Service area new energy charging management method and system based on multi-device data analysis

Abstract

The present invention relates to the technical field of charging pile power scheduling, and in particular to a service area new energy charging management method and system based on multi-device data analysis. The method comprises the following steps: obtaining real-time operation monitoring parameters of all charging piles in the service area; performing multi-dimensional feature perception and charging behavior time heat distribution analysis to construct a dynamic charging behavior hotspot map; performing multi-time point power sampling according to the dynamic charging behavior hotspot map, and performing power collaborative path topology evolution to construct a power collaborative path network; performing charging pile power trend prediction and power peak congestion evolution according to the power collaborative path network to generate power peak congestion state characteristics of the charging pile; obtaining new energy vehicle traffic data in the service area, performing average vehicle traffic per unit time calculation, and performing vehicle traffic prediction to obtain a vehicle traffic prediction heat map. The present invention performs charging power scheduling through demand prediction to improve the operating efficiency and stability of charging equipment.

Description

Technical Field

[0001] The present invention relates to the technical field of charging pile power scheduling, and in particular to a service area new energy charging management method and system based on multi-device data analysis. Background Art

[0002] With the rapid development and widespread adoption of new energy vehicles (NEVs), charging infrastructure development has become a key factor in supporting their sustainable development. In particular, in public areas like highway service areas, NEV charging demand is characterized by high frequency and concentration. As key nodes connecting transportation and energy, charging stations at service areas are gradually evolving into a core component of the smart transportation system. However, traditional charging management methods are no longer able to meet the growing demand for vehicle charging and the diverse service scenarios, necessitating the urgent need for more efficient and intelligent management methods.

[0003] In the current application environment, service areas are typically equipped with multiple charging devices from different manufacturers and with varying specifications. Data on operating status, charging efficiency, and user behavior is isolated, lacking unified data management and intelligent analysis capabilities. This "data silo" phenomenon severely restricts the operational efficiency and user experience of charging facilities in service areas. Furthermore, due to the limitations of traditional management methods in real-time data analysis and multi-device collaboration, problems such as high device idle rates, long waiting times, uneven load distribution, and delayed power dispatch are prone to occur, impacting overall energy utilization and service quality.

[0004] Current charging management systems often rely on fixed scheduling rules or manual maintenance plans, lacking in-depth mining and intelligent analysis of multi-device operating data. This makes it difficult to quickly diagnose equipment failures, optimize charging behavior in real time, and dynamically allocate power resources. Therefore, there is an urgent need for a more intelligent new energy charging management method that can break down data barriers between different devices, integrate multi-dimensional operating information, and use intelligent algorithms to rationally allocate charging resources, dynamically monitor equipment operating status, and accurately predict user behavior. This will comprehensively improve the intelligent management of new energy charging in service areas. Summary of the Invention

[0005] In order to solve the above technical problems, the present invention proposes a service area new energy charging management method and system based on multi-device data analysis to solve at least one of the above technical problems.

[0006] To achieve the above objectives, the present invention provides a service area new energy charging management method based on multi-device data analysis, comprising the following steps:

[0007] Step S1: Obtain real-time operating monitoring parameters of all charging piles in the service area; perform multi-dimensional feature perception and charging behavior time heat distribution analysis to construct a dynamic charging behavior hotspot map;

[0008] Step S2: Perform multi-time point power sampling based on the dynamic charging behavior hotspot map, and perform power coordination path topology evolution to build a power coordination path network;

[0009] Step S3: Predicting charging pile power trends and power peak congestion evolution based on the power cooperative path network to generate power peak congestion state characteristics of the charging pile;

[0010] Step S4: Obtain new energy vehicle flow data in the service area, calculate the average flow rate per unit time, and perform traffic flow prediction to obtain a traffic flow prediction heat map;

[0011] Step S5: performing comprehensive charging power demand prediction and pre-charging power intelligent scheduling based on the power peak congestion state characteristics according to the traffic flow prediction heat map, and constructing a charging power intelligent scheduling strategy;

[0012] Step S6: Shield faulty charging piles from the charging power intelligent scheduling strategy, make global power rescheduling decisions, and build an intelligent charging management engine.

[0013] By collecting real-time operating status data (such as power, current, usage frequency, and queue status) from all charging piles, this system establishes a comprehensive understanding of the operating conditions of charging piles in a service area. Through methods such as heat distribution and time period analysis, it identifies high-frequency charging periods and spatially concentrated areas. This provides an accurate spatiotemporal data foundation for subsequent load forecasting and resource allocation, improving overall response efficiency. Through multi-point power sampling, it identifies the synergistic relationships and path evolution patterns between different charging piles in terms of power load. Distributed devices in physical space are constructed into a collaborative network based on logical data relationships, providing a graph structure for scheduling optimization. This network topology can be used for subsequent load peak forecasting and congestion trend simulation, providing structural input for trend analysis. It can proactively identify charging piles likely to experience peak load and queue congestion in future time periods. The extracted "peak congestion status features" can be used as model input to improve the targeted nature of subsequent scheduling. This enables early awareness of future load pressures, facilitating the dispatching system to implement control measures such as preemptive peak shaving and guidance. Traffic flow prediction dynamically links traffic flow with charging demand, avoiding situations where "there are people but no charging piles" or "there are charging piles but no people." Heat maps visually display traffic concentration areas and time periods within the service area, facilitating resource and spatial reallocation. Understanding traffic flow trends and peak hours before formulating a dispatch plan makes power dispatch more forward-looking and accurate. Integrating traffic flow prediction heat maps with congestion state characteristics enables more accurate predictions of charging power demand. Rationally allocate power resources in the dispatch strategy, guiding vehicles to use idle charging piles and alleviating pressure in high-load areas. Effectively reduce charging waiting times and improve user charging experience, while ensuring equipment operating efficiency and grid stability. By shielding faulty pile nodes, interference with the entire system dispatch strategy is avoided. If some piles are unavailable, the system can reconstruct the dispatch plan in real time based on the remaining resources and traffic forecast results. Form an intelligent charging management hub that integrates data perception, predictive analysis, strategy generation, dispatch execution, and fault tolerance.

[0014] In this specification, a service area new energy charging management system based on multi-device data analysis is provided, which is used to execute the service area new energy charging management method based on multi-device data analysis as described above, including:

[0015] The multi-dimensional feature perception module is used to obtain real-time operating monitoring parameters of all charging piles in the service area; it also performs multi-dimensional feature perception and charging behavior time heat distribution analysis to construct a dynamic charging behavior hotspot map;

[0016] The power collaborative path module is used to perform multi-point power sampling based on the dynamic charging behavior hotspot map, and to evolve the power collaborative path topology to build a power collaborative path network;

[0017] The power trend prediction module is used to predict the power trend of charging piles and the evolution of power peak congestion based on the power cooperative path network, and generate the power peak congestion state characteristics of the charging piles;

[0018] The traffic flow prediction module is used to obtain the new energy vehicle traffic data in the service area, calculate the average traffic flow per unit time, and perform traffic flow prediction to obtain a traffic flow prediction heat map;

[0019] A power intelligent scheduling module is used to perform comprehensive charging power demand prediction and pre-charging power intelligent scheduling based on the power peak congestion state characteristics of the vehicle flow prediction heat map, and to build a charging power intelligent scheduling strategy;

[0020] The fault shielding module is used to shield faulty charging piles from the intelligent charging power scheduling strategy, make global power rescheduling decisions, and build an intelligent charging management engine.

[0021] By acquiring real-time operational monitoring parameters for all charging piles, this method can promptly reflect the operating status and usage of charging piles, providing an accurate data foundation for subsequent analysis and decision-making. Multi-dimensional feature perception and temporal heat distribution analysis of charging behavior can identify peak charging times and hotspots, helping to understand user charging habits and needs and optimize charging resource allocation. A dynamic charging behavior hotspot map is constructed, giving managers a visual understanding of charging pile usage and supporting decision-making and resource allocation. Multi-point power sampling based on the dynamic charging behavior hotspot map captures power variations over different time periods, providing a basis for power management. Power coordination path topology evolution is performed to construct a power coordination path network, which helps identify power relationships between charging piles and supports more efficient power scheduling and management. Charging pile power trend prediction using the power coordination path network can proactively identify changes in power demand, helping managers effectively address potential power peak congestion issues. Power peak congestion state signatures for charging piles are generated, allowing managers to quickly identify and take action to prevent user experience degradation caused by insufficient power. Capturing new energy vehicle traffic data within the service area and calculating the average traffic volume per unit time supports charging demand forecasting. Traffic flow forecasting generates a traffic flow prediction heat map, allowing managers to intuitively understand traffic flow changes over different time periods and optimize the distribution and scheduling of charging stations. Based on the traffic flow prediction heat map, comprehensive charging power demand forecasting based on peak power congestion characteristics helps rationally allocate charging resources and reduce peak loads. An intelligent charging power scheduling strategy is established to rationally allocate charging power across different time periods, improve charging station utilization, and reduce user wait times. This intelligent charging power scheduling strategy shields faulty charging stations, ensuring that if a charging station fails, the system automatically adjusts power allocation to minimize user inconvenience. Global power rescheduling decisions and an intelligent charging management engine enable the entire system to quickly adapt to dynamic environments, ensuring the stability and continuity of charging services. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 This is a schematic flow chart of the steps of a service area new energy charging management method based on multi-device data analysis according to the present invention;

[0023] Figure 2 Detailed implementation flow chart of step S1;

[0024] Figure 3 Detailed implementation flow chart of step S2;

[0025] Figure 4 Schematic diagram of the detailed implementation steps of step S3. DETAILED DESCRIPTION

[0026] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0027] This application example provides a service area new energy charging management method and system based on multi-device data analysis. The execution entities of the service area new energy charging management method and system based on multi-device data analysis include, but are not limited to, the following: mechanical equipment, data processing platforms, cloud server nodes, network upload devices, etc. equipped with the system, which can be regarded as general computing nodes of this application. The data processing platform includes, but is not limited to, at least one of: an audio and image management system, an information management system, and a cloud data management system.

