Automatic control method for participation of stored energy in power transaction

Abstract

The invention belongs to the technical field of power systems, and particularly relates to an automatic control method for participation of energy storage in power transaction, which comprises the following specific steps: S1, power market information: acquiring power market transaction rules, electricity price information and supply and demand condition data in real time, and carrying out classified arrangement and analysis; and S2, the state of the energy storage system: key parameters of the energy storage system are continuously monitored to evaluate the health state of the energy storage system, and the key parameters comprise the voltage, the current, the temperature and the residual capacity of the battery. Through setting of power market information, energy storage system state, intelligent decision making, simulation verification, automatic control execution and dynamic strategy adjustment, an efficient closed-loop process can be formed, the response speed of the energy storage system is remarkably improved, the economic benefit can be greatly improved to a certain extent, and the economic benefit is improved. And quick response of the energy storage system to market and power grid requirements is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of power systems, and in particular to an automatic control method for energy storage participating in power trading. Background Art

[0002] As renewable energy generation continues to expand, its intermittent and volatile nature poses challenges to the stable operation of the power system. Energy storage, as a key regulatory resource, participates in power trading and automatic control, which is of great significance for improving power system flexibility and promoting the absorption of renewable energy. However, the automatic control of energy storage in power trading still faces many problems, including the following:

[0003] 1. Slow response: Traditional energy storage systems, due to complex control processes, cannot quickly respond to price fluctuations and grid dispatch instructions when participating in electricity trading. For example, during peak-valley periods, when electricity prices shift from low to high, if the energy storage system cannot promptly switch from charging to discharging mode, it will miss the opportunity to profit from high-price discharge, resulting in reduced economic benefits.

[0004] 2. Excessive transaction costs: Manual participation in power trading decision-making and operations is not only inefficient but also prone to errors, increasing transaction costs. For example, when conducting multiple energy storage power transactions, power traders may accidentally set incorrect trading parameters, resulting in financial losses. Furthermore, manual operations are time-consuming and make it difficult to grasp market dynamics in a timely manner.

[0005] 3. Insufficient utilization of energy storage resources: The lack of precise automatic control strategies prevents energy storage systems from rationally adjusting charging and discharging power and duration based on actual grid demand and market conditions. For example, during certain periods of time when the grid has a high demand for peak load regulation, the energy storage system, due to inappropriate control strategies, fails to fully utilize its peak load regulation capabilities, resulting in idle and wasted energy storage resources and a failure to maximize their value.

[0006] Based on the above, an automatic control method for energy storage participating in electricity trading is invented. Summary of the Invention

[0007] To solve the above technical problems, according to one aspect of the present invention, the present invention provides the following technical solutions:

[0008] The automatic control method for energy storage participating in power trading includes the following specific steps:

[0009] S1, Power Market Information: Real-time acquisition of power market transaction rules, electricity price information, supply and demand data, and classification and analysis;

[0010] S2, energy storage system status: Continuously monitor key parameters of the energy storage system to assess its health status. The key parameters include battery voltage, current, temperature, and remaining capacity.

[0011] S3, intelligent decision-making: Based on electricity market information and energy storage system status, an optimization algorithm is used to make charging and discharging decisions;

[0012] S4, simulation verification: Build a virtual model that closely matches the physical energy storage system to simulate the operation of the energy storage system under different working conditions in a virtual environment to verify the feasibility and effectiveness of the strategy;

[0013] S5, automatic control execution: Automatically controls the charging and discharging process of the energy storage system according to the control instructions generated by the intelligent decision-making. At the same time, it has a manual control function to allow manual intervention in special circumstances;

[0014] S6, dynamic strategy adjustment: Continuously collect real-time dynamic information from the electricity market and energy storage systems to make real-time adjustments to the established charging and discharging strategies generated by intelligent decision-making based on sudden changes in the market and unexpected changes in the energy storage system's own status.

