An energy storage method and system for an electric vehicle charging station

Abstract

The present invention relates to the technical field of electric vehicle infrastructure, and specifically to an energy storage method and system for an electric vehicle charging station, which includes the following steps: Based on Internet of Things technology, data collection and network analysis algorithms are used to collect historical charging data of the charging station, surrounding traffic flow, weather forecasts, and user behavior patterns, generating a comprehensive data set. In the present invention, by applying the long short-term memory network algorithm, it is possible to predict the charging demand in each time period and region, achieve optimization of energy distribution. The linear programming algorithm ensures the maximization of energy utilization and efficiency improvement in formulating the charge and discharge strategies of energy storage devices. Through the energy scheduling optimization algorithm, the utilization of renewable energy such as solar energy and wind energy is made more efficient, promoting the sustainable use of energy. Combining the adaptive adjustment algorithm and pattern recognition technology, it maintains stable operation under dynamically changing conditions, realizes timely diagnosis and effective maintenance of faults, and improves the reliability and maintenance efficiency of the entire system.

Description

Technical Field

[0001] The present invention relates to the technical field of electric vehicle infrastructure, and particularly to an energy storage method and system for an electric vehicle charging station. Background Art

[0002] The technical field of electric vehicle infrastructure involves various technologies and facilities that provide necessary support for electric vehicles, including but not limited to charging stations, energy storage systems, and interactions with the power grid. The main goal of the field is to ensure that electric vehicle users can conveniently and efficiently charge their vehicles. With the rapid growth of the electric vehicle market, the demand for charging infrastructure is also increasing day by day. This includes building more public and private charging stations, increasing charging speed, and integrating intelligent charging technologies such as demand response and load balancing. In addition, with the integration of renewable energy, electric vehicle infrastructure is gradually developing towards a more environmentally friendly and sustainable direction.

[0003] The energy storage method for an electric vehicle charging station refers to the energy storage technology deployed at an electric vehicle charging station, whose main purpose is to improve charging efficiency and reduce the burden on the power grid by the charging station. This method can store energy when the power grid load is low and quickly release it during peak hours, thus alleviating the burden on the power grid during peak hours. It helps the charging station maintain stable operation when the output of renewable energy is unstable, such as on windless or cloudy days. In this way, the reliability and efficiency of electric vehicle charging can be improved, while promoting the use of renewable energy. This energy storage method is usually achieved by installing a battery energy storage system (BESS). These systems can store a large amount of electric energy when the demand is low and quickly release energy when the demand increases. In addition to batteries, more advanced management systems such as intelligent charging management and demand response technologies are also involved to optimize the interaction between the charging station and the power grid. Moreover, some advanced energy storage methods also integrate machine learning and artificial intelligence technologies to predict charging demand and optimize energy distribution. These technologies work together to ensure that the electric vehicle charging station can operate efficiently and stably in different operating environments.

[0004] There are some deficiencies in the traditional energy storage method for electric vehicle charging stations. The lack of efficient algorithm support, such as long short-term memory networks, makes the prediction of charging demand inaccurate and difficult to cope with demand fluctuations. In addition, traditional methods often lack flexibility and optimization in formulating energy management strategies and cannot make full use of renewable energy, resulting in low energy utilization efficiency. Finally, traditional systems usually have limited capabilities in real-time monitoring and fault diagnosis, making it difficult to achieve rapid response and effective maintenance, which affects the stability and reliability of the system. Summary of the Invention

[0005] The purpose of the present invention is to solve the deficiencies existing in the prior art, and to propose an energy storage method and system for an electric vehicle charging station.

[0006] To achieve the above object, the present invention adopts the following technical solutions: An energy storage method for an electric vehicle charging station, comprising the following steps:

[0007] S1: Based on Internet of Things technology, using data collection and network analysis algorithms to collect historical charging data of the charging station, surrounding traffic flow, weather forecast and user behavior patterns, and generating a comprehensive data set;

[0008] S2: Based on the comprehensive data set, using long short-term memory network algorithm to perform time series prediction of charging demand, and generating a charging demand prediction model;

[0009] S3: Based on the charging demand prediction model, using linear programming algorithm to formulate the charging and discharging strategy of the energy storage device, and generating an energy management strategy;

[0010] S4: Based on the energy management strategy, using energy scheduling optimization algorithm to integrate solar and wind energy output data, and generating an optimized energy integration plan;

[0011] S5: Based on Internet of Things and remote monitoring technology, using adaptive adjustment algorithm to dynamically adjust the energy management strategy according to the actual situation, and generating a real-time adjustment strategy;

[0012] S6: Based on the real-time adjustment strategy, using pattern recognition technology to perform intelligent fault diagnosis and system maintenance, and generating a fault diagnosis and maintenance plan.

[0013] As a further solution of the present invention, the comprehensive data set includes charging mode, traffic condition, climate change and user preference information. The charging demand prediction model is specifically the prediction analysis of charging demand in different time and regions. The energy management strategy includes the planning of energy distribution, storage timing and release timing. The optimized energy integration plan includes the strategy of using and storing electricity from renewable energy. The fault diagnosis and maintenance plan specifically refers to the immediate discovery, diagnosis and maintenance measures for system faults.

