be charged first according to the status of the battery units and future demands; while the discharging strategy refers to how to reasonably arrange the discharging sequence and power of each battery unit to ensure the stability and efficiency of power supply;

[0142] In this step, according to the power demand prediction, adjust the charging priorities and discharging strategies in the optimized charging and discharging plan to ensure that the SESF can maintain the best performance under various conditions. The formed initial personalized power usage plan guides subsequent charging and discharging behaviors, enabling the SESF to not only meet the immediate needs of users but also adapt to future changes in power demands;

[0143] Continuing with the previous example, after setting the power demand prediction, the SESF further adjusts the optimized charging and discharging plan. For example, if it is predicted that a certain household will use a large amount of power between 8 pm and 10 pm, it will be pre-charged during the period when the electricity price is low during the day and release power during the evening peak period for the household to use. In addition, if the historical data of a certain battery unit shows that it is prone to performance fluctuations under specific conditions, the charging strategy of this battery unit will be appropriately adjusted under similar conditions to ensure the stable operation of the entire SESF.

[0144] Step 504: Use a machine learning model to optimize the preliminary personalized power usage plan, calculate the influence of external factors, and adjust the charging and discharging time points and power in the preliminary personalized power usage plan to obtain the best personalized power usage plan;

[0145] In this step, the machine learning model refers to a mathematical model trained with a large amount of historical data, which can automatically learn and optimize future charging and discharging behaviors; external factors include variables such as weather changes and electricity price fluctuations that affect power production and usage;

[0146] In this step, use the machine learning model to analyze historical charging records, calculate the influence of external factors (such as weather changes and electricity price fluctuations) on the preliminary personalized power usage plan. By adjusting the charging and discharging time points and power, continuously optimize the preliminary personalized power usage plan to ensure that it is more in line with the actual situation and finally generate the best personalized power usage plan;

[0147] To ensure the long-term stable operation of the SESF and the virtual power plant project it belongs to, the effectiveness of cross-regional energy dispatch is regularly evaluated. For example, if the SESF in a certain residential area fails to reach the expected power output target for several consecutive days, possible reasons will be analyzed, such as inaccurate weather forecasts or changes in user electricity consumption patterns. Based on these analysis results, future dispatch strategies will be adjusted accordingly, such as storing more electricity in advance or adjusting the power exchange plan with other regions. In addition, through machine learning models, the initial personalized electricity usage plan can be continuously optimized. For example, when it is predicted that there will be consecutive cloudy days in the next few days, the charging amount during the day will be increased in advance to ensure that the SESF has enough electricity to cope with possible power shortages.

[0148] Based on this, the present invention provides a specific embodiment. In step 104, according to the personalized electricity usage plan, a virtual power plant model is constructed, and the charging and discharging behavior of the solar energy storage system is coordinately controlled by using the virtual power plant model to generate a cross-regional energy dispatch plan, which specifically includes the following steps:

[0149] Step 601: Using the personalized electricity usage plan, combining the data of other renewable energy power generation facilities and user-side flexible loads within the region, construct a virtual power plant model including the solar energy storage system;

[0150] In this step, the personalized electricity usage plan refers to a charging and discharging plan customized according to the user's daily electricity consumption pattern and power demand prediction; other renewable energy power generation facilities include wind turbines, small hydropower stations, etc.; the user-side flexible load data involves the changes in the user's electricity consumption behavior at different time periods. VPPM is a digital platform that integrates dispersed renewable energy power generation equipment and load resources and participates in power market transactions and technical regulation as a whole;

[0151] In this step, by integrating the personalized electricity usage plan, the data of other renewable energy power generation facilities within the region, and the information of user-side flexible loads, a comprehensive VPPM is constructed. It not only considers the state of the battery units inside the SESF but also combines external resources and user behavior, providing a unified framework for subsequent energy dispatch;

[0152] In the example of a SESF installed in a residential area, historical electricity consumption data for each resident is collected and combined with data from other renewable energy generation facilities in the area, such as power generation records of nearby wind turbines. Based on this information, a virtual power plant model that includes the SESF can be built. For example, if a resident usually uses a lot of electricity between 7 and 9 in the morning, and a nearby wind turbine has a higher power generation at night, it can be pre-charged when the night electricity price is lower, and the power can be released for the resident during the morning peak period. In addition, the power exchange between the SESF and other power generation facilities can be coordinated to ensure a more stable and efficient power supply for the entire area.