[0015] As a preferred solution of the automatic control method for energy storage participating in power trading described in the present invention, the specific steps of S1 are as follows:

[0016] S11, data collection: used to collect data on power market trading rules, electricity price information, and supply and demand conditions;

[0017] S12, format unification: standardize data from different sources and formats;

[0018] S13, missing value processing: use interpolation and mean filling methods to process missing values ​​in the data;

[0019] S14, outlier elimination: set data threshold range, identify and eliminate abnormal data;

[0020] S15, Classification and Archiving: Classify and store data according to its type and purpose;

[0021] S16, Basic Analysis: Perform statistical analysis on the data, calculate the mean, median, and standard deviation of the data, and draw visual charts to intuitively display the changing trends and distribution characteristics of the data.

[0022] As a preferred solution of the automatic control method for energy storage participating in power trading described in the present invention, the specific steps of S2 are as follows:

[0023] S21, multi-parameter acquisition: collects the battery voltage, current, temperature, and remaining capacity through sensors;

[0024] S22, format conversion: converting the collected sensor data in different formats into a standard format that can be recognized by the system;

[0025] S23, noise filtering: using digital filtering algorithm to remove noise from the original data;

[0026] S24, real-time status analysis: Based on the collected data, key operating indicators of the energy storage system are calculated in real time;

[0027] S25, Health status assessment: Use model-based and data-driven methods to assess the health status of batteries.

[0028] As a preferred solution of the automatic control method for energy storage participating in power trading described in the present invention, the specific steps of S3 are as follows:

[0029] S31, data reception and integration: First, receive power market information and energy storage system status, then integrate the data;

[0030] S32, Data Processing and Analysis: First, use data mining technology to extract features, and then use pre-trained prediction models to make predictions;

[0031] S33, strategy generation: first determine the optimization direction of the decision, and then calculate the optimal charging and discharging strategy.

[0032] As a preferred solution of the automatic control method for energy storage participating in power trading described in the present invention, the specific steps of S31 are as follows:

[0033] S311, multi-source data reception: first receiving power market information on power market trading rules, power price information, and supply and demand data, and then receiving battery voltage, current, temperature, and remaining capacity data of the energy storage system;

[0034] S312, data integration processing: unify and integrate the received data of different types and formats to eliminate conflicts and redundancies between the data.

[0035] As a preferred solution of the automatic control method for energy storage participating in power trading according to the present invention, the specific steps of S32 are as follows:

[0036] S321, Feature Extraction: Using data mining techniques to extract key features related to energy storage system charging and discharging decisions from comprehensive data sets;

[0037] S322, model calculation: Utilize pre-trained market price prediction models and energy storage system performance prediction models to predict electricity market price trends and changes in energy storage system available capacity over a period of time.

[0038] As a preferred solution of the automatic control method for energy storage participating in power trading according to the present invention, the specific steps of S33 are as follows:

[0039] S331, Goal Setting: Determine the optimization direction of decision-making based on user needs and system optimization goals;

[0040] S332, Algorithm Solution: Utilizes optimization algorithms, combined with data processing and analysis results and set objectives, to calculate the optimal charging and discharging strategy while satisfying the physical constraints of the energy storage system and the grid operation requirements.

[0041] As a preferred solution of the automatic control method for energy storage participating in power trading described in the present invention, the specific steps of S4 are as follows:

[0042] S41, physical modeling: Detailed physical modeling of each component of the energy storage system;

[0043] S42, data mapping: Mapping the data collected during the actual energy storage system operation with the corresponding parameters in the virtual model in real time to ensure that the virtual model can accurately reflect the status of the actual system;

[0044] S43, Normal Operating Condition Simulation: Based on historical data and actual operating experience, set up normal operating scenarios for the energy storage system, including different charging and discharging power, duration, and ambient temperature conditions, to simulate the operation of the energy storage system in daily electricity trading and evaluate the feasibility and effectiveness of the charging and discharging strategy generated by intelligent decision-making under normal operating conditions;

