CN118100240A

CN118100240A - Energy storage method and system for electric vehicle charging station

Info

Publication number: CN118100240A
Application number: CN202410094254.8A
Authority: CN
Inventors: 唐念登
Original assignee: Guangzhou Lingsheng New Energy Technology Co ltd
Current assignee: Guangzhou Lingsheng New Energy Technology Co ltd
Priority date: 2024-01-23
Filing date: 2024-01-23
Publication date: 2024-05-28

Abstract

The invention relates to the technical field of electric automobile infrastructure, in particular to an energy storage method and system for an electric automobile charging station, comprising the following steps: based on the internet of things technology, historical charging data of the charging station, peripheral traffic flow, weather forecast and user behavior patterns are collected by adopting a data acquisition and network analysis algorithm, and a comprehensive data set is generated. According to the invention, the charging requirements of each period and region can be predicted by applying a long-period memory network algorithm, the optimization of energy distribution is realized, the maximum utilization and the efficiency improvement of energy are ensured by a linear programming algorithm on the establishment of a charging and discharging strategy of energy storage equipment, the utilization of renewable energy sources such as solar energy, wind energy and the like is more efficient by an energy scheduling optimization algorithm, the sustainable use of the energy sources is promoted, the stable operation is kept under the condition of dynamic change by combining an adaptive regulation algorithm and a pattern recognition technology, the timely diagnosis and effective maintenance of faults are realized, and the reliability and the maintenance efficiency of the whole system are improved.

Description

Energy storage method and system for electric vehicle charging station

Technical Field

The invention relates to the technical field of electric automobile infrastructures, in particular to an energy storage method and system for an electric automobile charging station.

Background

The field of electric vehicle infrastructure technology relates to various technologies and facilities that provide the necessary support for electric vehicles, including but not limited to charging stations, energy storage systems, and interactions with the power grid. The main aim of the field is to ensure that the electric car user can conveniently and efficiently charge his vehicle. With the rapid growth of the electric automobile market, the demand for charging infrastructure is also increasing. 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 sources, electric automobile infrastructure is also gradually evolving towards more environmental protection and sustainability.

The energy storage method for the electric vehicle charging station refers to an energy storage technology deployed at the electric vehicle charging station, and the main purpose of the energy storage method is to improve charging efficiency and reduce the burden of the charging station on a power grid. The method can store energy when the load of the power grid is low and release the energy rapidly in the peak time, thereby reducing the load of the power grid in the peak time. Helping the charging station to maintain stable operation when renewable energy output is unstable, such as on windless or cloudy days. In this way, the reliability and efficiency of the electric vehicle charging can be improved while facilitating the use of renewable energy sources. This energy storage method is typically implemented by installing a Battery Energy Storage System (BESS). These systems are capable of storing large amounts of electrical energy when demand is low and rapidly releasing energy when demand increases. In addition to batteries, more advanced management systems, such as intelligent charge management and demand response techniques, are also involved to optimize the charging station interaction with the grid. In addition, some advanced energy storage methods integrate machine learning and artificial intelligence techniques to predict charging needs and optimize energy distribution. These techniques work together to ensure that the electric vehicle charging station operates efficiently and stably in different operating environments.

The conventional electric vehicle charging station energy storage method has some defects. The lack of efficient algorithm support, such as long and short term memory networks, makes charging demand predictions inaccurate enough to cope with demand fluctuations. In addition, the traditional method often lacks flexibility and optimization in energy management strategy formulation, and renewable energy sources cannot be fully utilized, so that the energy utilization efficiency is low. Finally, conventional systems are generally limited in their ability to monitor and diagnose faults in real time, making it difficult to achieve rapid response and effective maintenance, affecting the stability and reliability of the system.

Disclosure of Invention

The invention aims to solve the defects in the prior art, and provides an energy storage method and an energy storage system for an electric vehicle charging station.

In order to achieve the above purpose, the present invention adopts the following technical scheme: an energy storage method for an electric vehicle charging station, comprising the steps of:

s1: based on the internet of things technology, collecting historical charging data of a charging station, peripheral traffic flow, weather forecast and a user behavior mode by adopting a data acquisition and network analysis algorithm to generate a comprehensive data set;

S2: based on the comprehensive data set, adopting a long-short-term memory network algorithm to conduct time sequence prediction of the charging demand, and generating a charging demand prediction model;

S3: based on the charging demand prediction model, adopting a linear programming algorithm to formulate a charging and discharging strategy of the energy storage equipment, and generating an energy management strategy;

s4: based on the energy management strategy, integrating solar energy and wind energy output data by adopting an energy scheduling optimization algorithm to generate an optimized energy fusion scheme;

S5: based on the Internet of things and a remote monitoring technology, dynamically adjusting the energy management strategy according to actual conditions by adopting an adaptive adjustment algorithm, and generating a real-time adjustment strategy;

s6: based on the real-time adjustment strategy, intelligent fault diagnosis and system maintenance are performed by adopting a pattern recognition technology, and a fault diagnosis and maintenance scheme is generated.