[0153] Step 602: Based on the virtual power plant model, analyze the relationship and synergy potential between the power generation facilities and loads in the region, determine the role positioning of different facilities in different time periods, and form an initial role allocation;

[0154] In this step, the interrelationship refers to the physical connection and electrical characteristics between each power generation facility and load; the synergy potential refers to the maximum benefit that can be achieved through optimal scheduling between them;

[0155] In this step, VPPM is used to analyze the relationship and synergy potential between various power generation facilities and loads, and determine the roles of different facilities at different times. This ensures that each facility can perform at its best in the most suitable time period, thus improving the energy efficiency of the entire region.

[0156] Continuing with the example of the SESF in the residential area mentioned above, it is assumed that a virtual power plant model including the SESF has been built. On this basis, the interrelationships and synergy potentials between the various power generation facilities and loads in the region will be analyzed. For example, it is found that the power generation of solar panels is larger during the day, while the power generation of wind turbines is higher at night. Based on this information, it can be determined that the SESF mainly plays the role of energy storage during the day and is mainly responsible for power supply at night. In addition, the flexibility of electricity consumption of certain users in specific time periods can be identified, such as a resident can adjust the electricity consumption time between 8 pm and 10 pm, thereby further optimizing the power dispatch of the entire area.

[0157] Step 603: Formulate charging and discharging coordination rules among facilities according to the initial role allocation, and generate a preliminary cross-regional energy scheduling plan;

[0158] In this step, the charge-discharge coordination rule refers to how to reasonably arrange the charging and discharging sequence and power between facilities to ensure the stability and efficiency of power supply; the preliminary cross-regional energy dispatch plan refers to the preliminary power dispatch planning between facilities in the region;

[0159] In this step, based on the initial role assignment, charging and discharging coordination rules are formulated among various facilities to ensure that each facility can achieve the maximum efficiency during the most suitable time period. In this way, a preliminary cross-regional energy scheduling plan is generated to guide subsequent power scheduling behaviors, making the power supply in the entire region more stable and efficient;

[0160] Continuing with the previous example, after setting the initial role assignment, SESF further formulates the charging and discharging coordination rules among various facilities. For example, if SESF mainly plays the role of energy storage during the day, it will preferentially use the electricity generated by solar panels to charge SESF during the day and preferentially use the electricity stored in SESF for users at night. In addition, according to the power generation situation of wind turbines, the charging and discharging strategies of SESF will be appropriately adjusted to ensure that the power supply in the entire region is more stable and efficient.

[0161] Step 604: Use machine learning algorithms to evaluate the feasibility and adaptability of the preliminary cross-regional energy scheduling plan, calculate the uncertain factors in actual operation, and adjust the preliminary cross-regional energy scheduling plan to obtain the target cross-regional energy scheduling plan;

[0162] In this step, machine learning algorithms are used to evaluate the feasibility and adaptability of the preliminary cross-regional energy scheduling plan, and calculate the uncertain factors in actual operation, such as weather changes and electricity price fluctuations. By adjusting the preliminary cross-regional energy scheduling plan, the scheduling strategy is continuously optimized to ensure that it is more in line with the actual situation, and finally the target cross-regional energy scheduling plan is generated;