[0045] S44, abnormal operating condition simulation: setting corresponding abnormal operating condition scenarios for various possible abnormal conditions, including battery failure, power grid failure, and market price mutation;

[0046] S45, strategy execution: input the charging and discharging strategy generated by the intelligent decision into the virtual model for simulation operation, and record the changes in various parameters of the virtual system during operation;

[0047] S46, real-time monitoring: During the simulation operation, the operating status of the virtual energy storage system is monitored in real time, and the operating results of the virtual model are compared with the expected targets;

[0048] S47, Performance Evaluation: Based on the simulation results, evaluate the performance indicators of the energy storage system and analyze the advantages and disadvantages of the strategy to provide a basis for strategy optimization;

[0049] S48, Risk Assessment: First analyze the risks that may arise during the simulation operation, and use quantitative risk indicators to evaluate the risk level of the strategy and determine whether the strategy needs to be adjusted;

[0050] S49, parameter adjustment: first adjust the parameters of the charge and discharge strategy based on the feedback from the evaluation, and find the optimal combination of strategy parameters through multiple simulation runs and optimization adjustments.

[0051] Compared with existing technologies:

[0052] 1. Addressing the issue of delayed response speed: By integrating electricity market information, energy storage system status, intelligent decision-making, simulation verification, automatic control execution, and dynamic strategy adjustment, an efficient closed-loop process can be formed, significantly improving the response speed of the energy storage system. This can significantly increase economic benefits to a certain extent and enable the energy storage system to quickly respond to market and grid demands.

[0053] 2. Addressing the issue of excessively high transaction costs: By setting up intelligent decision-making, automatic control execution, and dynamic strategy adjustments, not only can the manual participation in power trading decision-making and operations be greatly reduced, but also errors such as parameter setting errors that may occur in manual operations can be avoided, reducing economic losses caused by operational errors; at the same time, the automated process greatly improves transaction efficiency, can track market dynamics in real time, seize transaction opportunities in a timely manner, and reduce the time cost of manual operations.

[0054] 3. Addressing the issue of insufficient utilization of energy storage resources: By setting electricity market information, energy storage system status, intelligent decision-making, simulation verification, automatic control execution and dynamic strategy adjustment, it has a precise automatic control strategy, allowing the energy storage system to reasonably adjust the charging and discharging power and duration according to the actual needs of the grid and market conditions, avoiding idle resources and wasting them, and realizing the maximum value utilization of energy storage resources in grid operation and market transactions. DETAILED DESCRIPTION

[0055] In order to make the objectives, technical solutions and advantages of the present invention more clear, the embodiments of the present invention will be described in further detail below.

[0056] The present invention provides an automatic control method for energy storage participating in power trading, including the following specific steps:

[0057] S1, Power Market Information: Real-time acquisition of power market trading rules, electricity price information, and supply and demand data, as well as categorization and analysis. For example, real-time monitoring and analysis of electricity price data can be used to determine price trends and provide a reference for charging and discharging decisions for energy storage systems.

[0058] The specific steps of S1 are as follows:

[0059] S11, data collection: used to collect data on power market trading rules, electricity price information, and supply and demand conditions;

[0060] S12, Format Unification: Standardize data from different sources and formats. For example, electricity price data in CSV and JSON formats exported from various trading platforms will be converted into a structured data format that the system can recognize, ensuring consistency in data storage and processing.

[0061] S13, Missing Value Processing: Use interpolation and mean filling methods to process missing values ​​in the data. For example, if real-time electricity price data for a certain period is missing, fill it by calculating the average of the electricity prices of the previous and next periods. If there are many missing values, estimate and supplement them by combining historical data for the same period and market trend forecasting models.