[0028] See also Figures 1 to 4 The present invention provides a service area new energy charging management method based on multi-device data analysis, the service area new energy charging management method based on multi-device data analysis includes the following steps:

[0029] Step S1: Obtain real-time operating monitoring parameters of all charging piles in the service area; perform multi-dimensional feature perception and charging behavior time heat distribution analysis to construct a dynamic charging behavior hotspot map;

[0030] Step S2: Perform multi-time point power sampling based on the dynamic charging behavior hotspot map, and perform power coordination path topology evolution to build a power coordination path network;

[0031] Step S3: Predicting charging pile power trends and power peak congestion evolution based on the power cooperative path network to generate power peak congestion state characteristics of the charging pile;

[0032] Step S4: Obtain new energy vehicle flow data in the service area, calculate the average flow rate per unit time, and perform traffic flow prediction to obtain a traffic flow prediction heat map;

[0033] Step S5: performing comprehensive charging power demand prediction and pre-charging power intelligent scheduling based on the power peak congestion state characteristics according to the traffic flow prediction heat map, and constructing a charging power intelligent scheduling strategy;

[0034] Step S6: Shield faulty charging piles from the charging power intelligent scheduling strategy, make global power rescheduling decisions, and build an intelligent charging management engine.

[0035] By collecting real-time operating status data (such as power, current, usage frequency, and queue status) from all charging piles, this system establishes a comprehensive understanding of the operating conditions of charging piles in a service area. Through methods such as heat distribution and time period analysis, it identifies high-frequency charging periods and spatially concentrated areas. This provides an accurate spatiotemporal data foundation for subsequent load forecasting and resource allocation, improving overall response efficiency. Through multi-point power sampling, it identifies the synergistic relationships and path evolution patterns between different charging piles in terms of power load. Distributed devices in physical space are constructed into a collaborative network based on logical data relationships, providing a graph structure for scheduling optimization. This network topology can be used for subsequent load peak forecasting and congestion trend simulation, providing structural input for trend analysis. It can proactively identify charging piles likely to experience peak load and queue congestion in future time periods. The extracted "peak congestion status features" can be used as model input to improve the targeted nature of subsequent scheduling. This enables early awareness of future load pressures, facilitating the dispatching system to implement control measures such as preemptive peak shaving and guidance. Traffic flow prediction dynamically links traffic flow with charging demand, avoiding situations where "there are people but no charging piles" or "there are charging piles but no people." Heat maps visually display traffic concentration areas and time periods within the service area, facilitating resource and spatial reallocation. Understanding traffic flow trends and peak hours before formulating a dispatch plan makes power dispatch more forward-looking and accurate. Integrating traffic flow prediction heat maps with congestion state characteristics enables more accurate predictions of charging power demand. Rationally allocate power resources in the dispatch strategy, guiding vehicles to use idle charging piles and alleviating pressure in high-load areas. Effectively reduce charging waiting times and improve user charging experience, while ensuring equipment operating efficiency and grid stability. By shielding faulty pile nodes, interference with the entire system dispatch strategy is avoided. If some piles are unavailable, the system can reconstruct the dispatch plan in real time based on the remaining resources and traffic forecast results. Form an intelligent charging management hub that integrates data perception, predictive analysis, strategy generation, dispatch execution, and fault tolerance.

[0036] In the embodiment of the present invention, see Figure 1 , is a flowchart of the steps of a service area new energy charging management method based on multi-device data analysis of the present invention. In this example, the steps of the service area new energy charging management method based on multi-device data analysis include:

[0037] Step S1: Obtain real-time operating monitoring parameters of all charging piles in the service area; perform multi-dimensional feature perception and charging behavior time heat distribution analysis to construct a dynamic charging behavior hotspot map;

[0038] In this embodiment, a real-time monitoring system for all charging piles within the service area is identified to ensure the extraction of necessary operating parameters. These parameters typically include the charging pile ID, current voltage, current, charging status (idle, charging, faulty), number of users, and charging time. Data is collected from the monitoring system every 5 minutes to ensure data timeliness and accuracy. Real-time data is periodically extracted from the monitoring systems of all charging piles using an API or data collection tool and stored in a database. The data format is ensured to be consistent for subsequent analysis. A database table is created containing fields such as "Charging Pile ID," "Current Voltage," "Current Current," "Charging Status," "Number of Users," and "Timestamp" to facilitate subsequent data query and analysis. The captured real-time data is validated to ensure there are no duplicates, missing values, or outliers. Records outside a reasonable range (e.g., voltage values ​​outside the normal range) are removed to maintain data integrity. The voltage range is set to 100V to 400V; any values ​​outside this range are marked as abnormal and recorded for subsequent analysis. Based on the collected real-time data, multi-dimensional features are extracted. These include, but are not limited to, charging pile voltage fluctuations, charging power, changes in the number of users, and charging duration. These features will be used for subsequent dynamic analysis. The average voltage and current for each charging pile over the past hour are calculated, and the change in the number of users in each time period is recorded. The extracted feature data is aggregated and summarized by time period (e.g., every 30 minutes) to form a comprehensive feature matrix. This ensures that the feature data within each time period reflects the dynamic state of the charging pile. For each charging pile, the average voltage, average current, and number of charging users in every 30 minutes are calculated for subsequent analysis. Data analysis techniques (such as time series analysis or cluster analysis) are applied to analyze the multi-dimensional features to identify dynamic patterns in charging behavior. This process helps understand charging pile usage and user behavior. Using time series analysis, peak charging periods and their corresponding charging pile usage are identified, and the analysis results are recorded. Based on the aggregated feature data, the popularity of charging behavior in different time periods is calculated. This can be comprehensively scored using indicators such as the number of users, charging duration, and charging power to identify periods with high popularity. Set the heat scoring formula to: Heat = Number of users × Average charging power × Charging duration. Calculate the heat value for each time period. Visualize the calculated heat values ​​to create a dynamic charging behavior heat map. The heat map should intuitively display charging station usage during different time periods, helping managers quickly identify peak periods. Use a heat map tool to map heat values ​​onto a timeline, using different colors to indicate high and low heat levels, facilitating decision-making and resource allocation.

[0039] Step S2: Perform multi-time point power sampling based on the dynamic charging behavior hotspot map, and perform power coordination path topology evolution to build a power coordination path network;

[0040] In this embodiment, based on the dynamic charging behavior heat map constructed in the previous step, peak usage periods for charging piles are identified. These periods generally correspond to the time periods when user charging demand is most concentrated. This ensures that the heat map accurately reflects the dynamic changes in charging behavior. Assuming that the heat map shows that 08:00-09:00 and 18:00-19:00 are peak periods every day, these periods are used as key periods for power sampling. During the identified peak periods, power data is collected from each charging pile's real-time monitoring system. This data should include information such as the actual charging power, charging status, and number of users at each charging pile at different time points. Power data is collected every minute, and the power value of each charging pile is recorded during the peak period. Assume that between 08:00 and 09:00, the power of charging pile A is recorded as 50 kW, the power of charging pile B is recorded as 60 kW, and so on. Graph theory methods are used to analyze the power coordination paths between charging piles. Each charging pile is considered a node in the graph, and the power flow relationship is considered as the edge between the nodes. Select an appropriate algorithm (such as the Dijkstra algorithm or the minimum spanning tree algorithm) to construct the network. Set the power flow relationship between adjacent charging piles as the edge weight. If the power flow of charging pile A during peak hours affects charging pile B, establish a connection in the graph. Generate a power coordination path network for the charging piles based on the collected power data. Identify the relationships between charging piles, determine which charging piles influence each other during peak hours, and the direction of their power flow. If the usage frequency of charging pile A during peak hours affects the power demand of charging pile B, establish a connection in the network and record the power flow information. After constructing the basic power coordination path network, perform topology evolution to dynamically adjust the network structure based on real-time power data changes. This ensures that the network can adapt to changes in charging demand over time. If the power demand of charging pile C increases dramatically during a certain period, adjust the connections in the network to ensure that charging pile C receives sufficient power support and record this change. The constructed power coordination path network and its topology evolution results are recorded in a database, and the network structure is visualized using visualization tools. This ensures that managers can intuitively visualize the coordination relationships and power flows between charging piles. Generate a network diagram showing the connections between charging stations and the direction of power flow, helping managers identify charging capacity and potential bottlenecks during peak hours.