[0163] To ensure the long-term stable operation of SESF and the virtual power plant project it belongs to, the effects of the preliminary cross-regional energy scheduling plan are regularly evaluated. For example, if the SESF in a certain residential area fails to reach the expected power output target for several consecutive days, possible reasons will be analyzed, such as inaccurate weather forecasts or changes in user electricity consumption patterns. Based on these analysis results, future scheduling strategies will be adjusted accordingly, such as storing more electricity in advance or adjusting the power exchange plan with other regions. In addition, through machine learning algorithms, the preliminary cross-regional energy scheduling plan can be continuously optimized. For example, when it is predicted that there will be continuous cloudy days in the next few days, the charging amount during the day will be increased in advance to ensure that SESF has enough electricity to cope with possible power shortages. In this way, SESF can not only better cope with unforeseen changes, but also continuously optimize its own performance and provide more reliable services for users. Finally, the target cross-regional energy scheduling plan is generated to ensure that the power supply in the entire region is more stable and efficient.

[0164] Based on this, the present invention provides a specific embodiment. Step 105 specifically includes the following steps:

[0165] Step 701: Generate the decision-making basis for the integrated energy management of the solar energy storage system by using the real-time obtained solar panel power input data, grid dynamic electricity price information, and the predicted lighting conditions provided by the weather forecast service;

[0166] In this step, the solar panel power input data includes parameters such as the hourly power generation and voltage, which are used to evaluate the current power production capacity; the grid dynamic electricity price information covers the electricity price fluctuations in different periods, which is used to optimize the charging and discharging costs; the predicted lighting conditions provided by the weather forecast service include the solar radiation intensity, weather conditions, etc. in the next few days, which helps to estimate the future power production potential;

[0167] In this step, by integrating the above three types of data, a comprehensive integrated energy management decision-making framework is constructed. This framework can analyze and predict the energy supply and demand situation in the next period of time in real time, providing a scientific basis for the subsequent adjustment of the charging balance strategy. Specifically, the optimal charging and discharging time points and power levels will be calculated based on these data to ensure the minimization of operating costs while meeting the user's needs;

[0168] In an example where a SESF is installed in a residential area, it receives the predicted lighting condition data from the local weather station every early morning, combines it with the time-of-use electricity price table released by the power grid company, and the actual power generation record of its own solar panels the previous day. Through this information, the best charging and discharging strategies for the current day and the next few days can be planned in advance. For example, increase the charging amount during the predicted sunny days and low electricity price periods, and give priority to using the stored electricity during rainy days or high electricity price periods, so as to maximize the economic benefits.

[0169] Step 702: According to the integrated energy management decision-making basis, use an adaptive algorithm to adjust the charging balance strategy among multiple distributed battery units in the solar energy storage system to obtain an optimized charging and discharging plan;

[0170] In this step, the charging balance strategy refers to how to reasonably distribute the charging current and time of each battery unit to ensure that all batteries can work in the best state;

[0171] In this step, the adaptive control theory will analyze the characteristic parameters of each battery unit (such as temperature, voltage, internal resistance, health status) and their relationships with external environmental factors (such as temperature, humidity, light intensity changes), and dynamically adjust the target charging rate of each battery unit. It not only considers the state of a single battery unit but also the mutual influence between them, ensuring the efficient operation and long-term stability of the entire SESF;

[0172] Continuing with the SESF in the above-mentioned residential area as an example, assume that multiple different types of lithium battery units are configured inside the SESF. As the seasons change, some battery units may exhibit different performances due to temperature differences. The adaptive control theory can automatically adjust the charging parameters according to the working status of each battery unit monitored in real time. For example, increasing the charging speed of battery units that perform poorly at low temperatures, or reducing the charging intensity of battery units that are prone to overheating in high-temperature environments. In this way, the SESF can maintain optimal performance under various conditions and extend the overall service life.