[0062] S14, outlier elimination: Set a data threshold range to identify and eliminate abnormal data. For example, if the real-time electricity price data exceeds the normal fluctuation range by more than 10 times, it will be identified as abnormal data and deleted to ensure the accuracy of subsequent analysis results.

[0063] S15, Classification and Archiving: Classify and store data according to its type and purpose; for example, store real-time electricity price data in the "Electricity Price Data" folder, electricity transaction information in the "Transaction Records" folder, and policy and regulatory documents in the "Policy Documents" folder, and create an index directory for quick retrieval;

[0064] S16, Basic Analysis: Perform statistical analysis on the data, calculate the mean, median, and standard deviation of the data, and draw visual charts to intuitively display the changing trends and distribution characteristics of the data. For example, by drawing a line chart of daily real-time electricity prices, analyze the fluctuation pattern of electricity prices within a day; calculate the average transaction volume of electricity in different months to evaluate the seasonal changes in market trading activity;

[0065] S2, Energy Storage System Status: Continuously monitors key parameters of the energy storage system to assess its health. These include battery voltage, current, temperature, and remaining capacity. When excessively high battery temperature or low remaining capacity is detected, a warning message is issued and the relevant data is transmitted to the decision-making control layer for adjustment of the control strategy.

[0066] The specific steps of S2 are as follows:

[0067] S21, multi-parameter acquisition: collects the battery voltage, current, temperature, and remaining capacity through sensors;

[0068] S22, format conversion: converting the collected sensor data in different formats into a standard format that can be recognized by the system; for example, converting the analog signal output by the sensor into a digital signal through an analog-to-digital converter (ADC) and encoding it according to the agreed data protocol to facilitate subsequent processing and storage;

[0069] S23, noise filtering: Use digital filtering algorithms (such as mean filtering and median filtering) to remove noise from the original data. For example, for battery voltage data with large fluctuations, use the median filtering algorithm to smooth the data curve and improve data accuracy.

[0070] S24, real-time status analysis: Based on the collected data, key operating indicators of the energy storage system are calculated in real time. For example, the battery charge and discharge capacity is calculated by integrating the current and time, and the battery charge and discharge efficiency is evaluated based on the relationship between battery voltage and remaining capacity. The voltage and temperature differences of each single cell in the battery pack are compared to determine the consistency of the battery pack.

[0071] S25, Health Status Assessment: Use model-based (e.g., equivalent circuit models) and data-driven (e.g., machine learning algorithms) methods to assess the health status of batteries. For example, by analyzing changes in voltage and internal resistance during battery charge and discharge, combined with a neural network model trained using historical data, the remaining service life of the battery can be predicted, providing a basis for battery maintenance and replacement.

[0072] S3, Intelligent Decision-Making: Based on electricity market information and energy storage system status, optimization algorithms (such as genetic algorithms and particle swarm optimization) are used to make charging and discharging decisions. For example, with the goal of maximizing economic benefits, the optimization algorithm calculates the optimal charging and discharging strategy under different market prices and energy storage conditions, and generates corresponding control instructions.

[0073] The specific steps of S3 are as follows:

[0074] S31, data reception and integration: First, receive power market information and energy storage system status, then integrate the data;

[0075] The specific steps of S31 are as follows:

[0076] S311, multi-source data reception: first receiving power market information on power market trading rules, power price information, and supply and demand data, and then receiving battery voltage, current, temperature, and remaining capacity data of the energy storage system;

[0077] S312, Data Integration Processing: Received data of different types and formats is consolidated to eliminate conflicts and redundancies. For example, real-time electricity price data is associated with the energy storage system's dischargeable time period, and battery health status data is combined with charge and discharge power constraints to form a comprehensive data set for decision-making analysis.