[0014] As a further solution of the present invention, based on Internet of Things technology, the steps of using data collection and network analysis algorithms to collect historical charging data of the charging station, surrounding traffic flow, weather forecast and user behavior patterns, and generating a comprehensive data set are specifically as follows:

[0015] S101: Based on Internet of Things technology, using data fusion and distributed database management system to collect historical charging data of the charging station, and generating a historical charging data set;

[0016] S102: Based on the historical charging data set, applying association rule learning and sequence pattern mining technology to analyze user charging behavior, and generating a user charging behavior analysis report;

[0017] S103: Based on the geographic information system, use spatial data analysis and traffic pattern recognition technologies to collect traffic flow and weather forecast data, and generate a traffic and weather dataset;

[0018] S104: Integrate the historical charging dataset, user charging behavior analysis report, and traffic and weather dataset, and use big data integration and analysis technologies to generate a comprehensive dataset;

[0019] The data fusion technology includes the integration and synchronization of heterogeneous data sources. The association rule learning is used to discover frequent patterns between data items. The spatial data analysis technology is used to identify patterns and trends in geospatial data. The big data integration technology includes data cleaning, transformation, and summarization.

[0020] As a further solution of the present invention, based on the comprehensive dataset, the steps of using the long short-term memory network algorithm to perform time series prediction of charging demand and generate a charging demand prediction model are specifically as follows:

[0021] S201: Based on the comprehensive dataset, use exploratory data analysis and factor analysis methods to determine the key factors affecting charging demand, and generate a list of factors affecting charging demand;

[0022] S202: Based on the list of factors affecting charging demand, apply the long short-term memory network algorithm to perform time series analysis, and generate a preliminary charging demand prediction report;

[0023] S203: Optimize the preliminary charging demand prediction report, and use the autoregressive moving average model and seasonal decomposition technology to improve the prediction accuracy, and generate an optimized charging demand prediction report;

[0024] S204: Based on the optimized charging demand prediction report, adjust and improve the long short-term memory network model, and generate a charging demand prediction model.

[0025] As a further solution of the present invention, based on the charging demand prediction model, the steps of using the linear programming algorithm to formulate the charge and discharge strategy of the energy storage device and generate an energy management strategy are specifically as follows:

[0026] S301: Based on the charging demand prediction model, use system dynamics modeling and prediction methods to evaluate the future charging demand trend, and generate a charging demand trend report;

[0027] S302: Based on the charging demand trend report, apply decision tree analysis and linear programming methods to design a preliminary charge and discharge strategy, and generate a preliminary charge and discharge strategy plan;

[0028] S303: Conduct an effectiveness analysis on the preliminary charge and discharge strategy plan, verify the actual application effect of the strategy using Monte Carlo simulation technology, and generate a charge and discharge strategy evaluation report;

[0029] S304: Based on the charge and discharge strategy evaluation report and real-time power grid data, finally determine the charge and discharge strategy of the energy storage device using improved linear programming and optimization methods, and generate an energy management strategy.

[0030] As a further solution of the present invention, based on the energy management strategy, the steps of integrating solar and wind energy output data using an energy scheduling optimization algorithm to generate an optimized energy integration plan are specifically as follows:

[0031] S401: Based on the energy management strategy, integrate solar energy output data using data assimilation technology to generate a solar energy data integration report;

[0032] S402: Based on the energy management strategy, integrate wind energy output data using data assimilation technology to generate a wind energy data integration report;

[0033] S403: Comprehensively analyze the solar energy data integration report and the wind energy data integration report, and apply the particle swarm optimization algorithm to generate a preliminary energy integration plan;

[0034] S404: Evaluate the preliminary energy integration plan, and use genetic algorithm optimization technology to generate an optimized energy integration plan;

[0035] The data assimilation technology includes sensor data and a prediction model. The particle swarm optimization algorithm is specifically an optimization tool based on swarm intelligence for searching the optimal energy combination. The genetic algorithm optimization technology imitates the natural selection mechanism to search for the best energy configuration plan.

[0036] As a further solution of the present invention, based on the Internet of Things and remote monitoring technology, the steps of using an adaptive adjustment algorithm to dynamically adjust the energy management strategy according to the actual situation to generate a real-time adjustment strategy are specifically as follows:

[0037] S501: Based on Internet of Things technology, collect the current state data of the power grid and charging stations using real-time data stream processing technology to generate a real-time state data report;

[0038] S502: Based on the real-time state data report, analyze the dynamic changes of the power grid and charging stations using machine learning algorithms to generate a system dynamic analysis report;

[0039] S503: Combine the system dynamic analysis report and the energy management strategy, and apply an adaptive control algorithm for strategy adjustment to generate a preliminary real-time adjustment strategy;

[0040] S504: Optimize the preliminary real-time adjustment strategy, and use model predictive control technology to generate a real-time adjustment strategy.

[0041] As a further solution of the present invention, based on the real-time adjustment strategy, using pattern recognition technology for intelligent fault diagnosis and system maintenance, the steps of generating a fault diagnosis and maintenance plan are specifically as follows:

[0042] S601: Based on the real-time adjustment strategy, use real-time monitoring and fault detection technology to generate a preliminary fault detection report;

[0043] S602: Based on the preliminary fault detection report, apply pattern recognition and deep learning technologies to analyze the cause of the fault and generate a fault cause analysis report;

[0044] S603: Compare the fault cause analysis report with historical maintenance data, and use case-based reasoning technology to determine the maintenance plan and generate a preliminary maintenance plan;

[0045] S604: Optimize and adjust the preliminary maintenance plan, and apply predictive maintenance and optimization decision support system technology to generate a fault diagnosis and maintenance plan.