[0173] Step 703: Based on the user's historical electricity consumption pattern and the current electricity demand forecast, customize the optimized charge and discharge plan to generate a personalized electricity usage plan;

[0174] In this step, analyze the user's daily electricity consumption habits, identify specific time periods and electricity consumption characteristics, and then combine the current electricity demand forecast to adjust the optimized charge and discharge plan to make it more in line with the user's actual needs. This can not only improve the user experience but also further optimize the energy utilization efficiency and reduce unnecessary electricity waste;

[0175] Continuing with the previous example, the SESF will also collect the historical electricity consumption data of each household to understand their daily electricity consumption patterns. For example, it is found that a household usually uses a large amount of electricity between 7 am and 9 am and less electricity between 3 pm and 5 pm. Based on this information, it can be pre-charged when the electricity price is low at night and release electricity during the morning peak period for this household to use, while reducing the external power supply appropriately during the afternoon low period to ensure that the electricity in the SESF is always in an optimal state, meeting the needs of the household while achieving energy-saving effects.

[0176] Step 704: According to the personalized electricity usage plan, construct a virtual power plant model, and use the virtual power plant model to coordinate and control the charge and discharge behavior of the solar energy storage system to generate a cross-regional energy scheduling plan

[0177] In this step, the VPPM will comprehensively consider the personalized electricity usage plans of all participants in the region and formulate unified charge and discharge coordination rules. In this way, not only can the local electricity supply and demand be balanced, but it can also work in coordination with similar facilities in other regions to form an energy scheduling network on a larger scale. This cross-regional collaboration helps to make full use of renewable resources in each region and improve the stability and flexibility of the entire power system;

[0178] Suppose the SESF in a residential area joins a local virtual power plant project, which covers multiple similar residential areas and other types of distributed energy facilities. When the SESF in a certain residential area generates excessive electricity during the day, the VPPM can coordinate to transfer its excess electricity to other areas with power shortages; conversely, at night or on cloudy days, the VPPM can also allocate power from other places with surplus electricity to supplement. In addition, the VPPM can also respond to the peak shaving requirements of the power grid company, such as increasing power supply to the outside during peak electricity prices or charging more during off-peak electricity prices, so as to optimize the operating efficiency of the entire power system.

[0179] Step 705: Use a machine learning algorithm to calculate the difference value between the actual effect and the predicted effect during the implementation of the cross-regional energy scheduling scheme, and based on the difference value, perform energy regulation of the solar energy storage system;

[0180] In this step, the machine learning algorithm continuously monitors the implementation of the cross-regional energy scheduling scheme, collects relevant data and analyzes it. Once it is found that the actual effect deviates from the predicted effect, the algorithm will automatically adjust the subsequent scheduling strategy to correct the deviation and optimize future performance. This feedback mechanism ensures that the scheduling scheme can be continuously improved according to the actual situation, improving the stability and reliability of the operation of the entire solar energy storage facility;

[0181] To ensure the long-term stable operation of the SESF and the virtual power plant project it belongs to, the effect of cross-regional energy scheduling is regularly evaluated. For example, if the SESF in a certain residential area fails to reach the expected power output target for several consecutive days, the machine learning algorithm will analyze the possible reasons, such as inaccurate weather forecasts or changes in user electricity consumption patterns. Based on these analysis results, the future scheduling strategy will be adjusted accordingly, such as storing more electricity in advance or adjusting the power exchange plan with other regions. In this way, the SESF can not only better cope with unforeseen changes, but also continuously optimize its own performance and provide more reliable services for users.

[0182] Figure 2 The structure diagram of an energy regulation system for a solar energy storage system is provided for an embodiment of the present invention, as Figure 2 shown, the system includes:

[0183] An acquisition module 21, configured to generate a basis for comprehensive energy management decision-making for the solar energy storage system by using the solar panel power input data obtained in real time, the grid dynamic electricity price information, and the light condition prediction provided by the weather forecast service;

[0184] An adjustment module 22, configured to adjust the charging balance strategy between multiple distributed battery units in the solar energy storage system by using an adaptive algorithm according to the comprehensive energy management decision-making basis, and obtain an optimized charge and discharge plan;

[0185] A customization module 23, configured to perform personalized customization on the optimized charge and discharge plan based on the user's historical electricity consumption pattern and current electricity demand prediction, and generate a personalized electricity consumption plan;

[0186] A construction module 24, configured to construct a virtual power plant model according to the personalized electricity consumption plan, and use the virtual power plant model to coordinately control the charge and discharge behavior of the solar energy storage system, and generate a cross-regional energy scheduling plan;

[0187] An execution module 25, configured to calculate the difference value between the actual effect and the estimated effect during the execution of the cross-regional energy scheduling plan by using a machine learning algorithm, and perform energy regulation of the solar energy storage system based on the difference value.