[0078] S32, Data Processing and Analysis: First, use data mining technology to extract features, and then use pre-trained prediction models to make predictions;

[0079] The specific steps of S32 are as follows:

[0080] S321, Feature Extraction: Using data mining techniques, key features relevant to energy storage system charging and discharging decisions are extracted from comprehensive data sets. For example, features such as electricity price fluctuation trends and peak-offset price differences are extracted from real-time electricity price data. Features such as battery charging and discharging efficiency and charging and discharging speed are extracted from energy storage system operating data to provide a core basis for subsequent decision-making.

[0081] S322, Model Calculation: Utilize pre-trained market price prediction models and energy storage system performance prediction models to predict future electricity market price trends and changes in energy storage system available capacity. For example, use an LSTM (Long Short-Term Memory) model to predict the real-time electricity price curve for the next 24 hours, and use a battery capacity decay model to estimate changes in remaining battery capacity under different charge and discharge strategies.

[0082] S33, strategy generation: first determine the optimization direction of the decision, and then calculate the optimal charging and discharging strategy;

[0083] The specific steps of S33 are as follows:

[0084] S331, Goal Setting: Determine the optimization direction of decision-making based on user needs and system optimization goals. For example, if the goal is to maximize economic benefits, consider charging during low electricity prices and discharging during peak electricity prices to generate price differential profits. If the goal is to ensure grid stability, prioritize meeting grid peak load regulation and frequency regulation needs.

[0085] S332, Algorithm Solution: Utilize an optimization algorithm (e.g., genetic algorithm, particle swarm optimization, dynamic programming algorithm, etc.) combined with data processing and analysis results and set objectives to calculate the optimal charge and discharge strategy while satisfying the physical constraints of the energy storage system (e.g., upper limits on charge and discharge power, battery capacity limitations, etc.) and grid operation requirements. For example, a genetic algorithm can be used to search for a charge and discharge power and duration combination that maximizes economic benefits among numerous possible charge and discharge combinations.

[0086] S4, Simulation Verification: Build a virtual model that closely mirrors the physical energy storage system to simulate the system's operation under different operating conditions in a virtual environment to verify the feasibility and effectiveness of the strategy. For example, simulate the charging and discharging performance of the energy storage system under extreme weather conditions to evaluate its support for the power grid; simulate different power market price fluctuation scenarios to test the strategy's profitability.

[0087] The specific steps of S4 are as follows:

[0088] S41, Physical Modeling: Conduct detailed physical modeling of each component of the energy storage system, such as the battery pack, energy storage converter, and transformer. For example, establish an equivalent circuit model of the battery to describe the battery's charge and discharge process, internal resistance changes, etc.; establish a mathematical model of the energy storage converter to simulate its power conversion and control characteristics.

[0089] S42, data mapping: Mapping the data collected during the actual energy storage system operation (such as voltage, current, temperature, capacity, etc.) with the corresponding parameters in the virtual model in real time to ensure that the virtual model can accurately reflect the status of the actual system;

[0090] S43, Normal Operating Condition Simulation: Based on historical data and actual operating experience, set up normal operating scenarios for the energy storage system, including different charging and discharging power, duration, and ambient temperature conditions, to simulate the operation of the energy storage system in daily electricity trading and evaluate the feasibility and effectiveness of the charging and discharging strategy generated by intelligent decision-making under normal operating conditions;

[0091] S44, abnormal operating condition simulation: setting corresponding abnormal operating condition scenarios for various possible abnormal conditions, including battery failure, power grid failure, and market price mutation;

[0092] S45, Strategy Execution: Input the charge and discharge strategy generated by the intelligent decision into the virtual model for simulation operation, and record the changes in various parameters of the virtual system during operation, such as battery capacity changes, power output, temperature changes, etc.