[0046] An energy storage system for an electric vehicle charging station, the energy storage system for an electric vehicle charging station is used to execute the above-mentioned energy storage method for an electric vehicle charging station, and the system includes a data collection module, a demand prediction module, an energy management module, an energy integration module, a real-time adjustment module, a fault diagnosis module, and a system maintenance module.

[0047] As a further solution of the present invention, the data collection module, based on Internet of Things technology, uses data fusion and distributed database management technology to collect historical charging data, traffic flow, weather forecast, and user behavior patterns, and generates a comprehensive data set;

[0048] The demand prediction module, based on the comprehensive data set, uses exploratory data analysis and factor analysis techniques to determine influencing factors, and applies long short-term memory network algorithms for time series analysis to generate a charging demand prediction model;

[0049] The energy management module, based on the charging demand prediction model, uses system dynamic modeling and prediction technology to evaluate demand trends, and combines decision tree analysis and linear programming methods to generate an energy management strategy;

[0050] The energy integration module, based on the energy management strategy, uses data assimilation technology to integrate solar and wind energy output data, and applies particle swarm optimization algorithm and genetic algorithm technology to generate an optimized energy integration plan;

[0051] The real-time adjustment module is based on Internet of Things technology and applies real-time data stream processing technology to collect current status data. Combining machine learning algorithms and adaptive control algorithms, it generates real-time adjustment strategies;

[0052] The fault diagnosis module is based on the real-time adjustment strategy, uses real-time monitoring and fault detection technology, and combines pattern recognition and deep learning technology to generate a fault cause analysis report;

[0053] The system maintenance module is based on the fault cause analysis report, adopts case-based reasoning technology and predictive maintenance technology, and combines an optimized decision support system to generate fault diagnosis and maintenance plans.

[0054] Compared with the prior art, the advantages and positive effects of the present invention are as follows:

[0055] In the present invention, the long short-term memory network algorithm makes the time series prediction of charging demand more accurate, can effectively predict the charging demand at different times and regions, and thus optimizes energy distribution. The application of the linear programming algorithm in formulating the charge and discharge strategies of energy storage devices ensures the maximization of energy utilization and efficiency improvement. The integration of the energy scheduling optimization algorithm enables more effective utilization of renewable energy such as solar energy and wind energy, and promotes the sustainable use of energy. The combination of the adaptive adjustment algorithm and pattern recognition technology enables the system to still operate stably under dynamically changing actual conditions, and can diagnose and maintain in a timely manner, improving the reliability and maintenance efficiency of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 is a schematic diagram of the working process of the present invention;

[0057] Figure 2 is a detailed flowchart of S1 of the present invention;

[0058] Figure 3 is a detailed flowchart of S2 of the present invention;

[0059] Figure 4 is a detailed flowchart of S3 of the present invention;

[0060] Figure 5 is a detailed flowchart of S4 of the present invention;

[0061] Figure 6 is a detailed flowchart of S5 of the present invention;

[0062] Figure 7 is a detailed flowchart of S6 of the present invention;

[0063] Figure 8 is the system flowchart of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0064] In order to make the objectives, technical solutions and advantages of the present invention more clear and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0065] In the description of the present invention, it should be understood that the orientation or positional relationship indicated by the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. is based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention. In addition, in the description of the present invention, the meaning of "a plurality" is two or more, unless otherwise specifically defined.

[0066] Embodiment 1

[0067] Please refer to Figure 1 , the present invention provides a technical solution: an energy storage method for an electric vehicle charging station, including the following steps:

[0068] S1: Based on the Internet of Things technology, collect the historical charging data of the charging station, the surrounding traffic flow, the weather forecast and the user behavior pattern by using data collection and network analysis algorithms, and generate a comprehensive data set;

[0069] S2: Based on the comprehensive data set, use the long short-term memory network algorithm to perform time series prediction of the charging demand, and generate a charging demand prediction model;

[0070] S3: Based on the charging demand prediction model, use the linear programming algorithm to formulate the charging and discharging strategy of the energy storage device, and generate an energy management strategy;

[0071] S4: Based on the energy management strategy, use the energy scheduling optimization algorithm to integrate the solar and wind energy output data, and generate an optimized energy integration plan;

[0072] S5: Based on the Internet of Things and remote monitoring technology, use the adaptive adjustment algorithm to dynamically adjust the energy management strategy according to the actual situation, and generate a real-time adjustment strategy;

[0073] S6: Based on the real-time adjustment strategy, use the pattern recognition technology to perform intelligent fault diagnosis and system maintenance, and generate a fault diagnosis and maintenance plan.

[0074] The comprehensive dataset includes charging patterns, traffic conditions, climate change, and user preference information. The charging demand prediction model specifically refers to the predictive analysis of charging demand in different time periods and regions. The energy management strategy includes the planning of energy allocation, storage timing, and release timing. The optimized energy integration plan includes strategies for utilizing and storing electricity from renewable energy sources. The fault diagnosis and maintenance plan specifically refers to the immediate detection, diagnosis, and maintenance measures for system failures.

[0075] Data collection and network analysis through Internet of Things (IoT) technology enable more comprehensive and accurate collection of historical charging data, surrounding traffic flow, weather conditions, and user behavior patterns of charging stations. This comprehensive data collection provides a solid foundation for accurate prediction of charging demand, helps better understand and predict the operating conditions and potential demand of charging stations, thereby improving the response efficiency and service quality of the entire system.