As a further aspect of the invention, the comprehensive data set comprises a charging mode, traffic conditions, climate change and user preference information, the charging demand prediction model is specifically a prediction analysis of differentiated time and region charging demand, the energy management strategy comprises energy distribution, storage opportunity and release opportunity planning, the optimized energy fusion scheme comprises a strategy for utilizing and storing electric power from renewable energy sources, and the fault diagnosis and maintenance scheme is specifically a strategy for immediately discovering, diagnosing and maintaining system faults.

As a further scheme of the invention, based on the technology of the Internet of things, the data acquisition and network analysis algorithm is adopted to collect historical charging data of the charging station, peripheral traffic flow, weather forecast and user behavior patterns, and the steps for generating the comprehensive data set are as follows:

S101: based on the internet of things technology, collecting historical charging data of a charging station by using a data fusion and distributed database management system, and generating a historical charging data set;

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

S103: based on a geographic information system, collecting traffic flow and weather forecast data by using a spatial data analysis and traffic pattern recognition technology, and generating a traffic and weather data set;

s104: integrating the historical charging data set, the user charging behavior analysis report and the traffic and weather data set, and generating an integrated data set by applying a big data integration and analysis technology;

The data fusion technology comprises the integration and synchronization of heterogeneous data sources, the association rule learning is used for finding frequent patterns among data items, the spatial data analysis technology is used for identifying patterns and trends of geospatial data, and the big data integration technology comprises data cleaning, conversion and summarization.

As a further scheme of the invention, based on the comprehensive data set, a long-short-term memory network algorithm is adopted to conduct time sequence prediction of the charging demand, and the step of generating a charging demand prediction model specifically comprises the following steps:

s201: determining key factors influencing the charging requirements by using exploratory data analysis and factor analysis methods based on the comprehensive data set, and generating a charging requirement influence factor list;

S202: based on the charging demand influence factor list, applying a long-short-term memory network algorithm to perform time sequence analysis, and generating a preliminary charging demand prediction report;

s203: optimizing the preliminary charging demand prediction report, improving the prediction accuracy by using an autoregressive moving average model and a seasonal decomposition technology, and generating an optimized charging demand prediction report;

s204: and adjusting and perfecting a long-and-short-term memory network model based on the optimized charging demand prediction report, and generating a charging demand prediction model.

As a further scheme of the invention, based on the charging demand prediction model, a linear programming algorithm is adopted to formulate a charging and discharging strategy of the energy storage device, and the step of generating the energy management strategy specifically comprises the following steps:

s301: based on the charging demand prediction model, estimating future charging demand trend by utilizing a system dynamic modeling and prediction method, and generating a charging demand trend report;

S302: based on the charging demand trend report, a decision tree analysis and linear programming method is applied to design a preliminary charging and discharging strategy, and a preliminary charging and discharging strategy scheme is generated;

S303: performing efficiency analysis on the preliminary charge-discharge strategy scheme, and verifying the actual application effect of the strategy by using a Monte Carlo simulation technology to generate a charge-discharge strategy evaluation report;

S304: based on the charge-discharge strategy evaluation report and the real-time power grid data, the charge-discharge strategy of the energy storage device is finally determined by using an improved linear programming and optimizing method, and an energy management strategy is generated.

As a further scheme of the present invention, based on the energy management strategy, the step of integrating solar energy and wind energy output data by adopting an energy scheduling optimization algorithm to generate an optimized energy fusion scheme specifically includes:

S401: integrating solar energy output data by adopting a data assimilation technology based on the energy management strategy to generate a solar energy data integration report;

S402: based on the energy management strategy, integrating wind energy output data by applying a data assimilation technology to generate a wind energy data integration report;

s403: comprehensively analyzing the solar data integrated report and the wind energy data integrated report, and generating a preliminary energy fusion scheme by applying a particle swarm optimization algorithm;

s404: evaluating the preliminary energy fusion scheme, and generating an optimized energy fusion scheme by adopting a genetic algorithm optimization technology;

The data assimilation technology comprises sensor data and a prediction model, the particle swarm optimization algorithm is specifically an optimization tool based on swarm intelligence and is used for searching optimal energy combination, and the genetic algorithm optimization technology simulates a natural selection mechanism and searches an optimal energy configuration scheme.