[0093] S46, real-time monitoring: During the simulation operation, the operating status of the virtual energy storage system is monitored in real time, and the operating results of the virtual model are compared with the expected targets;

[0094] S47, Performance Evaluation: Based on the simulation results, evaluate the performance indicators of the energy storage system (such as charging and discharging efficiency, economic benefits, and support capacity for the power grid), analyze the advantages and disadvantages of the strategy, and provide a basis for strategy optimization;

[0095] S48, Risk Assessment: First, analyze the risks that may arise during the simulation (such as shortened battery life, equipment damage, economic losses, etc.), and use quantitative risk indicators to evaluate the risk level of the strategy and determine whether the strategy needs to be adjusted;

[0096] S49, parameter adjustment: First, adjust the parameters of the charge and discharge strategy (such as charge and discharge power, duration, time window, etc.) based on the evaluation feedback, and find the optimal strategy parameter combination through multiple simulation runs and optimization adjustments;

[0097] By setting up simulation verification, it is possible to effectively reduce the operational risks and decision-making errors of the energy storage system. In actual applications, it can avoid excessive loss of energy storage equipment or poor economic benefits due to unverified strategies.

[0098] S5, automatic control execution: Automatically controls the charging and discharging process of the energy storage system according to the control instructions generated by the intelligent decision-making. At the same time, it has a manual control function to allow manual intervention in special circumstances (such as system failures, emergency dispatch, etc.);

[0099] S6, Dynamic Strategy Adjustment: Continuously collect real-time dynamic information from the electricity market and energy storage systems to make real-time adjustments to the established charging and discharging strategies generated by intelligent decision-making based on sudden market changes (such as policy adjustments, supply and demand imbalances caused by major accidents, etc.) and unexpected changes in the energy storage system's own state (such as equipment failures, sudden changes in battery performance, etc.). This allows the energy storage system to always maintain the optimal operating state in complex and changing actual environments, further improving economic benefits and resource utilization efficiency.

[0100] Although the present invention has been described above with reference to embodiments, various modifications may be made thereto and equivalent components may be substituted without departing from the scope of the present invention. In particular, as long as there are no structural conflicts, the various features of the embodiments disclosed herein may be combined with each other in any manner, and the omission of an exhaustive description of such combinations in this specification is solely for the sake of space and resource conservation. Therefore, the present invention is not limited to the specific embodiments disclosed herein, but includes all technical solutions falling within the scope of the claims.

Claims

1. An automatic control method for energy storage participating in power trading, characterized in that: The specific steps are as follows: S1, Power Market Information: Real-time acquisition of power market transaction rules, electricity price information, supply and demand data, and classification and analysis; S2, energy storage system status: Continuously monitor key parameters of the energy storage system to assess its health status. The key parameters include battery voltage, current, temperature, and remaining capacity. S3, intelligent decision-making: Based on electricity market information and energy storage system status, an optimization algorithm is used to make charging and discharging decisions; S4, simulation verification: Build a virtual model that closely matches the physical energy storage system to simulate the operation of the energy storage system under different working conditions in a virtual environment to verify the feasibility and effectiveness of the strategy; S5, automatic control execution: Automatically controls the charging and discharging process of the energy storage system according to the control instructions generated by the intelligent decision-making. At the same time, it has a manual control function to allow manual intervention in special circumstances; S6, Dynamic Strategy Adjustment: Continuously collects real-time dynamic information from the power market and energy storage systems to adjust the established charging and discharging strategies generated by intelligent decision-making in real time based on sudden market changes and unexpected changes in the energy storage system's own status; The specific steps of S4 are as follows: S41, physical modeling: Detailed physical modeling of each component of the energy storage system; S42, data mapping: Mapping the data collected during the actual energy storage system operation with the corresponding parameters in the virtual model in real time to ensure that the virtual model can accurately reflect the status of the actual system; S43, Normal Operating Condition Simulation: Based on historical data and actual operating experience, set up normal operating scenarios for the energy storage system, including different charging and discharging power, duration, and ambient temperature conditions, to simulate the operation of the energy storage system in daily electricity trading and evaluate the feasibility and effectiveness of the charging and discharging strategy generated by intelligent decision-making under normal operating conditions; S44, abnormal operating condition simulation: setting corresponding abnormal operating condition scenarios for various possible abnormal conditions, including battery failure, power grid failure, and market price mutation; S45, strategy execution: input the charging and discharging strategy generated by the intelligent decision into the virtual model for simulation operation, and record the changes in various parameters of the virtual system during operation; S46, real-time monitoring: During the simulation operation, the operating status of the virtual energy storage system is monitored in real time, and the operating results of the virtual model are compared with the expected targets; S47, Performance Evaluation: Based on the simulation results, evaluate the performance indicators of the energy storage system and analyze the advantages and disadvantages of the strategy to provide a basis for strategy optimization; S48, Risk Assessment: First analyze the risks that may arise during the simulation operation, and use quantitative risk indicators to evaluate the risk level of the strategy and determine whether the strategy needs to be adjusted; S49, parameter adjustment: first adjust the parameters of the charge and discharge strategy based on the feedback from the evaluation, and find the optimal combination of strategy parameters through multiple simulation runs and optimization adjustments.