[0188] Figure 2 The energy regulation system of a solar energy storage system described above can execute Figure 1 the energy regulation method of a solar energy storage system described in the illustrated embodiment. The implementation principle and technical effects will not be elaborated here. For the energy regulation system of a solar energy storage system in the above embodiment, the specific manners in which each module and unit perform operations have been described in detail in the embodiment related to the method, and will not be elaborated here.

[0189] In a possible design, Figure 2 the energy regulation system of a solar energy storage system described in the illustrated embodiment can be implemented as a computing device, such as Figure 3 shown, and the computing device may include a storage component 31 and a processing component 32;

[0190] The storage component 31 stores one or more computer instructions, and the one or more computer instructions are called and executed by the processing component 32.

[0191] The processing component 32 is used to generate a basis for comprehensive energy management decision-making for the solar energy storage system by using the real-time acquired solar panel power input data, the dynamic grid electricity price information, and the predicted lighting conditions provided by the weather forecast service; according to the basis for comprehensive energy management decision-making, an adaptive algorithm is used to adjust the charging balance strategy among multiple distributed battery units in the solar energy storage system to obtain an optimized charge and discharge plan; based on the user's historical electricity consumption pattern and the current electricity demand prediction, the optimized charge and discharge plan is customized to generate a personalized electricity consumption plan; according to the personalized electricity consumption plan, a virtual power plant model is constructed, and the charge and discharge behavior of the solar energy storage system is coordinated and controlled by using the virtual power plant model to generate a cross-regional energy scheduling plan; a machine learning algorithm is used to calculate the difference value between the actual effect and the estimated effect during the execution of the cross-regional energy scheduling plan, and based on the difference value, the energy regulation of the solar energy storage system is executed.

[0192] Among them, the processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components for executing the above method.

[0193] The storage component 31 is configured to store various types of data to support the operation of the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0194] Of course, the computing device may also necessarily include other components, such as input / output interfaces, display components, communication components, etc.

[0195] The input / output interface provides an interface between the processing component and the peripheral interface module, and the above peripheral interface module may be an output device, an input device, etc.

[0196] The communication component is configured to facilitate wired or wireless communication between the computing device and other devices, etc.

[0197] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform. In this case, the computing device can refer to a cloud server. The above processing components, storage components, etc. can be basic server resources rented or purchased from a cloud computing platform.

[0198] An embodiment of the present invention also provides a computer storage medium storing a computer program, and when the computer program is executed by a computer, it can implement the above Figure 1 energy regulation method of a solar energy storage system shown in the embodiment.

[0199] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described systems, devices, and units can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0200] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0201] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0202] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments or perform equivalent replacements for some of the technical features. And these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An energy control method for a solar energy storage system, characterized in that: include: Using real-time solar panel power input data, dynamic grid electricity price information, and light condition forecasts provided by weather forecast services, a basis for comprehensive energy management decision-making for solar energy storage systems is generated; According to the comprehensive energy management decision basis, an adaptive algorithm is used to adjust the charging balancing strategy between multiple distributed battery units in the solar energy storage system to obtain an optimized charging and discharging plan; Based on the user's historical electricity consumption pattern and current electricity demand forecast, the optimized charging and discharging plan is personalized to generate a personalized electricity consumption plan; According to the personalized electricity consumption plan, a virtual power plant model is constructed, and the charging and discharging behaviors of the solar energy storage system are coordinated and controlled by using the virtual power plant model to generate a cross-regional energy scheduling plan; A machine learning algorithm is used to calculate the difference between the actual effect and the estimated effect during the execution of the cross-regional energy scheduling plan, and energy regulation of the solar energy storage system is performed based on the difference.