[0041] Step S3: Predicting charging pile power trends and power peak congestion evolution based on the power cooperative path network to generate power peak congestion state characteristics of the charging pile;

[0042] In this embodiment, based on the previous power collaborative path network, the power data of the current charging pile is collected. This data should include historical charging power, number of users, charging time and other characteristics to facilitate power trend prediction.

[0043] Set the data collection cycle to hourly power data for the past week and extract relevant features. Ensure that each charging station record includes timestamp, average power, maximum power, and number of charging users.

[0044] Select a forecast model:

[0045] Select an appropriate power trend forecasting model based on the data characteristics. Common models include time series forecasting models (such as ARIMA and SARIMA) and machine learning models (such as LSTM and random forest). The selected model should be able to handle the characteristics of time series data.

[0046] The LSTM model was chosen because it can capture long-term dependencies when processing time series data and is suitable for predicting the power change trend of charging piles.

[0047] Model training and validation:

[0048] Use historical data to train the selected prediction model. Divide the data into training and test sets to ensure that the model can learn the changing pattern of charging pile power and verify it on the test set.

[0049] The model is trained using charging pile power data from the past two weeks to ensure that the root mean square error (RMSE) of the model during prediction is lower than the set threshold to ensure prediction accuracy.

[0050] To perform power trend forecasting:

[0051] The trained model is used to predict the charging pile power in future time periods, and the predicted value for each time period is recorded. This will provide basic data for the subsequent evolution of power peak congestion.

[0052] Predict the power demand of each charging pile for the next 24 hours and record the predicted power value for each time period. Based on the power trend prediction results, identify potential peak power congestion at the charging pile during peak hours. Set a congestion threshold; when the demand on a charging pile exceeds its maximum power capacity, it is considered congested. Set the maximum power of a charging pile to 100 kW. If the demand for a charging pile is predicted to reach 120 kW within a certain time period, the charging pile is marked as congested. Use time series analysis to dynamically monitor changes in charging pile power demand and analyze changes in congestion status over different time periods. Record the congestion status and its evolution trend for each charging pile. If, during peak hours (e.g., 6:00 PM to 7:00 PM), the power demand of charging pile A increases from 80 kW to 120 kW, record this evolution and analyze possible causes (e.g., concentrated charging). Summarize the identified congestion states and generate peak power congestion signatures for the charging piles. These signatures include information such as the time of congestion, duration, the ID of the charging pile involved, and its power demand. Record which charging piles are congested during a specific peak period, and summarize their common characteristics, such as the average congestion duration of 30 minutes and the number of charging piles involved.

[0053] Step S4: Obtain new energy vehicle flow data in the service area, calculate the average flow rate per unit time, and perform traffic flow prediction to obtain a traffic flow prediction heat map;

[0054] In this embodiment, the source of new energy vehicle flow data is determined, typically including sensors, cameras, or traffic monitoring systems installed in service areas. These devices should be able to monitor the number of new energy vehicles entering and exiting the service area in real time. Set a five-minute interval to collect flow data from the traffic monitoring system, and ensure the equipment is functioning properly to ensure data accuracy. Use an API or data collection tool to periodically extract new energy vehicle flow data from the monitoring system and store it in a database. Ensure the data format is consistent to facilitate subsequent processing. Create a database table containing fields such as "timestamp," "vehicle type," "entry and exit direction," and "traffic volume" to facilitate subsequent analysis and querying. During the data collection process, validate the collected flow data. Check for missing values, duplicate records, or outliers, and perform necessary cleaning. Set a reasonable flow range to filter out unreasonable data (such as negative values ​​or vehicles exceeding the maximum carrying capacity). If the flow rate within a certain time period exceeds expectations, mark it as an anomaly and record it. Divide the time period into multiple windows (such as hourly or 30-minute intervals) based on analysis requirements to facilitate segmented statistics of the flow data. Ensure that the data within each time window is complete. Set a 30-minute time window and record traffic flow data within each time period. Calculate the average of the traffic flow data per unit time for each time window. Divide the traffic flow within each window by the window duration to obtain the traffic flow per unit time. For a 30-minute time window, if the total traffic flow recorded within that window is 300 vehicles, the traffic flow per unit time is 300 vehicles / 0.5 hours = 600 vehicles / hour. Select an appropriate traffic flow forecasting model based on the characteristics of the traffic flow data per unit time. Common models include ARIMA models, time series analysis, and machine learning models (such as LSTM). The selected model should be able to handle the characteristics of time series data. The ARIMA model is selected because it performs well in handling seasonal and trend data, making it suitable for traffic flow forecasting. Train the selected forecasting model using historical traffic flow data. Split the data into training and test sets to ensure that the model can learn the changing patterns of traffic flow. Validate the model on the test set to assess the accuracy of the forecast. Use the last three months of hourly traffic flow data for training, ensuring that the model's root mean square error (RMSE) during prediction is below a set threshold. Apply the trained model to predict traffic flow for future time periods, generating traffic flow predictions and recording the predictions for each time period. Predict traffic flow changes over the next 24 hours, recording the predicted values ​​for each time period. For example, if a traffic flow of 500 vehicles is expected during a certain time period, organize the predicted traffic flow data into a format suitable for heat map display. This can be done by combining the time periods and the corresponding predicted traffic flows to construct a matrix. Create a two-dimensional array with rows representing time periods and columns representing traffic flows for easy visualization.Use data visualization tools (such as Tableau or Matplotlib) to generate a heat map from the traffic flow forecast data. Ensure that the heat map clearly displays traffic flow distribution over different time periods. Use different shades of color in the heat map to represent high and low traffic flow, helping managers quickly identify peak and low periods.

[0055] Step S5: performing comprehensive charging power demand prediction and pre-charging power intelligent scheduling based on the power peak congestion state characteristics according to the traffic flow prediction heat map, and constructing a charging power intelligent scheduling strategy;

[0056] In this example, the traffic flow prediction heatmap and previously extracted power peak congestion state features are combined to integrate data for comprehensive charging power demand forecasting. This data must cover the actual power demand of charging piles and future traffic flow fluctuations. The data timeframe is set to the next 24 hours, and the predicted traffic flow, historical charging power data, and current charging pile availability for each time window are recorded. Based on the characteristics of the integrated data, an appropriate prediction model is selected for comprehensive charging power demand forecasting. Common models include linear regression, decision trees, and random forests. The selected model should be able to handle multi-dimensional feature data and consider the relationship between traffic flow and charging power. The random forest model is selected because it performs well with complex feature relationships and can effectively handle nonlinear relationships. The selected prediction model is trained using historical data. The data is divided into training and test sets to ensure that the model can learn the changing patterns of charging demand. The model is then validated on the test set to assess prediction accuracy. The model is trained using traffic flow and charging power data from the past three months, ensuring that the root mean square error (RMSE) of the model predictions is below a set threshold (e.g., 15%). The trained model is used to predict the comprehensive charging power demand for future time periods. The predicted power demand values ​​for each time period are recorded, providing foundational data for subsequent intelligent scheduling decisions. Charging power demand is forecasted for the next 24 hours, with certain peak periods (such as 8:00 AM to 9:00 AM) expected to reach 100 kW. Based on the predicted comprehensive charging power demand, an intelligent charging power scheduling strategy is designed to ensure efficient allocation of charging resources during high-demand periods. The scheduling strategy should consider the maximum load capacity of charging piles, user queues, and charging demand priorities. During peak periods, the maximum charging power of charging piles is set at 100 kW. If the predicted charging demand exceeds this value, power is allocated preferentially to users with the longest queues. A dynamic scheduling algorithm (such as an optimal allocation algorithm or a greedy algorithm) is used to schedule charging piles in real time, dynamically adjusting charging power allocation based on predicted demand. This ensures that charging piles are used most efficiently during peak charging demand periods. If charging demand is predicted to be 150 kW between 8:00 AM and 9:00 AM, and there are only two charging stations, 75 kW can be allocated to each station to prevent overloading of a single station. After implementing the scheduling strategy, monitor its effectiveness in real time, collecting user feedback and charging station operational data. Ensure that the scheduling strategy effectively improves charging efficiency and adjust the strategy promptly to address changes. Monitor user wait times and charging success rates. If user wait times are excessively long during a specific period, reassess the charging power allocation strategy.

[0057] Step S6: Shield faulty charging piles from the charging power intelligent scheduling strategy, make global power rescheduling decisions, and build an intelligent charging management engine.