As a further scheme of the invention, based on the Internet of things and a remote monitoring technology, an adaptive adjustment algorithm is adopted to dynamically adjust the energy management strategy according to actual conditions, and the step of generating a real-time adjustment strategy specifically comprises the following steps:

s501: based on the internet of things technology, current state data of a power grid and a charging station are collected by applying a real-time data stream processing technology, and a real-time state data report is generated;

s502: based on the real-time state data report, analyzing dynamic changes of the power grid and the charging station by using a machine learning algorithm, and generating a system dynamic analysis report;

S503: combining the system dynamic analysis report and the energy management strategy, and applying a self-adaptive control algorithm to carry out strategy adjustment to generate a preliminary real-time adjustment strategy;

s504: and optimizing the preliminary real-time adjustment strategy, and generating the real-time adjustment strategy by adopting a model predictive control technology.

As a further scheme of the invention, based on the real-time adjustment strategy, intelligent fault diagnosis and system maintenance are performed by adopting a mode identification technology, and the steps for generating the fault diagnosis and maintenance scheme are as follows:

s601: based on the real-time adjustment strategy, generating a preliminary fault detection report by utilizing a real-time monitoring and fault detection technology;

S602: based on the preliminary fault detection report, performing fault cause analysis by using a mode identification and deep learning technology, and generating a fault cause analysis report;

S603: comparing the fault cause analysis report with historical maintenance data, determining a maintenance scheme by using a case-based reasoning technology, and generating a preliminary maintenance scheme;

s604: and optimizing and adjusting the preliminary maintenance scheme, and applying a predictive maintenance and optimization decision support system technology to generate a fault diagnosis and maintenance scheme.

An energy storage system for an electric vehicle charging station for executing the energy storage method for the electric vehicle charging station comprises a data collection module, a demand prediction module, an energy management module, an energy fusion module, a real-time adjustment module, a fault diagnosis module and a system maintenance module.

As a further scheme of the invention, the data collection module is used for collecting historical charging data, traffic flow, weather forecast and user behavior modes by adopting a data fusion and distributed database management technology based on the Internet of things technology to generate a comprehensive data set;

the demand prediction module is used for determining influence factors by adopting exploratory data analysis and factor analysis technology based on the comprehensive data set, and performing time sequence analysis by applying a long-term and short-term memory network algorithm to generate a charging demand prediction model;

The energy management module is used for evaluating the demand trend by utilizing a system dynamic modeling and prediction technology based on a charging demand prediction model, and generating an energy management strategy by combining a decision tree analysis and a linear programming method;

The energy fusion module integrates solar energy and wind energy output data by adopting a data assimilation technology based on an energy management strategy, and an optimized energy fusion scheme is generated by applying a particle swarm optimization algorithm and a genetic algorithm technology;

the real-time adjustment module is based on the internet of things technology, collects current state data by applying a real-time data stream processing technology, and combines a machine learning algorithm and a self-adaptive control algorithm to generate a real-time adjustment strategy;

The fault diagnosis module generates a fault cause analysis report by combining a mode identification and a deep learning technology based on a real-time adjustment strategy and by utilizing a real-time monitoring and fault detection technology;

the system maintenance module generates a fault diagnosis and maintenance scheme by adopting a case-based reasoning technology and a predictive maintenance technology and combining an optimized decision support system based on a fault cause analysis report.

Compared with the prior art, the invention has the advantages and positive effects that:

According to the invention, the long-term and short-term memory network algorithm enables the time sequence prediction of the charging demand to be more accurate, and the charging demands of different times and areas can be effectively predicted, so that the energy distribution is optimized. The application of the linear programming algorithm ensures the maximization of energy utilization and the improvement of efficiency in terms of the preparation of the charge-discharge strategy of the energy storage device. The integration of the energy scheduling optimization algorithm enables renewable energy sources such as solar energy, wind energy and the like to be utilized more effectively, and sustainable use of the energy sources is promoted. The combination of the adaptive regulation algorithm and the pattern recognition technology ensures that the system can still keep stable operation under the actual condition of dynamic change, and can diagnose and maintain in time, thereby improving the reliability and maintenance efficiency of the system.

Drawings

FIG. 1 is a schematic workflow diagram of the present invention;

FIG. 2 is a S1 refinement flowchart of the present invention;

FIG. 3 is a S2 refinement flowchart of the present invention;

FIG. 4 is a S3 refinement flowchart of the present invention;

FIG. 5 is a S4 refinement flowchart of the present invention;

FIG. 6 is a S5 refinement flowchart of the present invention;

FIG. 7 is a S6 refinement flowchart of the present invention;

fig. 8 is a system flow diagram of the present invention.

Detailed Description

The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.

In the description of the present invention, it should be understood that the terms "length," "width," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," and the like indicate orientations or positional relationships based on the orientation or positional relationships shown in the drawings, merely to facilitate describing the present invention and simplify the description, and do not indicate or imply that the devices or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and therefore should not be construed as limiting the present invention. Furthermore, in the description of the present invention, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.