2. The automatic control method for energy storage participating in power trading according to claim 1 is characterized in that: The specific steps of S1 are as follows: S11, data collection: used to collect data on power market trading rules, electricity price information, and supply and demand conditions; S12, format unification: standardize data from different sources and formats; S13, missing value processing: use interpolation and mean filling methods to process missing values ​​in the data; S14, outlier elimination: set data threshold range, identify and eliminate abnormal data; S15, Classification and Archiving: Classify and store data according to its type and purpose; S16, Basic Analysis: Perform statistical analysis on the data, calculate the mean, median, and standard deviation of the data, and draw visual charts to intuitively display the changing trends and distribution characteristics of the data.

3. The automatic control method for energy storage participating in power trading according to claim 1, characterized in that: The specific steps of S2 are as follows: S21, multi-parameter acquisition: collects the battery voltage, current, temperature, and remaining capacity through sensors; S22, format conversion: converting the collected sensor data in different formats into a standard format that can be recognized by the system; S23, noise filtering: using digital filtering algorithm to remove noise from the original data; S24, real-time status analysis: Based on the collected data, key operating indicators of the energy storage system are calculated in real time; S25, Health status assessment: Use model-based and data-driven methods to assess the health status of batteries.

4. The automatic control method for energy storage participating in power trading according to claim 1, characterized in that: The specific steps of S3 are as follows: S31, data reception and integration: First, receive power market information and energy storage system status, then integrate the data; S32, Data Processing and Analysis: First, use data mining technology to extract features, and then use pre-trained prediction models to make predictions; S33, strategy generation: first determine the optimization direction of the decision, and then calculate the optimal charging and discharging strategy.

5. The automatic control method for energy storage participating in power trading according to claim 4 is characterized in that: The specific steps of S31 are as follows: S311, multi-source data reception: first receiving power market information on power market trading rules, power price information, and supply and demand data, and then receiving battery voltage, current, temperature, and remaining capacity data of the energy storage system; S312, data integration processing: unify and integrate the received data of different types and formats to eliminate conflicts and redundancies between the data.

6. The automatic control method for energy storage participating in power trading according to claim 4 is characterized in that: The specific steps of S32 are as follows: S321, Feature Extraction: Using data mining techniques to extract key features related to energy storage system charging and discharging decisions from comprehensive data sets; S322, model calculation: Utilize pre-trained market price prediction models and energy storage system performance prediction models to predict electricity market price trends and changes in energy storage system available capacity over a period of time.

7. The automatic control method for energy storage participating in power trading according to claim 4, characterized in that: The specific steps of S33 are as follows: S331, Goal Setting: Determine the optimization direction of decision-making based on user needs and system optimization goals; S332, Algorithm Solution: Utilizes optimization algorithms, combined with data processing and analysis results and set objectives, to calculate the optimal charging and discharging strategy while satisfying the physical constraints of the energy storage system and the grid operation requirements.