[0058] In this embodiment, a real-time monitoring system integrated with charging piles automatically identifies charging pile faults by monitoring parameters (such as voltage, current, and temperature) and fault log data. Fault identification rules are established to facilitate real-time detection. Fault criteria are set: if a charging pile's current fluctuation exceeds ±20% or its temperature exceeds 80°C within a certain period, it is marked as faulty. Once a faulty charging pile is identified, its status is immediately updated to "faulty," and the time of the fault, charging pile ID, and fault type are recorded. This data is used to adjust the subsequent scheduling strategy. If charging pile ID "C001" is determined to be faulty at 08:15, it is marked, and the fault cause (such as overheating) and its impact range are recorded. A faulty charging pile shielding mechanism is implemented in the intelligent charging power scheduling strategy to ensure that these charging piles are not considered in scheduling decisions. This prevents faulty charging piles from being assigned to users, reducing charging risks for users. The scheduling algorithm is updated to exclude faulty charging piles when calculating available charging piles, thereby reallocating power to other functioning charging piles. The global power scheduling strategy is analyzed based on the current charging pile usage status and fault conditions. Ensure efficient allocation of charging resources even after a faulty charging pile is disabled. If there are originally four available charging piles but one fails, the power allocation capacity of the remaining three piles needs to be reassessed. Use a dynamic scheduling algorithm (such as an optimal allocation algorithm, a greedy algorithm, or linear programming) for global power rescheduling. Dynamically adjust the power allocation plan based on real-time charging demand and available charging piles. For example, if the predicted total charging demand during peak hours is 150 kW and the total power of available charging piles is 200 kW, prioritize power allocation based on user queues. During rescheduling, establish a real-time monitoring and feedback mechanism to ensure timely access to scheduling results and user feedback. Dynamically adjust the scheduling strategy based on user charging status and wait time. Monitor actual user wait time and charging pile utilization during a specific period. If a charging pile's utilization is excessive and user wait times are prolonged, readjust its power allocation. Record the results of global scheduling decisions in a database and generate a detailed scheduling report. The report should include the execution of the scheduling strategy, user feedback, and charging pile utilization efficiency to facilitate subsequent analysis and optimization. Generate a report that includes "time period," "charging demand forecast," "actual power distribution," and "user wait time" to help managers evaluate the effectiveness of scheduling strategies and make necessary adjustments. Design the architecture of the intelligent charging management engine to ensure it can process monitoring data, fault identification, scheduling decisions, and user feedback in real time. The engine should include a data input module, a fault detection module, a scheduling decision module, and a data output module. Ensure that the engine can receive data streams from charging stations and output scheduling results and user notifications in real time. Integrate the various modules to ensure smooth data flow, and perform functional testing using real data to verify the engine's effectiveness and stability.Use simulated data for testing to observe the engine's response to different failure scenarios and ensure that it can quickly adjust scheduling strategies.

[0059] In this embodiment, refer to Figure 2 , is a flowchart of the detailed implementation steps of step S1. In this embodiment, the detailed implementation steps of step S1 include:

[0060] Obtaining real-time operating monitoring parameters of all charging piles in the service area; calculating the voltage and current parameters of the charging piles based on the real-time operating monitoring parameters of the charging piles to obtain the electrical characteristics of each charging pile;

[0061] Performing statistics on the usage frequency of the real-time operation monitoring parameters of the charging pile to extract the usage frequency parameters of the charging pile;

[0062] Extracting the charging time and idle period of the real-time operation monitoring parameters of the charging pile;

[0063] Performing multi-dimensional feature perception on the usage frequency parameters of the electrical characteristic charging pile, the charging time and the idle period to construct a multi-dimensional feature matrix;

[0064] Perform time stamp synchronization on the multi-dimensional feature matrix and perform time vectorization decomposition to construct a rasterized time window for charging behavior;

[0065] Each charging behavior is extracted based on the rasterized time window of the charging behavior, and the time heat distribution analysis of the charging behavior is performed to construct a dynamic charging behavior hotspot map.

[0066] In this embodiment, the source of real-time monitoring data for the charging pile is determined, typically including parameters such as voltage, current, charging status, and usage frequency. This data can be obtained through the charging pile's communication interface (such as a REST API or MQTT protocol). Real-time data collection for the charging pile is set to occur every 30 seconds to ensure data timeliness and accuracy. A unique identifier for each charging pile is obtained through the configuration interface to facilitate subsequent data processing and analysis. A data collection program is written to periodically collect the real-time operating monitoring parameters of the charging pile and store the data in a database. The data format is ensured to be consistent for subsequent analysis. A database table is created with fields such as "charging pile ID," "voltage," "current," "charging status," and "timestamp" to ensure that this information is recorded during each data collection. The collected real-time monitoring parameters are validated to ensure data integrity and validity. Irrational outliers (such as voltage less than 0 or current exceeding the rated range) are removed. The normal voltage range is set to 100V to 400V and the normal current range is set to 0A to 100A. Any values ​​outside these ranges should be marked as abnormal and recorded. Based on the collected real-time monitoring parameters, the electrical characteristics of each charging pile are calculated. Electrical characteristics include charging power (P = U * I) and energy consumption. If the charging pile voltage is 220V and the current is 16A, the charging power is 220V * 16A = 3520W. Record this power value and its timestamp. Calculate the energy consumption of each charging pile based on the charging time and charging power. Use the formula: Energy (kWh) = Power (kW) * Time (h). For a one-hour charge, the energy consumption is 3520W / 1000 * 1 = 3.52 kWh. Store this information for later analysis. Based on the real-time monitoring parameters of the charging piles, calculate the usage frequency of each charging pile—that is, the number of times the charging pile is used within a certain period. Set a statistical period (such as daily or hourly). Count the number of charges at each charging pile over the past 24 hours and record the usage frequency of each charging pile. Aggregate the statistical results into a database to generate a charging pile usage frequency report. Sort by usage frequency to identify the most popular charging piles. Generate a table containing the charging pile ID and the corresponding usage frequency to record charging pile usage for later analysis. Using time series analysis, analyze the usage trends of charging stations and identify peak and off-peak periods. Use a moving average to calculate the hourly usage frequency and create a trend chart for visual analysis. Based on real-time monitoring parameters, extract the start and end times of each charge and calculate the charging duration. Record the duration of each charging session. If a charging station starts charging at 08:00 and ends at 09:00, the charging duration is one hour. This duration and related time information are stored. Based on the charging duration, identify idle periods at the charging station.Idle periods are defined as periods of time when a charging station is not in use. The idle periods for each charging station are recorded. If a charging station is not used between 9:00 AM and 10:00 AM, this period is recorded as idle. The extracted charging station electrical characteristics, usage frequency, charging duration, and idle periods are integrated into a multidimensional feature matrix. Each row represents a charging station, and each column represents a feature. Columns in the feature matrix can include "charging station ID," "voltage," "current," "usage frequency," "charging duration," and "idle period" to ensure data comprehensiveness. The feature matrix is ​​normalized to eliminate dimensionality effects between different features and ensure accuracy in subsequent analysis. Z-score normalization is used to adjust the mean of each feature to 0 and the standard deviation to 1 to ensure data adaptability. Timestamps in the multidimensional feature matrix are synchronized to ensure that all feature data is analyzed using the same time base, eliminating the impact of time differences. Timestamps for all charging stations are standardized to UTC time, and data from different time periods are interpolated to ensure temporal continuity. Vectorize timestamp data to generate time series data for subsequent analysis. Time can be divided into fixed time windows (e.g., every 5 minutes or every hour). Divide a day into 288 5-minute time windows, and aggregate charging behavior data within each time window. Record the processed time window data in a database to form a time series of charging behavior for subsequent analysis and visualization. Generate a time window data table that records the number of charges and total charging duration within each time window to facilitate subsequent heat distribution analysis. Based on the time window data, extract each charging activity, including information such as the start and end time, and charging station ID, for subsequent analysis. Record the charging station ID and charging duration within each time window to form a charging behavior record table. Perform heat distribution analysis on the extracted charging behavior data, calculating a heat value based on the frequency of charging station use and charging duration. The heat value can be weighted by the number of charges. Set the heat value calculation formula to: Heat value = frequency of use × average charging duration. Record the heat value for each charging station. Based on the calculated heat values, construct a dynamic charging behavior hotspot map. Use visualization tools to display the heat distribution of different charging stations to facilitate decision-making. Generate a heat map to show the heat distribution of each charging station, using different colors to indicate high and low heat levels, helping to identify charging station utilization efficiency and room for improvement.

[0067] In this embodiment, refer to Figure 3 , is a flowchart of the detailed implementation steps of step S2. In this embodiment, the detailed implementation steps of step S2 include:

[0068] Calculate the power of each charging behavior based on the dynamic charging behavior hotspot map to generate the power characteristics of each charging pile;

[0069] Performing power sampling at multiple time points on the charging power characteristics to construct charging power curves for multiple charging piles;

[0070] Perform discrete Fourier transform on the charging power curves of multiple charging piles to generate charging power frequency domain data;

[0071] Perform spectrum peak detection on the charging power frequency domain data and mark multiple spectrum peaks;

[0072] Identifying the peak timing shift characteristics of the spectrum peaks and marking high-frequency charge and discharge fluctuation nodes;

[0073] The power collaborative path topology evolves according to the high-frequency charging and discharging fluctuation nodes, and a power collaborative path network is constructed.