Example 1

Referring to fig. 1, the present invention provides a technical solution: an energy storage method for an electric vehicle charging station, comprising the steps of:

S3: based on a charging demand prediction model, adopting a linear programming algorithm to formulate a charging and discharging strategy of the energy storage equipment, and generating an energy management strategy;

s4: based on an energy management strategy, integrating solar energy and wind energy output data by adopting an energy scheduling optimization algorithm to generate an optimized energy fusion scheme;

S5: based on the Internet of things and a remote monitoring technology, an adaptive adjustment algorithm is adopted to dynamically adjust an energy management strategy according to actual conditions, and a real-time adjustment strategy is generated;

The comprehensive data set comprises a charging mode, traffic conditions, climate change and user preference information, the charging demand prediction model is specifically a prediction analysis of the differentiated time and the charging demand of the region, the energy management strategy comprises energy distribution, storage time and release time planning, the optimized energy fusion scheme comprises a strategy for utilizing and storing electric power from renewable energy sources, and the fault diagnosis and maintenance scheme is specifically a system fault immediate discovery, diagnosis and maintenance measure.

Through the internet of things technology, data acquisition and network analysis can more comprehensively and accurately collect historical charging data, peripheral traffic flow, weather conditions and user behavior patterns of the charging station. The comprehensive data collection provides a solid foundation for accurate prediction of charging demands, and is helpful for better understanding and predicting the running condition and potential demands of the charging station, so that the response efficiency and service quality of the whole system are improved.

The application of the long-term and short-term memory network algorithm enables the time sequence prediction to be more accurate. The algorithm can effectively process and analyze time series data, accurately predict the charging demand of different time and areas, and help a charging station manager to better plan resource allocation and operation strategies, so that the operation efficiency of the charging station is optimized.

The linear programming algorithm is applied to the establishment of a charging and discharging strategy of the energy storage device, so that energy management is more efficient. The establishment of the strategy considers the optimal distribution, storage time and release time of energy, is beneficial to reducing energy waste, improving energy utilization efficiency and ensuring the stable operation of the charging station in peak time.

The energy scheduling optimization algorithm integrates solar energy and wind energy output data to form an optimized energy fusion scheme. The method not only improves the utilization rate of renewable energy sources and reduces the dependence on traditional energy sources, but also is beneficial to reducing environmental pollution and promoting the green development of charging stations.

The combination of the Internet of things and the remote monitoring technology and the application of the adaptive adjustment algorithm enable the energy management strategy to be dynamically adjusted according to actual conditions. The real-time adjustment strategy improves the flexibility and adaptability of the system and ensures stable operation under various emergency conditions. The application of the pattern recognition technology in intelligent fault diagnosis and system maintenance greatly improves the accuracy of fault detection and the efficiency of maintenance work.

Referring to fig. 2, based on the internet of things technology, the steps of collecting charging station historical charging data, surrounding traffic flow, weather forecast and user behavior patterns by adopting a data collection and network analysis algorithm, and generating a comprehensive data set are specifically as follows:

S102: based on the historical charging data set, analyzing the charging behavior of the user by applying association rule learning and sequence pattern mining technologies, and generating a user charging behavior analysis report;

s104: a comprehensive historical charging data set, a user charging behavior analysis report, a traffic and weather data set and a big data integration and analysis technology are applied to generate a comprehensive data set;

The data fusion technology comprises the integration and synchronization of heterogeneous data sources, association rule learning is used for finding frequent patterns among data items, the spatial data analysis technology is used for identifying patterns and trends of geospatial data, and the big data integration technology comprises data cleaning, conversion and summarization.

In S101, the system collects historical charging data by deploying various types of sensors, such as an electric energy meter, an environmental monitor, etc., at the charging station using the internet of things technology. These data are then integrated by a distributed database management system to form a historical charging dataset. The data fusion technique in this process, particularly the integration and synchronization of heterogeneous data sources, ensures that the collected data has a high degree of integrity and consistency.

In S102, the system further analyzes the historical charge data set. Association rule learning and sequence pattern mining techniques are applied here to identify the charging behavior patterns of the user, such as charging time preference, charging frequency, etc. The purpose of this step is to generate a user charging behavior analysis report that provides more accurate user behavior insight for subsequent demand prediction and policy formulation.

In S103, the system collects data related to traffic flow and weather forecast around the charging station through Geographic Information System (GIS) technology. By using the spatial data analysis and traffic pattern recognition technology, the system can understand and predict the influence of traffic flow change on the charging requirement and evaluate the charging behavior patterns under different weather conditions. Such a data set provides important information about external environmental factors.