[0076] The application of the Long Short-Term Memory (LSTM) network algorithm makes time series prediction more accurate. This algorithm can effectively process and analyze time series data, accurately predict the charging demand in different time periods and regions, and help charging station managers better plan resource allocation and operation strategies, thus optimizing the operating efficiency of charging stations.

[0077] The use of the linear programming algorithm in formulating the charging and discharging strategies of energy storage devices makes energy management more efficient. The formulation of this strategy takes into account the optimal allocation of energy, storage timing, and release timing, helps reduce energy waste, improve energy utilization efficiency, and ensure the stable operation of charging stations during peak hours.

[0078] The energy scheduling optimization algorithm integrates solar and wind energy output data to form an optimized energy integration plan. This not only improves the utilization rate of renewable energy, reduces dependence on traditional energy sources, but also helps reduce environmental pollution and promotes the green development of charging stations.

[0079] The combination of IoT and remote monitoring technology and the application of adaptive adjustment algorithms enable the energy management strategy to be dynamically adjusted according to actual situations. This real-time adjustment strategy enhances the flexibility and adaptability of the system and ensures stable operation in various emergency situations. The application of pattern recognition technology in intelligent fault diagnosis and system maintenance greatly improves the accuracy of fault detection and the efficiency of maintenance work.

[0080] Please refer to Figure 2 , based on IoT technology, the steps for generating a comprehensive dataset by using data collection and network analysis algorithms to collect historical charging data, surrounding traffic flow, weather forecasts, and user behavior patterns of charging stations are as follows:

[0081] S101: Based on Internet of Things technology, use data fusion and distributed database management system to collect historical charging data of charging stations and generate a historical charging data set;

[0082] S102: Based on the historical charging data set, apply association rule learning and sequential pattern mining techniques to analyze user charging behavior and generate a user charging behavior analysis report;

[0083] S103: Based on geographic information system, use spatial data analysis and traffic pattern recognition techniques to collect traffic flow and weather forecast data and generate a traffic and weather data set;

[0084] S104: Integrate the historical charging data set, user charging behavior analysis report, and traffic and weather data set, and use big data integration and analysis techniques to generate a comprehensive data set;

[0085] Data fusion technology includes the integration and synchronization of heterogeneous data sources. Association rule learning is used to discover frequent patterns between data items. Spatial data analysis technology is used to identify patterns and trends in geospatial data. Big data integration technology includes data cleaning, transformation, and summarization.

[0086] In S101, the system uses Internet of Things technology to collect historical charging data by deploying various types of sensors at charging stations, such as electricity meters, environmental monitors, etc. These data are then integrated through a distributed database management system to form a historical charging data set. The data fusion technology in this process, especially the integration and synchronization of heterogeneous data sources, ensures the high integrity and consistency of the collected data.

[0087] In S102, the system further analyzes the historical charging data set. Here, association rule learning and sequential pattern mining techniques are applied to identify user charging behavior patterns, such as charging time preferences, charging frequencies, etc. The purpose of this step is to generate a user charging behavior analysis report to provide more accurate user behavior insights for subsequent demand prediction and strategy formulation.

[0088] In S103, the system collects data related to traffic flow and weather forecast around the charging station through geographic information system (GIS) technology. Using spatial data analysis and traffic pattern recognition techniques, the system can understand and predict the impact of traffic flow changes on charging demand, and at the same time evaluate charging behavior patterns under different weather conditions. Such a data set provides important information about external environmental factors.

[0089] In S104, the system synthesizes the historical charging dataset, the user charging behavior analysis report, and the traffic and weather datasets, and uses big data integration and analysis technologies to generate a comprehensive dataset. The big data technologies in this step, especially data cleaning, transformation, and summarization, ensure the quality and applicability of the data, making the finally generated comprehensive dataset a key asset for formulating effective energy storage strategies and optimizing the operation of charging stations.

[0090] Please refer to Figure 3 , based on the comprehensive dataset, the steps of using the long short-term memory network algorithm for time series prediction of charging demand to generate a charging demand prediction model are as follows:

[0091] S201: Based on the comprehensive dataset, use exploratory data analysis and factor analysis methods to determine the key factors affecting charging demand and generate a list of factors affecting charging demand;

[0092] S202: Based on the list of factors affecting charging demand, apply the long short-term memory network algorithm for time series analysis and generate a preliminary charging demand prediction report;

[0093] S203: Optimize the preliminary charging demand prediction report, use the autoregressive integrated moving average model and seasonal decomposition technology to improve the prediction accuracy, and generate an optimized charging demand prediction report;

[0094] S204: Based on the optimized charging demand prediction report, adjust and improve the long short-term memory network model to generate a charging demand prediction model.

[0095] In S201, exploratory data analysis and factor analysis are performed based on the comprehensive dataset to determine the key factors affecting charging demand. This step includes analyzing various variables affecting charging demand, such as time, weather, seasonal changes, economic indicators, etc., as well as the correlation and influence between these factors. Through this analysis, a list of factors affecting charging demand is generated.

[0096] In S202, based on the determined list of influencing factors, the long short-term memory (LSTM) network algorithm is applied for time series analysis. LSTM is particularly suitable for processing and predicting long-term dependencies in time series data. Through the analysis of the LSTM model, a preliminary charging demand prediction report is generated, showing the prediction results of charging demand under different conditions.

[0097] In S203, to improve the prediction accuracy, the preliminary charging demand prediction report is optimized. The autoregressive integrated moving average (ARIMA) model and seasonal decomposition technology are used to further refine the prediction. The ARIMA model helps to capture the trends and seasonal changes in time series data, while seasonal decomposition can clarify the demand fluctuations in different time periods. This step generates an optimized charging demand prediction report.