[0074] In this example, the charging behavior records for each charging station are extracted from the previously generated dynamic charging behavior heat map, including information such as the charging start time, end time, and charging station ID. This information is used to calculate the power consumption of each charging session. For a charging station with a charging start time of 08:00 and an end time of 09:00, and a charging power of 3.5 kW, the energy consumption for this charging session is calculated as 3.5 kW × 1 h = 3.5 kWh. Based on the extracted charging behavior data, the charging power characteristics of each charging station are calculated sequentially. The power characteristic calculation should take into account the voltage and current parameters of different charging periods, typically using the formula P = U × I. If the voltage of a charging station at 08:30 is 220V and the current is 16A, the charging power at that time is calculated to be 220V × 16A = 3520W. The power characteristics of each charging session are recorded along with their timestamps. The calculated power characteristics of each charging session are stored in a database to ensure data structure and facilitate subsequent analysis. Each record should include information such as the charging station ID, charging time, and power characteristics. Create a database table storing fields such as "Charging Station ID," "Charging Time," and "Charging Power" for subsequent querying and analysis. Extract power data from multiple charging stations at different time points from the stored charging power characteristics to form a power dataset. Ensure that the data covers different time periods and charging stations to obtain comprehensive information on power variations. Set the time period to one day and extract hourly power data for each charging station, recording the power characteristics of each charging station at different times of the day. Sort the extracted power data chronologically and generate charging power curves for each charging station. These curves should demonstrate the power variation trend over time. Use a line chart to display the power variation of each charging station over a 24-hour period, with time on the X-axis and power on the Y-axis, ensuring clear visibility of charging peaks and troughs. Perform a discrete Fourier transform (DFT) on the charging power curve data for multiple charging stations to analyze the frequency domain characteristics of the charging power. The DFT converts time domain signals into frequency domain signals, revealing hidden frequency components. Set the data length of each charging station's power curve to 1024 points to ensure that the transformed data effectively captures the frequency domain characteristics. Use DFT to transform the power curve of each charging pile to generate frequency domain data, which will show the performance of each frequency component during the charging process. Use the standard DFT algorithm to transform the power data of each charging pile, and record the amplitude and phase information of each frequency point for subsequent analysis. Select an appropriate spectrum peak detection method, usually using a threshold method or a derivative-based peak detection algorithm to identify significant peaks in the spectrum, which represent the key frequency components in the charging power change. Set the peak detection threshold to an amplitude greater than 0.5 to ensure that only significant spectrum peaks are marked. Perform peak detection on the frequency domain data of each charging pile and mark all significant peaks in the spectrum and their corresponding frequencies.Record the amplitude and location of each peak for subsequent analysis. If a peak with a frequency of 60 Hz and an amplitude of 10 dB is detected in the spectrum of a charging station, record this information. Perform time-series offset analysis on the detected spectrum peaks to identify changing trends during the charging process. This process will reveal the dynamic characteristics of charging behavior. Observe the changes in the peaks in the time series, record the time of each peak and its changes, and identify potential charging and discharging fluctuation nodes. Mark high-frequency charging and discharging fluctuation nodes. These nodes typically indicate high-frequency power fluctuations at the charging station, which may be related to changes in charging demand or the operating status of the device. If peaks at 60 Hz and its multiples are found to change frequently in the spectrum, mark these nodes as high-frequency charging and discharging fluctuation nodes and record their occurrence time and amplitude. Based on the identified high-frequency charging and discharging fluctuation nodes, analyze the power coordination paths between multiple charging stations. Identify the mutual influence and collaborative working relationship between different charging stations during the charging process. If the usage frequency of a charging station is similar to that of other charging stations during peak hours, these charging stations are considered to have a collaborative relationship, and the characteristics of their collaborative paths are recorded. The identified collaborative paths are integrated to construct a power collaborative path network between charging piles. This network should reflect the relationships and interactions between charging piles. Graph theory is used to construct a network diagram, with nodes representing charging piles and edges representing power collaborative relationships. This ensures that the network clearly reflects the collaborative characteristics of each charging pile. The constructed power collaborative path network is analyzed to identify key nodes and edges within the network, and optimization recommendations are made to improve the overall efficiency of the charging piles. The network's connectivity is analyzed to identify the most active charging piles, and recommendations are provided to optimize the layout and configuration of charging piles to improve charging efficiency.

[0075] In this embodiment, the specific steps of performing power cooperative path topology evolution based on high-frequency charge and discharge fluctuation nodes and constructing a power cooperative path network are as follows:

[0076] Multi-cycle trend encoding is performed on high-frequency charging and discharging fluctuation nodes to generate charging power fluctuation change chains for different charging piles;

[0077] Perform power fluctuation coupling detection on the charging power fluctuation chain to extract and identify the power fluctuation coupling relationship between charging piles;

[0078] The power fluctuation coupling relationship is used to mine the power correlation changes of multiple charging piles to generate the power linkage law between charging piles;

[0079] Identify nearby associated charging piles based on the charging power fluctuation chain;

[0080] According to the power linkage rules between charging piles, the potential power coordination paths of adjacent related charging piles are analyzed to extract the power coordination path of each charging pile;

[0081] Analyze the power conflict situation of the power linkage between charging piles to obtain the power conflict situation between charging piles;

[0082] Predict power flow based on power conflict between charging piles;

[0083] Based on the power flow direction, the power cooperative path of each charging pile is subjected to power cooperative path topology evolution to construct a power cooperative path network.

[0084] In this embodiment, relevant data is extracted from previously identified high-frequency charging and discharging fluctuation nodes, including the time, amplitude, and frequency characteristics of each node. This data will be used to analyze charging pile power fluctuations. The charging and discharging fluctuations of multiple charging piles are recorded over different time periods, ensuring that the data covers a specific time period (e.g., 24 hours) and includes specific timestamps for each node. Trend analysis methods are used to encode high-frequency fluctuation nodes, typically using a moving average or exponential smoothing method, to capture fluctuation trends and cyclical variations. A window size of 6 hours is set, and the power fluctuation trend of each charging pile within this time window is calculated using a moving average method to generate encoded fluctuation data. Based on this encoded fluctuation data, a charging power fluctuation chain is generated for each charging pile. This chain should reflect the trend and fluctuation characteristics of charging power over time. The trend values ​​of each charging pile over a specific time period are recorded and formed into a time series to ensure that the data clearly demonstrates the dynamic characteristics of power fluctuations. Appropriate coupling detection methods, such as mutual information or correlation coefficient analysis, are selected to identify power fluctuation coupling relationships between charging piles. These methods can quantify the mutual influence between charging piles. The mutual information threshold is set to 0.5 to ensure that only significant fluctuation coupling relationships are detected. Coupling detection is performed on the power fluctuation chains of different charging piles. The coupling relationship between each pair of charging piles is calculated, and charging piles with significant coupling relationships are identified. The coupling coefficient between charging piles A and B is recorded. If its value exceeds a set threshold, the two charging piles are considered to have a power fluctuation coupling relationship. Cluster analysis or association rule mining methods are used to analyze the power fluctuation coupling relationship between charging piles and extract the power linkage patterns between charging piles. The K-means clustering algorithm is used to cluster the power coupling data and identify the linkage characteristics of the charging piles. By analyzing the clustering results, the power correlation changes between charging piles are identified and the power linkage patterns of charging piles in different time periods are extracted. If charging piles A and B are found to have similar usage frequencies during peak hours, their correlation is recorded and the common characteristics of their power fluctuations are analyzed. Based on the discovered power linkage patterns, adjacent charging piles are identified. These charging piles often have similar geographical locations or power fluctuations. Geographic Information System (GIS) data is used to determine the distance between charging piles, and charging piles within a distance of less than 500 meters are marked as adjacent. Analyze the identified adjacent charging piles, recording their power characteristics and coupling relationships for subsequent analysis and decision-making. Generate a table containing the IDs, power characteristics, and coupling relationships of the adjacent charging piles to help identify potential collaborative charging opportunities. Based on the identified adjacent, related charging piles, use graph theory to analyze the power coordination paths between the charging piles. Ensure that the path analysis reflects the power flow relationships between the charging piles. Use the Dijkstra algorithm to calculate the shortest path for each charging pile and identify the optimal path for power flow.

[0085] The power coordination paths of adjacent charging piles are analyzed to extract the power coordination path characteristics of each charging pile, ensuring that the data reflects the dynamic characteristics of power flow. The power flow path from charging pile A to charging pile B is recorded to ensure detailed and accurate path information. A conflict detection algorithm is used to analyze power conflicts between charging piles and identify potential power conflicts during peak charging periods. The conflict detection threshold is set to the maximum power limit. If multiple charging piles simultaneously request power exceeding this limit, a conflict is recorded. A conflict analysis is performed on the power flows of the identified charging piles, evaluating the power requests of each charging pile during peak charging periods to identify potential conflicts. If charging pile A requests 50 kW at a certain moment and charging pile B also requests 40 kW, and the total system power limit is 80 kW, a conflict is recorded. A time series prediction model (such as an ARIMA model or a long short-term memory (LSTM) network) is used to predict the power flow between charging piles. Selecting an appropriate model can improve prediction accuracy. The LSTM model is selected because it can handle long-term dependencies in time series data and is suitable for analyzing dynamic changes in charging power. Use historical charging station power data to train the selected prediction model to ensure that the model can learn the power flow pattern between charging stations. Use the power data from the past 30 days for training to ensure that the model can capture the patterns and changes in charging peaks.