In S104, the system synthesizes the historical charging data set, the user charging behavior analysis report and the traffic and weather data set, and generates the synthesized data set by applying the big data integration and analysis technology. The big data technology in the step, especially data cleaning, conversion and summarization, ensures the quality and applicability of the data, and integrates the finally generated comprehensive data into key assets for formulating an effective energy storage strategy and optimizing the operation of the charging station.

Referring to fig. 3, based on the integrated data set, the method for predicting the time sequence of the charging requirement by adopting the long-short-term memory network algorithm specifically includes the following steps:

S201: based on the comprehensive data set, determining key factors influencing the charging requirement by using exploratory data analysis and a factor analysis method, and generating a charging requirement influence factor list;

S204: and adjusting and perfecting the long-period memory network model based on the optimized charging demand prediction report to generate a charging demand prediction model.

In S201, exploratory data analysis and factor analysis are performed based on the integrated data set, and key factors affecting the charging demand are determined. This step includes analyzing various variables that affect the charging demand, such as time, weather, seasonal changes, economic indicators, etc., as well as correlations and influences between these factors. Through this analysis, a charging demand influence factor list is generated.

In S202, based on the determined influence factor list, a long short term memory network (LSTM) algorithm is applied for time series analysis. LSTM is particularly suitable for processing and predicting long-term dependencies in time series data. And generating a preliminary charging demand prediction report through LSTM model analysis, and displaying the prediction results of the charging demands under different conditions.

In S203, to improve the prediction accuracy, the preliminary charging demand prediction report is optimized. The prediction is further refined using an autoregressive moving average (ARIMA) model and seasonal decomposition techniques. The ARIMA model helps capture trends and seasonal changes in time series data, while seasonal decomposition allows for the definition of demand fluctuations over different time periods. This step generates an optimized charge demand prediction report.

In S204, the LSTM model is adjusted and refined based on the optimized charge demand prediction report. This includes adjusting network parameters, increasing training periods, or modifying the data preprocessing approach. The optimized LSTM model reflects the dynamic change of the charging demand more accurately, and a final charging demand prediction model is generated.

Referring to fig. 4, based on a charging demand prediction model, a linear programming algorithm is adopted to formulate a charging and discharging strategy of an energy storage device, and the step of generating an energy management strategy specifically includes:

s303: performing efficiency analysis on the preliminary charge-discharge strategy scheme, verifying the actual application effect of the strategy by using a Monte Carlo simulation technology, and generating a charge-discharge strategy evaluation report;

In S301, a future charging demand trend is estimated based on the charging demand prediction model by using a system dynamic modeling and prediction method. This step includes analyzing the time series data provided by the predictive model to identify periodicity, trending, and potential fluctuations in the charging demand. Through the analysis, a charging demand trend report is generated, and a basis is provided for formulating a charging and discharging strategy.

In S302, based on the charging demand trend report, a decision tree analysis and a linear programming method are applied to design a preliminary charging and discharging strategy. In this step, a preliminary charge-discharge schedule and operation guidelines are formulated in consideration of factors such as charge demand, grid conditions, energy storage device capacity and efficiency. The preliminary charge-discharge strategy scheme generated at this stage is the first draft of strategy formulation.

In S303, a performance analysis is performed on the preliminary charge-discharge strategy scheme. And simulating the strategy for a plurality of times by using a Monte Carlo simulation technology, and verifying the actual application effect and stability of the strategy under different conditions. The charge-discharge strategy evaluation report generated in this step provides performance indicators and potential risks of the strategy.

In S304, based on the charge-discharge policy evaluation report and the real-time grid data, the charge-discharge policy of the energy storage device is finally determined using the improved linear programming and optimization method. At this stage, the strategy is refined and adjusted according to the actual situation and the power grid demand, so as to ensure that the efficiency and economic benefit of the energy storage device are maximized. After these steps are completed, the final energy management strategy is generated.

Referring to fig. 5, based on an energy management policy, the steps of integrating solar energy and wind energy output data by using an energy scheduling optimization algorithm to generate an optimized energy fusion scheme are specifically as follows:

S401: integrating solar energy output data by adopting a data assimilation technology based on an energy management strategy to generate a solar energy data integration report;

s402: based on an energy management strategy, integrating wind energy output data by applying a data assimilation technology to generate a wind energy data integration report;

In S401, solar energy output data is integrated by adopting a data assimilation technology based on an energy management strategy. Data assimilation refers herein to combining real-time solar sensor data with predictive models to improve the accuracy and usability of the data. The solar data integration report generated by this step provides detailed solar yield analysis, including potential capacity and efficiency.

In S402, the same data assimilation technique is applied to integrate wind energy production data. This involves analyzing the effects of key factors such as wind speed, wind direction, etc. on wind power generation and combining these real-time data with a wind energy production model. The generated wind energy data integration report also provides detailed information about wind energy production.