2. The method according to claim 1, characterized in that According to the comprehensive energy management decision basis, an adaptive algorithm is used to adjust the charging balancing strategy between multiple distributed battery units in the solar energy storage system to obtain an optimized charging and discharging plan, including: Based on the real-time power input data in the integrated energy management decision basis, the current energy storage level of each battery unit in the solar energy storage system, the light condition forecast and the user's power consumption pattern, the target charging rate and the maximum allowable charging amount of each battery unit are set to obtain preliminary charging parameters; According to the preliminary charging parameters, in combination with adaptive control theory and multi-objective optimization algorithm, characteristic parameters of each battery cell and external environmental factors are calculated to obtain an optimal charging current and charging sequence, and based on the optimal charging current and charging sequence, an initial charging balancing strategy is obtained; Based on the initial charging balancing strategy, the state changes of each battery unit during the actual charging process are monitored, the charging parameters are adjusted, and an abnormal detection mechanism is introduced to identify the charging behavior that affects the safety of the energy storage system, so as to obtain an adjusted charging balancing strategy; By comparing the status information of each battery cell before and after each charging cycle, the effectiveness of the adjusted charging equalization strategy is evaluated, the adaptive algorithm parameter settings are updated, and the historical charging records are analyzed through machine learning technology to generate an optimized charging and discharging plan.

3. The method according to claim 2, characterized in that According to the preliminary charging parameters, combined with adaptive control theory and multi-objective optimization algorithm, the characteristic parameters of each battery cell and external environmental factors are calculated to obtain the optimal charging current and charging sequence. Based on the optimal charging current and charging sequence, an initial charging balancing strategy is obtained, including: Using preliminary charging parameters, combined with adaptive control theory and multi-objective optimization algorithm, a comprehensive evaluation of the characteristic parameters of each battery cell is carried out, and a dynamic weight factor is introduced to reflect the importance of different parameters under different conditions, and a comprehensive evaluation result is obtained; Based on the comprehensive evaluation results, a machine learning model is used to predict the performance change trend of each battery cell, and the optimal charging current and optimal charging sequence are calculated in combination with real-time power input data and light condition prediction to generate optimal charging parameters; Based on the user's historical power usage pattern, the optimal charging parameters are adjusted individually to generate personalized charging parameters; The personalized charging parameters are used to calculate the mutual influence between adjacent battery cells, determine the priority and coordination mode of each battery cell during the charging process, and form an initial charging balancing strategy.

4. The method according to claim 3, characterized in that Using preliminary charging parameters, combined with adaptive control theory and multi-objective optimization algorithm, a comprehensive evaluation of the characteristic parameters of each battery cell is carried out, and a dynamic weight factor is introduced to reflect the importance of different parameters under different conditions, and a comprehensive evaluation result is obtained, including: Using the preliminary charging parameters, combined with adaptive control theory and multi-objective optimization algorithm, the characteristic parameters of each battery cell and external environmental factors are initially analyzed to obtain the initial parameter evaluation; Based on the initial parameter evaluation, a parameter impact model is constructed to calculate the interaction between different parameters under different conditions, a basic weight is assigned to each parameter, and a basic weight setting is generated; Based on the basic weight setting, a dynamic weight factor is introduced, and the basic weight of each parameter is adjusted by using real-time power input data and light condition prediction to reflect the actual importance of different parameters under current conditions, thereby obtaining a dynamic weight configuration; The dynamic weight configuration is used to evaluate the characteristic parameters of each battery cell and the influence of external environmental factors again to generate an updated comprehensive evaluation result.