[0086] The trained model is used to predict future power flows, identifying the direction and intensity of power flow at each charging pile. It is predicted that within the next hour, the power flow to charging pile A will be 60 kW, and the power flow to charging pile B will be 40 kW. Data accuracy is ensured and timestamps are recorded. An appropriate topology evolution method, typically dynamic network analysis, is selected to ensure that changes in the power coordination paths between charging piles are reflected. A network reconstruction algorithm is used to dynamically adjust the connections between charging piles based on the predicted power flows and historical data. The topology of the power coordination paths for each charging pile is evolved based on the predicted power flows, ensuring that the paths adapt to environmental changes and usage demands. If the power requests for a charging pile increase significantly during peak hours, its coordination paths with other charging piles are dynamically adjusted to ensure system stability and efficiency. The topology evolution results are recorded in a database and generated as a report for subsequent analysis and decision-making. A topology diagram of the charging pile coordination paths is generated, showing the connections and power flow paths between charging piles, to assist managers in optimization and adjustment.

[0087] In this embodiment, refer to Figure 4 , is a flowchart of the detailed implementation steps of step S3. In this embodiment, the detailed implementation steps of step S3 include:

[0088] Identify the idle state of the charging piles according to the real-time operation monitoring parameters of the charging piles, and extract the idle available charging piles and occupied charging piles;

[0089] Analyze the time-series charging power changes of occupied charging piles and generate time-series charging power change characteristics;

[0090] Calculating the number of available idle charging piles and performing idle time distribution prediction to obtain a predicted value of idle charging pile time distribution;

[0091] The charging pile power trend is predicted based on the idle charging pile time distribution prediction value and the time series charging power change characteristics, and the charging pile power trend prediction status for the future time period is generated;

[0092] The power peak congestion evolution of the charging pile power trend prediction state is performed according to the power cooperative path network to generate a power peak congestion state feature of the charging pile.

[0093] In this embodiment, current operating parameters are extracted from the real-time monitoring system of charging piles, including the charging status (idle or occupied), charging start and end times, and other information for each charging pile. This ensures the timeliness and accuracy of the data for subsequent analysis. Charging pile status data is collected from the system every 30 seconds, and the status of each charging pile (e.g., "idle" or "charging") is recorded. The collected charging pile status data is classified into "idle and available" and "occupied." Charging piles are labeled with corresponding attributes based on their current status. If a charging pile is currently displayed as "charging," it is marked as "occupied"; otherwise, it is marked as "idle and available." The status information of each charging pile is recorded, including the timestamps of idle and occupied times. Data related to occupied charging piles is extracted from the charging pile status records, primarily including charging power, charging duration, and status change time. This provides basic data for analyzing charging power variations. The power variation information of each occupied charging pile during the charging process is recorded to ensure complete data coverage of the charging cycle. Time series analysis of the charging power of occupied charging piles is performed to calculate the power variation characteristics. Statistical methods (such as moving average and variance) can be used to analyze power trends over time. Set a time window (e.g., every 5 minutes) and calculate the average charging power of each occupied charging station within that window, recording its changes. Calculate the number of currently idle charging stations based on the charging station status records. Ensure data accuracy for subsequent idle time distribution analysis. Count the number of charging stations currently in the "Idle" state. If there are currently 10 idle stations, record this number. To forecast the time distribution of idle charging stations, use time series analysis methods such as ARIMA models or exponential smoothing to predict future idle time distribution. Analyze idle time data from the past two weeks to predict the idle time distribution of charging stations within the next 24 hours and calculate the expected idle time. Record the forecast results in a database and generate a forecast report on the idle charging station time distribution to facilitate subsequent management and decision-making. Generate a forecast report recording the expected number of idle charging stations in each time period to help managers allocate and optimize charging stations. Based on the time-series charging power variation characteristics of occupied charging piles, select an appropriate power trend prediction model (such as linear regression or LSTM) to predict charging pile power trends. The LSTM model is selected because it is suitable for processing time series data and can effectively capture the temporal dependence of power variations. Use historical charging power data to train the selected prediction model to ensure that the model can learn the patterns of power variation. Use training and validation sets to evaluate the model to ensure accuracy. Use charging power data from the past 30 days for training to verify the model's predictive capabilities and ensure that the error is within an acceptable range. Apply the trained model to predict charging pile power trends for future time periods to generate a projected power variation state.Predict charging power changes within the next 6 hours and record the predicted power values ​​for each time period for subsequent analysis and optimization. Analyze the power collaborative path network based on the power trend prediction status of the charging piles to identify potential power peak congestion situations. Ensure that the network analysis can reflect the mutual influence between charging piles. Use graph theory to construct a power collaborative path network between charging piles, where nodes represent charging piles and edges represent power flow relationships. Based on the analysis results of the power collaborative path network, identify the power requests of charging piles during peak periods and mark possible congestion states. If it is found that multiple charging piles request power in the same time period that exceeds the maximum carrying capacity of the system, it will be recorded as a power peak congestion state, and the time of occurrence and scope of impact will be marked.

[0094] In this embodiment, step S4 includes the following steps:

[0095] Obtaining new energy vehicle traffic data in a service area; dividing the new energy vehicle traffic data into time windows and extracting traffic data in multiple time windows;

[0096] The traffic flow data of multiple time windows are averaged per unit time, and the average traffic flow per unit time of each time window is extracted;

[0097] Performing dynamic traffic flow differentiation analysis based on the average traffic flow per unit time, and extracting traffic flow differentiation features of multiple time windows;

[0098] Identify the current cycle situation based on the new energy vehicle traffic data in the service area;

[0099] Obtain the service area's historical traffic flow record logs; match the service area's historical traffic flow record logs to the corresponding period according to the current time period, analyze traffic flow changes, and generate periodic change patterns;

[0100] Traffic flow prediction is performed on the differentiated characteristics of traffic flow according to the periodic variation law to obtain a traffic flow prediction heat map.

[0101] In this embodiment, the sources of new energy vehicle flow data are determined, typically including the service area's traffic monitoring system, sensors, cameras, and traffic flow counting equipment. Ensure data integrity and accuracy for subsequent analysis. Set a 5-minute interval to collect traffic flow data from the traffic monitoring system, recording the number of new energy vehicles entering the service area during each time period. By developing a data collection program or using an existing API, periodically collect new energy vehicle flow data and store it in a database. Ensure a consistent data format for subsequent processing. Create a database table with fields such as "timestamp" and "traffic flow" to ensure that this information is recorded during each data collection. Verify the collected traffic flow data to ensure data integrity and absence of outliers. Remove duplicate records and unreasonable outliers (such as negative values ​​or traffic exceeding expectations). Set the acceptable range for traffic flow to 0 to 1000 vehicles; any values ​​outside this range should be marked as anomalies and recorded. Divide time into multiple windows (such as hourly or half-hourly) based on analysis requirements to facilitate segmented analysis of traffic flow data. Ensure data integrity within each time window. Set up a 30-minute time window and record traffic flow data for each time period. Organize the data within the divided time windows and extract traffic flow data for each time window. Ensure that the data for each window reflects the traffic flow situation for that time period. Calculate the total traffic flow for each time window and record the start and end times of each window. Calculate the average traffic flow per unit time for each time window. Divide the traffic flow per unit time by the window duration to obtain the traffic flow per unit time. For a 30-minute time window, if the traffic flow per unit time is 300 vehicles, the traffic flow per unit time is 300 vehicles / 0.5 hour = 600 vehicles / hour. Record the calculated average traffic flow per unit time in the database to generate a traffic flow statistics report for subsequent analysis. Generate a table containing "Time Window" and "Average Traffic Flow Per Unit Time" to record the average traffic flow for each time window. Select an appropriate differential analysis method, such as a t-test or analysis of variance, to compare the average traffic flow per unit time for different time windows and identify differential characteristics of traffic flow. Set the significance level to 0.05 to ensure that statistically significant differences in traffic flow can be identified. Perform differential analysis on the average traffic flow per unit time of multiple time windows to identify time periods with significant changes in traffic flow. Record the analysis results and mark the time windows with significant differences. If significant differences are found in traffic flow between the morning peak and evening peaks, record the relevant information of these time windows. Use periodic analysis methods, such as Fourier transform or autocorrelation analysis, to identify the traffic flow cycle at the current time to ensure that the periodic characteristics of traffic flow can be captured. Use the autocorrelation function to analyze traffic flow data and identify the frequency of periodic fluctuations. Perform periodic analysis on the traffic flow data at the current time to identify the periodic characteristics of traffic flow.Record the analysis results and mark any periodic features. If the analysis results indicate 24-hour periodic fluctuations in traffic flow, record the periodic features and their associated parameters. Extract historical traffic flow logs for the service area from the database, ensuring that the data covers a sufficiently long period for periodic change analysis. Extract traffic flow records from the past six months to ensure data completeness and accuracy. Match the service area's historical traffic flow logs to the corresponding period based on the current time period and analyze the relationship between the historical data and the current period. If the currently identified period is 24 hours, extract the corresponding 24-hour data from the historical records for analysis and compare traffic flow changes. Select an appropriate forecasting model, such as linear regression or a time series forecasting model (such as ARIMA or LSTM), to forecast traffic flow based on periodic fluctuations to determine future traffic flow conditions. Select an ARIMA model for forecasting to ensure that it captures trends and seasonal variations in historical data. Use historical traffic flow data to train the selected forecasting model to ensure that the model learns the patterns of traffic flow changes. Evaluate the model's accuracy using training and validation sets. Use traffic flow data from the past three months for training and validation to ensure that the forecast error is within an acceptable range. Use the trained model to predict traffic flow for future time periods, generate traffic flow forecasts, and record the forecast results for each time period. Forecast traffic flow changes over the next 24 hours and record the forecast values ​​for each time period. Generate a traffic flow heat map based on the forecast results to visualize traffic flow distribution over different time periods, helping managers quickly identify peak and low periods. Use a heat map tool to display traffic flow changes over the next 24 hours, using different colors to represent different traffic flow levels, to facilitate decision-making.