In S403, the solar energy data integration report and the wind energy data integration report are comprehensively analyzed, and a Particle Swarm Optimization (PSO) algorithm is applied. PSO is a population intelligent optimization tool used for searching the optimal energy combination and scheduling scheme. The primary energy fusion scheme generated in the step considers the complementary characteristics of solar energy and wind energy, and ensures the continuity and efficiency of energy supply.

In S404, the preliminary energy fusion scheme is evaluated and optimized using a genetic algorithm. This step mimics the natural selection mechanism, searches for the optimal energy configuration scheme, and achieves maximum efficiency and cost effectiveness of energy supply. The optimized energy fusion scheme provides specific guidance on how to efficiently utilize solar and wind energy.

Referring to fig. 6, based on the internet of things and the remote monitoring technology, an adaptive adjustment algorithm is adopted to dynamically adjust an energy management policy according to actual conditions, and the steps of generating a real-time adjustment policy are specifically as follows:

s503: combining a system dynamic analysis report and an energy management strategy, and applying a self-adaptive control algorithm to carry out strategy adjustment to generate a preliminary real-time adjustment strategy;

In S501, current state data of the power grid and the charging station are collected by using the internet of things technology and the real-time data stream processing technology. This includes, but is not limited to, grid load conditions, charging station usage conditions, the status of the energy storage device, and the like. The collected data is integrated and analyzed by real-time data stream processing techniques to generate real-time status data reports. This report provides the basis data for real-time adjustment of the energy management strategy.

In S502, based on the real-time status data report, dynamic changes of the power grid and the charging station are analyzed using a machine learning algorithm. This step aims at identifying and predicting the behavior trend of the power grid and the charging station through advanced analysis technology, and generating a system dynamic analysis report. The report provides insight into the current and future state of the power grid and charging station.

In S503, in combination with the system dynamic analysis report and the existing energy management policy, the adaptive control algorithm is applied to perform policy adjustment. The self-adaptive control algorithm can dynamically adjust the energy management strategy according to the real-time data and the prediction result, and ensure that the strategy is still effective in a continuously-changing environment. This step generates a preliminary real-time adjustment strategy.

In S504, the preliminary real-time adjustment strategy is optimized, and a Model Predictive Control (MPC) technique is adopted. MPC is an advanced control strategy that uses models to predict future system behavior and make optimization decisions based thereon. By application of MPC technology, an accurate and efficient real-time tuning strategy is generated.

Referring to fig. 7, based on a real-time adjustment strategy, intelligent fault diagnosis and system maintenance are performed by using a pattern recognition technology, and the steps of generating a fault diagnosis and maintenance scheme are specifically as follows:

S601: based on a real-time adjustment strategy, generating a preliminary fault detection report by utilizing a real-time monitoring and fault detection technology;

s603: comparing the fault cause analysis report with the historical maintenance data, determining a maintenance scheme by using a case-based reasoning technology, and generating a preliminary maintenance scheme;

In S601, the system is monitored based on a real-time adjustment strategy by using a real-time monitoring and fault detection technique, and any signs of abnormality or fault are found in time. This step includes monitoring key indicators of equipment 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 points of failure.

In S602, based on the preliminary fault detection report, a pattern recognition and deep learning technique is applied to perform fault cause analysis. This step utilizes advanced algorithms, such as Convolutional Neural Networks (CNNs) or Recurrent Neural Networks (RNNs), to analyze the root cause and influencing factors of the fault. Through the deep analysis, a fault cause analysis report is generated, and a detailed basis is provided for maintenance decision.

In S603, the fault cause analysis report is compared with the historical maintenance data, and the most suitable maintenance scheme is determined by applying a case-based reasoning technique. The case-based reasoning technique finds the most efficient maintenance strategy by analyzing historical cases like faults. This step generates a preliminary maintenance solution, including the type, steps, and timing of maintenance activities.

In S604, further optimization and adjustment of the preliminary maintenance scheme is performed, and predictive maintenance and optimization decision support system techniques are applied. This includes consideration of life cycle, maintenance cost and operating efficiency of the device, as well as risk and safety factors. Through this optimization, a final fault diagnosis and maintenance scheme is generated.

Referring to fig. 8, an energy storage system for an electric vehicle charging station is used for executing the energy storage method for the electric vehicle charging station, and the system includes a data collection module, a demand prediction module, an energy management module, an energy fusion module, a real-time adjustment module, a fault diagnosis module, and a system maintenance module.