[0098] In S204, based on the optimized charging demand prediction report, the LSTM model is adjusted and improved. This includes adjusting network parameters, increasing the number of training cycles, or modifying the data preprocessing method. The optimized LSTM model more accurately reflects the dynamic changes in charging demand, generating the final charging demand prediction model.

[0099] Please refer to Figure 4 , based on the charging demand prediction model, the linear programming algorithm is used to formulate the charge and discharge strategy of the energy storage device. The specific steps for generating the energy management strategy are as follows:

[0100] S301: Based on the charging demand prediction model, use system dynamic modeling and prediction methods to evaluate the future charging demand trend, generating a charging demand trend report;

[0101] S302: Based on the charging demand trend report, apply decision tree analysis and linear programming methods to design a preliminary charge and discharge strategy, generating a preliminary charge and discharge strategy plan;

[0102] S303: Conduct an effectiveness analysis of the preliminary charge and discharge strategy plan, use Monte Carlo simulation technology to verify the actual application effect of the strategy, generating a charge and discharge strategy evaluation report;

[0103] S304: Based on the charge and discharge strategy evaluation report and real-time grid data, use improved linear programming and optimization methods to finally determine the charge and discharge strategy of the energy storage device, generating an energy management strategy.

[0104] In S301, using system dynamic modeling and prediction methods, based on the charging demand prediction model, evaluate the future charging demand trend. This step includes analyzing the time series data provided by the prediction model, identifying the periodicity, trend, and potential fluctuations of the charging demand. Through this analysis, a charging demand trend report is generated, providing a basis for formulating the charge and discharge strategy.

[0105] In S302, based on the charging demand trend report, apply decision tree analysis and linear programming methods to design a preliminary charge and discharge strategy. In this step, consider factors such as charging demand, grid conditions, energy storage device capacity and efficiency, and formulate a preliminary charge and discharge schedule and operation guidelines. The preliminary charge and discharge strategy plan generated in this stage is the first draft of the strategy formulation.

[0106] In S303, conduct an effectiveness analysis of the preliminary charge and discharge strategy plan. Use Monte Carlo simulation technology to simulate the strategy multiple times, verifying its actual application effect and stability in different scenarios. The charge and discharge strategy evaluation report generated in this step provides the performance indicators and potential risks of the strategy.

[0107] In S304, based on the charge-discharge strategy evaluation report and real-time grid data, an improved linear programming and optimization method is used to finally determine the charge-discharge strategy of the energy storage device. At this stage, the strategy will be refined and adjusted according to the actual situation and grid demand to ensure the maximization of the efficiency and economic benefits of the energy storage device. After completing these steps, the final energy management strategy is generated.

[0108] Please refer to Figure 5 , based on the energy management strategy, the steps to generate an optimized energy integration plan by integrating solar and wind energy output data using an energy scheduling optimization algorithm are as follows:

[0109] S401: Based on the energy management strategy, use data assimilation technology to integrate solar energy output data and generate a solar energy data integration report;

[0110] S402: Based on the energy management strategy, apply data assimilation technology to integrate wind energy output data and generate a wind energy data integration report;

[0111] S403: Comprehensively analyze the solar energy data integration report and the wind energy data integration report, and apply the particle swarm optimization algorithm to generate a preliminary energy integration plan;

[0112] S404: Evaluate the preliminary energy integration plan and use genetic algorithm optimization technology to generate an optimized energy integration plan;

[0113] Data assimilation technology includes sensor data and prediction models. The particle swarm optimization algorithm is specifically an optimization tool based on swarm intelligence for searching the optimal energy combination. The genetic algorithm optimization technology imitates the natural selection mechanism to search for the best energy configuration plan.

[0114] In S401, based on the energy management strategy, data assimilation technology is used to integrate solar energy output data. Data assimilation here refers to the combination of real-time solar sensor data and prediction models to improve the accuracy and availability of data. The solar energy data integration report generated in this step provides a detailed analysis of solar energy output, including potential production capacity and efficiency.

[0115] In S402, the same data assimilation technology is applied to integrate wind energy output data. This includes analyzing the impact of key factors such as wind speed and wind direction on wind power generation and combining this real-time data with the wind energy output model. The generated wind energy data integration report also provides detailed information about wind energy output.

[0116] In S403, the solar energy data integration report and the wind energy data integration report are comprehensively analyzed, and the Particle Swarm Optimization (PSO) algorithm is applied. PSO is a swarm intelligence optimization tool used to search for the optimal energy combination and scheduling scheme. The preliminary energy integration scheme generated in this step takes into account the complementary characteristics of solar energy and wind energy to ensure the continuity and efficiency of energy supply.

[0117] In S404, the preliminary energy integration scheme is evaluated, and the genetic algorithm is used for optimization. This step mimics the natural selection mechanism to search for the best energy configuration scheme to achieve the maximum efficiency and cost-effectiveness of energy supply. The optimized energy integration scheme provides specific guidance on how to efficiently utilize solar energy and wind energy.