[0102] In this embodiment, the specific steps of step S5 are:

[0103] Identifying user charging queues based on real-time operation monitoring parameters of the charging piles;

[0104] Statistics are collected on the queuing time of users charging, and the total time spent in and out of the queue is calculated to obtain the total queue length.

[0105] Charging demand analysis is performed based on the total queue length and traffic flow prediction heat map to generate user charging demand characteristics;

[0106] Performing a comprehensive charging power demand forecast on the user's charging demand characteristics based on the power peak congestion state characteristics to generate comprehensive charging power demand forecast data;

[0107] Based on the comprehensive charging power demand forecast data, intelligent charging power scheduling is carried out in advance to build an intelligent charging power scheduling strategy.

[0108] In this embodiment, user charging status data, including the current usage status of each charging station (e.g., idle, charging, queued, etc.), is extracted from the real-time monitoring system for charging stations. This ensures data accuracy and timeliness to identify user charging queues. Charging station status information is collected every five minutes, recording the queue status, current number of users, and queue time for each station. A queue identification method based on status monitoring is used to analyze the usage status of each charging station and identify users in the queue. A threshold is set to determine whether a user is in the queue (e.g., if the charging station status is "queued" and there are users waiting). If a charging station status is "charging" and there are subsequently users waiting, these users are recorded as queued, and a queue list is created. Identified user charging queue data is recorded in a database, including information such as user ID, queue time, and charging station ID, providing basic data for subsequent analysis. A table containing "user ID," "charging station ID," and "queue time" is generated to ensure data structure and queryability. Queue time statistics are collected for user charging queues, and the queue duration for each user is calculated. The queue length can be calculated by recording the time a user enters the queue and the time they start charging. If a user enters the queue at 08:00 and starts charging at 08:15, their queue time is 15 minutes. The queue time for all users is counted to calculate the total queue length. This is the sum of all users' queue times and is recorded for later analysis. If, within a certain time period, five users queue for 15 minutes, 10 minutes, 20 minutes, 5 minutes, and 30 minutes, respectively, the total queue length is 15 + 10 + 20 + 5 + 30 = 80 minutes. Based on the total queue length and the traffic flow prediction heat map, demand analysis methods such as regression analysis or time series analysis are used to analyze the characteristics of user charging demand. This ensures that changing trends in demand can be identified. Combined with peak-hour data from the traffic flow prediction heat map, the characteristics of user charging demand during peak hours are analyzed. A comprehensive analysis of the collected queue time and traffic flow data is performed to extract user charging demand characteristics, including peak-hour demand volume and duration. If the total queue length during a peak period is 80 minutes and the vehicle volume is 200 vehicles, the charging demand characteristics for this period are recorded and a demand analysis report is generated. Based on the previously identified power peak congestion state characteristics, the relationship between peak user charging demand and the power availability of charging piles is analyzed to make a comprehensive prediction. If power peak congestion is recorded for a certain period, the gap between charging demand and power supply capacity during this period is analyzed. Select an appropriate prediction model, such as a multivariate linear regression model or a machine learning algorithm (such as a random forest or LSTM), to make a comprehensive prediction of user charging demand and generate comprehensive charging power demand forecast data. Use historical charging demand data and current charging demand characteristics for model training to ensure that the model can capture the complex patterns of charging demand.Use the trained model to predict future charging demand and generate comprehensive charging power demand forecast data, ensuring that the data reflects future demand trends. Forecast charging demand for the next hour and record the predicted power demand value for each time period. Based on the comprehensive charging power demand forecast data, design an intelligent scheduling strategy to optimize the power allocation of charging piles to ensure that charging resources are properly scheduled during periods of high demand. During peak charging demand periods, prioritize charging power allocation to users with longer queues. Implement the designed intelligent charging power scheduling strategy and monitor its effectiveness. Monitor charging pile usage and user queues in real time to ensure that the scheduling strategy effectively improves charging efficiency. Monitor changes in user queue times after implementation; if queue times decrease, the scheduling strategy is effective.

[0109] In this embodiment, the specific steps of step S6 are:

[0110] Analyze abnormal voltage fluctuations on the multi-dimensional feature matrix and extract abnormal voltage fluctuation data;

[0111] Identify abnormal current thermal drift, abnormal plug-in and plug-out frequency, and thermal runaway trigger records based on a multi-dimensional feature matrix;

[0112] Predict charging pile failures based on abnormal voltage fluctuation data, abnormal current thermal drift, abnormal plugging and unplugging frequency, and thermal runaway trigger records, and mark faulty charging piles.

[0113] According to the faulty charging pile, the charging power intelligent scheduling strategy is used to shield the faulty charging pile, make global power rescheduling decisions, and build an intelligent charging management engine.

[0114] In this embodiment, voltage data is extracted from a previously generated multi-dimensional feature matrix, ensuring that the data includes voltage readings for each charging pile over different time periods. This ensures the timeliness and accuracy of the data for anomaly analysis. The data collection cycle is set to every second, and voltage data is acquired from the charging piles. The voltage value at each charging pile at a specific time point is recorded. Statistical analysis methods (such as Z-score analysis or the IQR method) are used to detect abnormal voltage fluctuations. A reasonable threshold is set to identify voltage fluctuations outside the normal range. The Z-score threshold is set to ±3. If the Z-score of a charging pile voltage reading exceeds this threshold, it is marked as abnormal. Detected abnormal voltage data is extracted and recorded, including the time of the anomaly, charging pile ID, and abnormal voltage value. This data will be used for subsequent fault prediction. If a charging pile records a voltage of 450V at 08:15 (the normal range is 100V-400V), the time and abnormal voltage value are recorded. Current data is extracted from the multi-dimensional feature matrix and analyzed for current fluctuations at the charging pile. This ensures data integrity for thermal drift detection. Set the normal current range to 0A-100A. If current fluctuations exceeding this range are recorded repeatedly, it is flagged as abnormal thermal excursion. Count the plugging and unplugging frequency of charging piles, recording the number of times each charging pile is plugged and unplugged within a certain period of time. Frequent plugging and unplugging can cause equipment damage or failure. If a charging pile is plugged and unplugged more than five times within an hour, record the charging pile ID and plugging and unplugging frequency, and flag it as abnormal. Monitor charging pile temperature data to identify any triggers for thermal runaway risks. Set a temperature threshold (such as 80°C). If the threshold is reached, record the event. If the temperature of a charging pile exceeds 80°C during charging, record the event and correlate it with other abnormal data. Select an appropriate fault prediction model, such as a decision tree, random forest, or support vector machine (SVM), to comprehensively analyze multiple features, including abnormal voltage, abnormal current thermal excursion, and plugging frequency. The random forest model is selected because it can handle multidimensional data and has good classification performance. Train the selected model using historical fault data to ensure that it can learn the difference between fault characteristics and normal conditions. Divide the data into training and test sets for model validation. Use failure data from the past year for training to verify the model's accuracy and recall to ensure its effectiveness in fault detection. Apply the trained model to predict faults based on the current status of charging piles and mark charging piles with potential failures. Record the prediction results for each charging pile. If the model predicts that the charging pile with ID "C001" is at risk of failure, record the charging pile and its failure probability. Identify and record charging piles marked as faulty to ensure that they can be blocked in a timely manner during scheduling decisions. Avoid assigning faulty charging piles to users. Generate a list of faulty charging piles, including the charging pile ID, failure type, and predicted probability.Based on the identification of faulty charging piles, the existing intelligent charging power scheduling strategy is adjusted to ensure that remaining charging resources are effectively allocated even when a faulty charging pile is blocked. If a charging pile fails during peak hours, its load is redistributed to other available charging piles to ensure overall charging efficiency is not affected. Based on the blocking results of the faulty charging pile, a global power rescheduling decision is made, ensuring that the system can maintain efficient operation even in the event of a fault. The load capacity and estimated charging demand of each available charging pile are calculated, and power is reallocated to minimize user wait time. The architecture of the intelligent charging management engine is designed, including a data input module (receiving real-time monitoring data), a fault detection module, a scheduling decision module, and a data output module (generating scheduling results). This ensures that the engine can process monitored data in real time and quickly make fault detection and scheduling decisions. The various modules are integrated to ensure smooth data flow, and functional testing is conducted using real data to verify the engine's effectiveness and stability. Testing is conducted using simulated data to observe the engine's response to different fault conditions and ensure that it can quickly adjust the scheduling strategy. During engine operation, the scheduling effectiveness is monitored, and user feedback and system performance data are collected for continuous optimization. Record users' charging waiting time and charging success rate, analyze the effectiveness of scheduling strategies, and make adjustments based on feedback.