The data collection module is used for collecting historical charging data, traffic flow, weather forecast and user behavior modes by adopting a data fusion and distributed database management technology based on the Internet of things technology to generate a comprehensive data set;

The energy management module is used for evaluating the demand trend by utilizing a system dynamic modeling and prediction technology based on the charging demand prediction model, and generating an energy management strategy by combining a decision tree analysis and a linear programming method;

The fault diagnosis module generates a fault cause analysis report by utilizing a real-time monitoring and fault detection technology and combining a mode recognition and deep learning technology based on a real-time adjustment strategy;

The system maintenance module generates fault diagnosis and maintenance schemes by adopting a case-based reasoning technology and a predictive maintenance technology and combining an optimized decision support system based on the fault cause analysis report.

The application of the data collection module enables the system to comprehensively collect and analyze historical charging data, traffic flow, weather forecast and user behavior patterns of the charging station. The generation of the comprehensive data set not only improves the quality and depth of data processing, but also provides a solid data base for accurately predicting the charging requirement and formulating an effective strategy.

The demand prediction module performs time sequence analysis on the charging demand by using a long-term and short-term memory network algorithm, so that a prediction result is more accurate and reliable. This is important for electric vehicle charging stations, as it helps to optimize the resource allocation, planning the operation of the charging facilities in advance, thereby improving service efficiency and user satisfaction.

The energy management module is introduced, the demand trend is estimated through a system dynamic modeling and prediction technology, and an energy management strategy is effectively formulated by combining a decision tree analysis and a linear programming method. Such a strategy can ensure efficient distribution and utilization of energy, reducing waste, while maintaining efficient operation of the system.

The design of the energy fusion module not only reduces the dependence on traditional energy sources, but also promotes the development of the charging station towards a greener and sustainable direction by integrating renewable energy sources such as solar energy, wind energy and the like. According to the optimized energy fusion scheme, the efficiency and the economy of energy utilization are further improved through a particle swarm optimization algorithm and a genetic algorithm technology.

The real-time adjustment module utilizes the internet of things technology and the real-time data stream processing technology, so that the response speed and the adaptability of the system to the current state are improved. This dynamic adjustment strategy enables the system to quickly cope with various changes and potential problems, ensuring continuity and stability of operation.

The combined use of the fault diagnosis module and the system maintenance module not only improves the accuracy of fault detection, but also accelerates the efficiency of fault response and maintenance. The intelligent diagnosis based on deep learning and the maintenance strategy based on case reasoning greatly improve the reliability and the safety of the system.

The present invention is not limited to the above embodiments, and any equivalent embodiments which can be changed or modified by the technical disclosure described above can be applied to other fields, but any simple modification, equivalent changes and modification made to the above embodiments according to the technical matter of the present invention will still fall within the scope of the technical disclosure.

Claims

1. An energy storage method for an electric vehicle charging station, comprising the steps of:

Based on the internet of things technology, collecting historical charging data of a charging station, peripheral traffic flow, weather forecast and a user behavior mode by adopting a data acquisition and network analysis algorithm to generate a comprehensive data set;

Based on the comprehensive data set, adopting a long-short-term memory network algorithm to conduct time sequence prediction of the charging demand, and generating a charging demand prediction model;

Based on the charging demand prediction model, adopting a linear programming algorithm to formulate a charging and discharging strategy of the energy storage equipment, and generating an energy management strategy;

Based on the energy management strategy, integrating solar energy and wind energy output data by adopting an energy scheduling optimization algorithm to generate an optimized energy fusion scheme;

Based on the Internet of things and a remote monitoring technology, dynamically adjusting the energy management strategy according to actual conditions by adopting an adaptive adjustment algorithm, and generating a real-time adjustment strategy;

based on the real-time adjustment strategy, intelligent fault diagnosis and system maintenance are performed by adopting a pattern recognition technology, and a fault diagnosis and maintenance scheme is generated.

2. The energy storage method for electric vehicle charging stations according to claim 1, characterized in that the comprehensive data set comprises charging modes, traffic conditions, climate change and user preference information, the charging demand prediction model is in particular a predictive analysis of differentiated times and regions of charging demand, the energy management strategy comprises a planning of energy distribution, storage opportunities and release opportunities, the optimized energy fusion scheme comprises a strategy of utilizing and storing electric power from renewable energy sources, the fault diagnosis and maintenance scheme is in particular an immediate discovery, diagnosis and maintenance measure of system faults.