5. The method according to claim 1, characterized in that Based on the user's historical electricity consumption pattern and current electricity demand forecast, the optimized charging and discharging plan is personalized to generate a personalized electricity consumption plan. include: Analyze the user's daily electricity usage pattern using the user's historical electricity usage data to obtain the user's electricity usage pattern analysis results; Based on the analysis results of the user's electricity consumption pattern and in combination with the current electricity demand forecast, the electricity demand fluctuation is evaluated to generate an electricity demand forecast; Based on the power demand forecast, adjusting the charging priority and discharging strategy in the optimized charging and discharging plan to form an initial personalized power consumption plan; The preliminary personalized electricity usage plan is optimized by using a machine learning model, the impact of external factors is calculated, and the charging and discharging time points and power in the preliminary personalized electricity usage plan are adjusted to obtain the best personalized electricity usage plan.

6. The method according to claim 1, characterized in that According to the personalized electricity consumption plan, a virtual power plant model is constructed, and the charging and discharging behaviors of the solar energy storage system are coordinated and controlled by the virtual power plant model to generate a cross-regional energy scheduling plan, including: Using the personalized electricity consumption plan, combined with data of other renewable energy power generation facilities and user-side flexible loads in the region, a virtual power plant model including a solar energy storage system is constructed; Based on the virtual power plant model, the relationship and synergy potential between the power generation facilities and loads in the region are analyzed, the roles of different facilities in different time periods are determined, and an initial role allocation is formed; According to the initial role allocation, formulate charging and discharging coordination rules between facilities and generate a preliminary cross-regional energy dispatch plan; The feasibility and adaptability of the preliminary cross-regional energy scheduling plan are evaluated by using a machine learning algorithm, the uncertainties in the actual operation are calculated, the preliminary cross-regional energy scheduling plan is adjusted, and the target cross-regional energy scheduling plan is obtained.

7. The method according to claim 1, characterized in that The difference between the actual effect and the estimated effect during the execution of the cross-regional energy dispatching scheme is calculated using a machine learning algorithm, and based on the difference, energy regulation of the solar energy storage system is performed, including: Using real-time solar panel power input data, dynamic grid electricity price information, and light condition forecasts provided by weather forecast services, a basis for comprehensive energy management decision-making for solar energy storage systems is generated; According to the comprehensive energy management decision basis, an adaptive algorithm is used to adjust the charging balancing strategy between multiple distributed battery units in the solar energy storage system to obtain an optimized charging and discharging plan; Based on the user's historical electricity consumption pattern and current electricity demand forecast, the optimized charging and discharging plan is personalized to generate a personalized electricity consumption plan; According to the personalized electricity consumption plan, a virtual power plant model is constructed, and the charging and discharging behaviors of the solar energy storage system are coordinated and controlled by using the virtual power plant model to generate a cross-regional energy scheduling plan; A machine learning algorithm is used to calculate the difference between the actual effect and the estimated effect during the execution of the cross-regional energy scheduling plan, and energy regulation of the solar energy storage system is performed based on the difference.

8. An energy control system for a solar energy storage system, characterized in that: include: The acquisition module is used to generate the basis for comprehensive energy management decision-making for the solar energy storage system using the real-time acquired solar panel power input data, the dynamic power price information of the power grid, and the light condition prediction provided by the weather forecast service; An adjustment module is used to adjust the charging balancing strategy between multiple distributed battery units in the solar energy storage system according to the comprehensive energy management decision basis using an adaptive algorithm to obtain an optimized charging and discharging plan; A customization module, for customizing the optimized charging and discharging plan based on the user's historical power consumption pattern and current power demand forecast, and generating a personalized power consumption plan; A construction module, used to construct a virtual power plant model according to the personalized power consumption plan, and use the virtual power plant model to coordinate and control the charging and discharging behavior of the solar energy storage system to generate a cross-regional energy scheduling plan; The execution module is used to calculate the difference between the actual effect and the estimated effect during the execution of the cross-regional energy scheduling plan using a machine learning algorithm, and based on the difference, perform energy regulation of the solar energy storage system.

9. A computing device, characterized in that It comprises a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement an energy regulation method for a solar energy storage system as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a computer, an energy regulation method for a solar energy storage system as described in any one of claims 1 to 7 is implemented.

Images