[0118] Please refer to Figure 6 , based on the Internet of Things and remote monitoring technologies, the adaptive adjustment algorithm is used to dynamically adjust the energy management strategy according to the actual situation. The steps to generate the real-time adjustment strategy are as follows:

[0119] S501: Based on the Internet of Things technology, the real-time data stream processing technology is applied to collect the current state data of the power grid and charging stations, and a real-time state data report is generated;

[0120] S502: Based on the real-time state data report, machine learning algorithms are used to analyze the dynamic changes of the power grid and charging stations, and a system dynamic analysis report is generated;

[0121] S503: Combining the system dynamic analysis report and the energy management strategy, the adaptive control algorithm is applied for strategy adjustment to generate a preliminary real-time adjustment strategy;

[0122] S504: Optimize the preliminary real-time adjustment strategy, adopt the model predictive control technology, and generate the real-time adjustment strategy.

[0123] In S501, the Internet of Things technology and the real-time data stream processing technology are used to collect the current state data of the power grid and charging stations. This includes but is not limited to the power grid load situation, the usage of charging stations, the status of energy storage devices, etc. The collected data is integrated and analyzed through the real-time data stream processing technology to generate a real-time state data report. This report provides the basic data for the real-time adjustment of the energy management strategy.

[0124] In S502, based on the real-time state data report, machine learning algorithms are used to analyze the dynamic changes of the power grid and charging stations. This step aims to identify and predict the behavior trends of the power grid and charging stations through advanced analysis technologies to generate a system dynamic analysis report. This report provides in-depth insights into the current and future states of the power grid and charging stations.

[0125] In S503, by combining the system dynamic analysis report and the existing energy management strategy, an adaptive control algorithm is applied for strategy adjustment. The adaptive control algorithm can dynamically adjust the energy management strategy according to real-time data and prediction results, ensuring that the strategy remains effective in a constantly changing environment. This step generates a preliminary real-time adjustment strategy.

[0126] In S504, the preliminary real-time adjustment strategy is optimized by adopting model predictive control (MPC) technology. MPC is an advanced control strategy that uses a model to predict future system behavior and makes optimized decisions based on this. Through the application of MPC technology, an accurate and efficient real-time adjustment strategy is generated.

[0127] Please refer to Figure 7 , based on the real-time adjustment strategy, pattern recognition technology is used for intelligent fault diagnosis and system maintenance. The steps to generate a fault diagnosis and maintenance plan are as follows:

[0128] S601: Based on the real-time adjustment strategy, using real-time monitoring and fault detection technology, a preliminary fault detection report is generated;

[0129] S602: Based on the preliminary fault detection report, pattern recognition and deep learning technologies are applied for fault cause analysis, and a fault cause analysis report is generated;

[0130] S603: The fault cause analysis report is compared with historical maintenance data, and case-based reasoning technology is used to determine the maintenance plan, generating a preliminary maintenance plan;

[0131] S604: The preliminary maintenance plan is optimized and adjusted by applying predictive maintenance and optimized decision support system technology, generating a fault diagnosis and maintenance plan.

[0132] In S601, with real-time monitoring and fault detection technology, the system is monitored based on the real-time adjustment strategy to promptly detect any abnormal or fault signs. This step includes monitoring key indicators such as device performance, energy consumption, temperature, etc., and analyzing abnormal fluctuations of these indicators. Through this real-time monitoring, a preliminary fault detection report is generated, identifying potential fault points.

[0133] In S602, based on the preliminary fault detection report, pattern recognition and deep learning technologies are applied for fault cause analysis. This step uses advanced algorithms, such as convolutional neural networks (CNNs) or recurrent neural networks (RNNs), to analyze the root causes and influencing factors of faults. Through this in-depth analysis, a fault cause analysis report is generated, providing detailed basis for maintenance decisions.

[0134] In S603, the fault cause analysis report is compared with historical maintenance data, and case-based reasoning technology is used to determine the most appropriate maintenance plan. Case-based reasoning technology analyzes historical cases of similar faults to find the most effective maintenance strategy. This step generates a preliminary maintenance plan, including the types, steps, and schedules of maintenance activities.

[0135] In S604, the preliminary maintenance plan is further optimized and adjusted by applying predictive maintenance and optimized decision support system technology. This includes considering the life cycle of the equipment, maintenance costs, and operating efficiency, as well as risk and safety factors. Through this optimization, a final fault diagnosis and maintenance plan is generated.

[0136] Please refer to Figure 8 , an energy storage system for an electric vehicle charging station. The energy storage system for an electric vehicle charging station is used to execute the above-mentioned energy storage method for an electric vehicle charging station. The system includes a data collection module, a demand prediction module, an energy management module, an energy integration module, a real-time adjustment module, a fault diagnosis module, and a system maintenance module.

[0137] Based on Internet of Things technology, the data collection module uses data fusion and distributed database management technology to collect historical charging data, traffic flow, weather forecasts, and user behavior patterns, generating a comprehensive data set;

[0138] Based on the comprehensive data set, the demand prediction module uses exploratory data analysis and factor analysis techniques to determine influencing factors, and applies long short-term memory network algorithms for time series analysis, generating a charging demand prediction model;

[0139] Based on the charging demand prediction model, the energy management module uses system dynamic modeling and prediction technology to evaluate demand trends, and combines decision tree analysis and linear programming methods to generate an energy management strategy;

[0140] Based on the energy management strategy, the energy integration module uses data assimilation technology to integrate solar and wind energy output data, and applies particle swarm optimization algorithm and genetic algorithm technology to generate an optimized energy integration plan;

[0141] Based on Internet of Things technology, the real-time adjustment module uses real-time data stream processing technology to collect current state data, and combines machine learning algorithms and adaptive control algorithms to generate a real-time adjustment strategy;

[0142] Based on the real-time adjustment strategy, the fault diagnosis module uses real-time monitoring and fault detection technology, and combines pattern recognition and deep learning technology to generate a fault cause analysis report;

[0143] Based on the fault cause analysis report, the system maintenance module uses case-based reasoning technology and predictive maintenance technology, and combines an optimized decision support system to generate a fault diagnosis and maintenance plan.