3. The energy storage method for an electric vehicle charging station of claim 1, wherein the step of collecting charging station historical charging data, peripheral traffic flow, weather forecast and user behavior patterns using a data collection and network analysis algorithm based on internet of things technology to generate a comprehensive data set comprises the steps of:

based on the internet of things technology, collecting historical charging data of a charging station by using a data fusion and distributed database management system, and generating a historical charging data set;

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

based on a geographic information system, collecting traffic flow and weather forecast data by using a spatial data analysis and traffic pattern recognition technology, and generating a traffic and weather data set;

Integrating the historical charging data set, the user charging behavior analysis report and the traffic and weather data set, and generating an integrated data set by applying a big data integration and analysis technology;

4. The energy storage method for an electric vehicle charging station of claim 1, wherein the step of generating a charging demand prediction model based on the integrated data set by using a long-short term memory network algorithm to predict a time sequence of charging demands comprises:

Determining key factors influencing the charging requirements by using exploratory data analysis and factor analysis methods based on the comprehensive data set, and generating a charging requirement influence factor list;

Based on the charging demand influence factor list, applying a long-short-term memory network algorithm to perform time sequence analysis, and generating a preliminary charging demand prediction report;

Optimizing the preliminary charging demand prediction report, improving the prediction accuracy by using an autoregressive moving average model and a seasonal decomposition technology, and generating an optimized charging demand prediction report;

And adjusting and perfecting a long-and-short-term memory network model based on the optimized charging demand prediction report, and generating a charging demand prediction model.

5. The energy storage method for an electric vehicle charging station of claim 1, wherein the step of formulating a charge-discharge strategy of the energy storage device with a linear programming algorithm based on the charge demand prediction model, the step of generating an energy management strategy specifically comprises:

Based on the charging demand prediction model, estimating future charging demand trend by utilizing a system dynamic modeling and prediction method, and generating a charging demand trend report;

based on the charging demand trend report, a decision tree analysis and linear programming method is applied to design a preliminary charging and discharging strategy, and a preliminary charging and discharging strategy scheme is generated;

performing efficiency analysis on the preliminary charge-discharge strategy scheme, and verifying the actual application effect of the strategy by using a Monte Carlo simulation technology to generate a charge-discharge strategy evaluation report;

Based on the charge-discharge strategy evaluation report and the real-time power grid data, the charge-discharge strategy of the energy storage device is finally determined by using an improved linear programming and optimizing method, and an energy management strategy is generated.

6. The energy storage method for an electric vehicle charging station of claim 1, wherein the step of integrating solar energy and wind energy production data using an energy scheduling optimization algorithm based on the energy management strategy to generate an optimized energy fusion scheme is specifically:

integrating solar energy output data by adopting a data assimilation technology based on the energy management strategy to generate a solar energy data integration report;

based on the energy management strategy, integrating wind energy output data by applying a data assimilation technology to generate a wind energy data integration report;

comprehensively analyzing the solar data integrated report and the wind energy data integrated report, and generating a preliminary energy fusion scheme by applying a particle swarm optimization algorithm;

Evaluating the preliminary energy fusion scheme, and generating an optimized energy fusion scheme by adopting a genetic algorithm optimization technology;

7. The energy storage method for an electric vehicle charging station according to claim 1, wherein the step of dynamically adjusting the energy management policy according to actual conditions by adopting an adaptive adjustment algorithm based on internet of things and a remote monitoring technology to generate a real-time adjustment policy specifically comprises:

Based on the internet of things technology, current state data of a power grid and a charging station are collected by applying a real-time data stream processing technology, and a real-time state data report is generated;

Based on the real-time state data report, analyzing dynamic changes of the power grid and the charging station by using a machine learning algorithm, and generating a system dynamic analysis report;

Combining the system dynamic analysis report and the energy management strategy, and applying a self-adaptive control algorithm to carry out strategy adjustment to generate a preliminary real-time adjustment strategy;

and optimizing the preliminary real-time adjustment strategy, and generating the real-time adjustment strategy by adopting a model predictive control technology.

8. The energy storage method for an electric vehicle charging station of claim 1, wherein based on the real-time adjustment strategy, intelligent fault diagnosis and system maintenance are performed using a pattern recognition technique, and the step of generating a fault diagnosis and maintenance scheme is specifically:

Based on the real-time adjustment strategy, generating a preliminary fault detection report by utilizing a real-time monitoring and fault detection technology;

Based on the preliminary fault detection report, performing fault cause analysis by using a mode identification and deep learning technology, and generating a fault cause analysis report;

Comparing the fault cause analysis report with historical maintenance data, determining a maintenance scheme by using a case-based reasoning technology, and generating a preliminary maintenance scheme;

and optimizing and adjusting the preliminary maintenance scheme, and applying a predictive maintenance and optimization decision support system technology to generate a fault diagnosis and maintenance scheme.

9. An energy storage system for an electric vehicle charging station according to any of claims 1-8, the system comprising a data collection module, a demand prediction module, an energy management module, an energy fusion module, a real-time adjustment module, a fault diagnosis module, a system maintenance module.

10. The energy storage system for an electric vehicle charging station of claim 9, wherein the data collection module collects historical charging data, traffic flow, weather forecast, and user behavior patterns based on internet of things technology using data fusion and distributed database management technology to generate a comprehensive data set;