[0144] The application of the data collection module enables the system to comprehensively collect and analyze historical charging data, traffic flow, weather forecasts, and user behavior patterns of charging stations. The generation of such a comprehensive dataset not only improves the quality and depth of data processing but also provides a solid data foundation for accurately predicting charging demand and formulating effective strategies.

[0145] The demand prediction module uses the long short-term memory network algorithm to perform time series analysis on charging demand, making the prediction results more accurate and reliable. This is crucial for electric vehicle charging stations as it helps optimize resource allocation and plan the operation of charging facilities in advance, thereby improving service efficiency and user satisfaction.

[0146] The introduction of the energy management module evaluates demand trends through system dynamic modeling and prediction techniques, and combines decision tree analysis and linear programming methods to effectively formulate energy management strategies. Such strategies can ensure the effective allocation and utilization of energy, reduce waste, and maintain the efficient operation of the system.

[0147] The design of the energy integration module, by integrating renewable energy such as solar and wind energy, not only reduces the dependence on traditional energy but also promotes the charging station to develop in a more green and sustainable direction. This optimized energy integration solution further improves the efficiency and economy of energy utilization through particle swarm optimization algorithm and genetic algorithm techniques.

[0148] The real-time adjustment module uses Internet of Things technology and real-time data stream processing technology to improve the system's response speed and adaptability to the current state. This dynamic adjustment strategy enables the system to quickly respond to various changes and potential problems, ensuring the continuity and stability of operation.

[0149] The combined use of the fault diagnosis module and the system maintenance module not only improves the accuracy of fault detection but also speeds up the efficiency of fault response and maintenance. This intelligent diagnosis based on deep learning and maintenance strategy based on case-based reasoning greatly enhances the reliability and security of the system.

[0150] The above is only the preferred embodiment of the present invention, and it is not intended to limit the present invention in other forms. Any person skilled in the art may use the disclosed technical content to make changes or modifications into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change, and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution content of the present invention still fall within the protection scope of the technical solution of the present invention.

Claims

1. An energy storage method for an electric vehicle charging station, characterized in that: The following steps are involved: Based on the Internet of Things technology, data collection and network analysis algorithms are used to collect historical charging data of charging stations, surrounding traffic flow, weather forecasts and user behavior patterns to generate a comprehensive data set; Based on the comprehensive data set, a long short-term memory network algorithm is used to perform time series forecasting of charging demand and generate a charging demand forecasting model; Based on the charging demand prediction model, a linear programming algorithm is used to formulate a charging and discharging strategy for the energy storage device and generate an energy management strategy; Based on the energy management strategy, an energy scheduling optimization algorithm is used to integrate solar and wind energy output data to generate an optimized energy fusion solution; Based on the Internet of Things and remote monitoring technology, an adaptive adjustment algorithm is used to dynamically adjust the energy management strategy according to actual conditions to generate a real-time adjustment strategy; Based on the real-time adjustment strategy, pattern recognition technology is used to perform intelligent fault diagnosis and system maintenance to generate fault diagnosis and maintenance plans; Based on the comprehensive data set, the long short-term memory network algorithm is used to predict the time series of charging demand. The steps of generating the charging demand prediction model are as follows: Based on the comprehensive data set, using exploratory data analysis and factor analysis methods to identify key factors affecting charging demand, and generate a list of factors affecting charging demand; Based on the list of factors affecting charging demand, a long short-term memory network algorithm is used to perform time series analysis to generate a preliminary charging demand forecast report; Optimizing the preliminary charging demand forecast report, using an autoregressive moving average model and seasonal decomposition technology to improve forecast accuracy, and generating an optimized charging demand forecast report; Based on the optimized charging demand forecast report, adjusting and improving the long short-term memory network model to generate a charging demand forecast model; Based on the energy management strategy, the energy scheduling optimization algorithm is used to integrate the solar energy and wind energy output data to generate the optimized energy fusion solution in the following steps: Based on the energy management strategy, the solar energy output data is integrated by using data assimilation technology to generate a solar energy data integration report; Based on the energy management strategy, the wind energy output data is integrated by applying data assimilation technology to generate a wind energy data integration report; Comprehensively analyzing the solar energy data integration report and the wind energy data integration report, and applying a particle swarm optimization algorithm to generate a preliminary energy fusion plan; Evaluate the preliminary energy fusion plan and generate an optimized energy fusion plan using genetic algorithm optimization technology; The data assimilation technology includes sensor data and prediction models. The particle swarm optimization algorithm is specifically an optimization tool based on swarm intelligence, which is used to search for the optimal energy combination. The genetic algorithm optimization technology imitates the natural selection mechanism to search for the best energy configuration solution.

2. The energy storage method for an electric vehicle charging station according to claim 1, characterized in that: The comprehensive data set includes charging patterns, traffic conditions, climate change and user preference information. The charging demand prediction model specifically includes a predictive analysis of charging demand at differentiated times and regions. The energy management strategy includes energy allocation, storage timing and release timing planning. The optimized energy fusion solution includes a strategy for utilizing and storing electricity from renewable energy. The fault diagnosis and maintenance solution specifically refers to immediate discovery, diagnosis and maintenance measures for system faults.

3. The energy storage method for an electric vehicle charging station according to claim 1, characterized in that: Based on the Internet of Things technology, data collection and network analysis algorithms are used to collect historical charging data of charging stations, surrounding traffic flow, weather forecasts and user behavior patterns. The steps to generate a comprehensive data set are as follows: Based on the Internet of Things technology, data fusion and distributed database management system are used to collect historical charging data of charging stations and generate historical charging data sets; Based on the historical charging data set, association rule learning and sequence pattern mining techniques are applied to analyze user charging behavior and generate a user charging behavior analysis report; Based on geographic information system, spatial data analysis and traffic pattern recognition technology are used to collect traffic flow and weather forecast data to generate traffic and weather data sets; Integrate the historical charging data set, user charging behavior analysis report, traffic and weather data set, and use big data integration and analysis technology to generate a comprehensive data set; The data fusion technology includes the integration and synchronization of heterogeneous data sources, the association rule learning is used to discover frequent patterns between data items, the spatial data analysis technology is used to identify patterns and trends in geospatial data, and the big data integration technology includes data cleaning, conversion and aggregation.

4. The energy storage method for an electric vehicle charging station according to claim 1, characterized in that: Based on the charging demand prediction model, a linear programming algorithm is used to formulate a charging and discharging strategy for energy storage equipment. The steps for generating an energy management strategy are as follows: Based on the charging demand prediction model, the future charging demand trend is evaluated by using system dynamic modeling and prediction methods, and a charging demand trend report is generated; Based on the charging demand trend report, a preliminary charging and discharging strategy is designed by applying decision tree analysis and linear programming methods to generate a preliminary charging and discharging strategy solution; Conducting performance analysis on the preliminary charging and discharging strategy, using Monte Carlo simulation technology to verify the actual application effect of the strategy, and generating a charging and discharging strategy evaluation report; Based on the charging and discharging strategy evaluation report and real-time power grid data, the charging and discharging strategy of the energy storage device is finally determined using improved linear programming and optimization methods to generate an energy management strategy.

5. The energy storage method for an electric vehicle charging station according to claim 1, characterized in that: Based on the Internet of Things and remote monitoring technology, an adaptive adjustment algorithm is used to dynamically adjust the energy management strategy according to actual conditions. The steps of generating a real-time adjustment strategy are as follows: Based on the Internet of Things technology, real-time data stream processing technology is used to collect the current status data of the power grid and charging stations, and generate real-time status data reports; Based on the real-time status data report, a machine learning algorithm is used to analyze the dynamic changes of the power grid and the charging station to generate a system dynamic analysis report; Combining the system dynamic analysis report and energy management strategy, applying an adaptive control algorithm to adjust the strategy and generate a preliminary real-time adjustment strategy; The preliminary real-time adjustment strategy is optimized and a real-time adjustment strategy is generated using model predictive control technology.

6. The energy storage method for an electric vehicle charging station according to claim 1, characterized in that: Based on the real-time adjustment strategy, pattern recognition technology is used to perform intelligent fault diagnosis and system maintenance, and the steps of generating fault diagnosis and maintenance solutions are as follows: Based on the real-time adjustment strategy, using real-time monitoring and fault detection technology, generate a preliminary fault detection report; Based on the preliminary fault detection report, applying pattern recognition and deep learning technology to perform fault cause analysis and generate a fault cause analysis report; Compare the fault cause analysis report with historical maintenance data, use case-based reasoning technology to determine the maintenance plan, and generate a preliminary maintenance plan; The preliminary maintenance plan is optimized and adjusted, and predictive maintenance and optimization decision support system technology is applied to generate fault diagnosis and maintenance plans.

7. An energy storage system for an electric vehicle charging station, characterized in that: According to the energy storage method for an electric vehicle charging station according to any one of claims 1 to 6, the system includes a data collection module, a demand forecasting module, an energy management module, an energy fusion module, a real-time adjustment module, a fault diagnosis module, and a system maintenance module.

8. The energy storage system for an electric vehicle charging station according to claim 7, characterized in that: The data collection module is based on the Internet of Things technology and uses data fusion and distributed database management technology to collect historical charging data, traffic flow, weather forecasts and user behavior patterns to generate a comprehensive data set; The demand forecasting module is based on a comprehensive data set, uses exploratory data analysis and factor analysis techniques to determine influencing factors, applies a long short-term memory network algorithm to perform time series analysis, and generates a charging demand forecasting model; The energy management module generates an energy management strategy based on the charging demand forecasting model, using system dynamic modeling and forecasting technology to evaluate demand trends, and combining decision tree analysis and linear programming methods; The energy fusion module is based on energy management strategy, uses data assimilation technology to integrate solar energy and wind energy output data, and applies particle swarm optimization algorithm and genetic algorithm technology to generate optimized energy fusion solutions; The real-time adjustment module is based on the Internet of Things technology, applies real-time data stream processing technology to collect current state data, combines machine learning algorithms and adaptive control algorithms, and generates real-time adjustment strategies; The fault diagnosis module generates a fault cause analysis report based on real-time adjustment strategies, using real-time monitoring and fault detection technology, combined with pattern recognition and deep learning technology; The system maintenance module generates fault diagnosis and maintenance plans based on the fault cause analysis report, using case-based reasoning technology and predictive maintenance technology, combined with an optimized decision support system.

Images