[0115] In this embodiment, a service area new energy charging management system based on multi-device data analysis is provided, which is used to execute the service area new energy charging management method based on multi-device data analysis as described above, including:

[0116] The multi-dimensional feature perception module is used to obtain real-time operating monitoring parameters of all charging piles in the service area; it also performs multi-dimensional feature perception and charging behavior time heat distribution analysis to construct a dynamic charging behavior hotspot map;

[0117] The power collaborative path module is used to perform multi-point power sampling based on the dynamic charging behavior hotspot map, and to evolve the power collaborative path topology to build a power collaborative path network;

[0118] The power trend prediction module is used to predict the power trend of charging piles and the evolution of power peak congestion based on the power cooperative path network, and generate the power peak congestion state characteristics of the charging piles;

[0119] The traffic flow prediction module is used to obtain the new energy vehicle traffic data in the service area, calculate the average traffic flow per unit time, and perform traffic flow prediction to obtain a traffic flow prediction heat map;

[0120] A power intelligent scheduling module is used to perform comprehensive charging power demand prediction and pre-charging power intelligent scheduling based on the power peak congestion state characteristics of the vehicle flow prediction heat map, and to build a charging power intelligent scheduling strategy;

[0121] The fault shielding module is used to shield faulty charging piles from the intelligent charging power scheduling strategy, make global power rescheduling decisions, and build an intelligent charging management engine.

[0122] By acquiring real-time operational monitoring parameters for all charging piles, this method can promptly reflect the operating status and usage of charging piles, providing an accurate data foundation for subsequent analysis and decision-making. Multi-dimensional feature perception and temporal heat distribution analysis of charging behavior can identify peak charging times and hotspots, helping to understand user charging habits and needs and optimize charging resource allocation. A dynamic charging behavior hotspot map is constructed, giving managers a visual understanding of charging pile usage and supporting decision-making and resource allocation. Multi-point power sampling based on the dynamic charging behavior hotspot map captures power variations over different time periods, providing a basis for power management. Power coordination path topology evolution is performed to construct a power coordination path network, which helps identify power relationships between charging piles and supports more efficient power scheduling and management. Charging pile power trend prediction using the power coordination path network can proactively identify changes in power demand, helping managers effectively address potential power peak congestion issues. Power peak congestion state signatures for charging piles are generated, allowing managers to quickly identify and take action to prevent user experience degradation caused by insufficient power. Capturing new energy vehicle traffic data within the service area and calculating the average traffic volume per unit time supports charging demand forecasting. Traffic flow forecasting generates a traffic flow prediction heat map, allowing managers to intuitively understand traffic flow changes over different time periods and optimize the distribution and scheduling of charging stations. Based on the traffic flow prediction heat map, comprehensive charging power demand forecasting based on peak power congestion characteristics helps rationally allocate charging resources and reduce peak loads. An intelligent charging power scheduling strategy is established to rationally allocate charging power across different time periods, improve charging station utilization, and reduce user wait times. This intelligent charging power scheduling strategy shields faulty charging stations, ensuring that if a charging station fails, the system automatically adjusts power allocation to minimize user inconvenience. Global power rescheduling decisions and an intelligent charging management engine enable the entire system to quickly adapt to dynamic environments, ensuring the stability and continuity of charging services.

[0123] The present invention is therefore intended to be illustrative and non-restrictive in all respects, with the scope of the invention being defined by the appended claims rather than the foregoing description, and all changes that come within the meaning and range of equivalents of the application documents are intended to be embraced therein.

[0124] The foregoing description is intended only to provide specific embodiments of the present invention, which will enable those skilled in the art to understand and implement the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown herein, but is to be construed in the widest possible manner consistent with the principles and novel features disclosed herein.

Claims

1. A service area new energy charging management method based on multi-device data analysis, characterized in that: The following steps are involved: Step S1: Obtain real-time operating monitoring parameters of all charging piles in the service area; It also conducts multi-dimensional feature perception and charging behavior time heat distribution analysis to build a dynamic charging behavior hotspot map; Step S2: Perform multi-time point power sampling based on the dynamic charging behavior hotspot map, and perform power coordination path topology evolution to build a power coordination path network; Step S3: Predicting charging pile power trends and power peak congestion evolution based on the power cooperative path network to generate power peak congestion state characteristics of the charging pile; Step S4: Obtain new energy vehicle flow data in the service area, calculate the average flow rate per unit time, and perform traffic flow prediction to obtain a traffic flow prediction heat map; Step S5: performing comprehensive charging power demand prediction and pre-charging power intelligent scheduling based on the power peak congestion state characteristics according to the traffic flow prediction heat map, and constructing a charging power intelligent scheduling strategy; Step S6: Shield faulty charging piles from the charging power intelligent scheduling strategy, make global power rescheduling decisions, and build an intelligent charging management engine; Among them, the specific steps of step S2 are: Calculate the power of each charging behavior based on the dynamic charging behavior hotspot map to generate the power characteristics of each charging pile; Performing power sampling at multiple time points on the charging power characteristics to construct charging power curves for multiple charging piles; Perform discrete Fourier transform on the charging power curves of multiple charging piles to generate charging power frequency domain data; Perform spectrum peak detection on the charging power frequency domain data and mark multiple spectrum peaks; Identifying the peak timing shift characteristics of the spectrum peaks and marking high-frequency charge and discharge fluctuation nodes; Evolve the power cooperative path topology based on high-frequency charging and discharging fluctuation nodes and build a power cooperative path network; The specific steps of performing power cooperative path topology evolution according to high-frequency charge and discharge fluctuation nodes and constructing a power cooperative path network are as follows: Multi-cycle trend encoding is performed on high-frequency charging and discharging fluctuation nodes to generate charging power fluctuation change chains for different charging piles; Perform power fluctuation coupling detection on the charging power fluctuation chain to extract and identify the power fluctuation coupling relationship between charging piles; The power fluctuation coupling relationship is used to mine the power correlation changes of multiple charging piles to generate the power linkage law between charging piles; Identify nearby associated charging piles based on the charging power fluctuation chain; According to the power linkage rules between charging piles, the potential power coordination paths of adjacent related charging piles are analyzed to extract the power coordination path of each charging pile; Analyze the power conflict situation of the power linkage between charging piles to obtain the power conflict situation between charging piles; Predict power flow based on power conflict between charging piles; Based on the power flow direction, a power cooperative path topology evolution is performed on the power cooperative path of each charging pile to construct a power cooperative path network; Among them, the specific steps of step S3 are: Identify the idle state of the charging piles according to the real-time operation monitoring parameters of the charging piles, and extract the idle available charging piles and occupied charging piles; Analyze the time-series charging power changes of occupied charging piles and generate time-series charging power change characteristics; Calculating the number of available idle charging piles and performing idle time distribution prediction to obtain a predicted value of idle charging pile time distribution; The charging pile power trend is predicted based on the idle charging pile time distribution prediction value and the time series charging power change characteristics, and the charging pile power trend prediction status for the future time period is generated; The power peak congestion evolution of the charging pile power trend prediction state is performed according to the power cooperative path network to generate a power peak congestion state feature of the charging pile.

2. The service area new energy charging management method based on multi-device data analysis according to claim 1 is characterized in that: The specific steps of step S1 are: Obtaining real-time operating monitoring parameters of all charging piles in the service area; calculating the voltage and current parameters of the charging piles based on the real-time operating monitoring parameters of the charging piles to obtain the electrical characteristics of each charging pile; Performing statistics on the usage frequency of the real-time operation monitoring parameters of the charging pile to extract the usage frequency parameters of the charging pile; Extracting the charging time and idle period of the real-time operation monitoring parameters of the charging pile; Performing multi-dimensional feature perception on the usage frequency parameters of the electrical characteristic charging pile, the charging time and the idle period to construct a multi-dimensional feature matrix; Perform time stamp synchronization on the multi-dimensional feature matrix and perform time vectorization decomposition to construct a rasterized time window for charging behavior; Each charging behavior is extracted based on the rasterized time window of the charging behavior, and the time heat distribution analysis of the charging behavior is performed to construct a dynamic charging behavior hotspot map.

3. The service area new energy charging management method based on multi-device data analysis according to claim 1 is characterized in that: The specific steps of step S4 are: Obtaining new energy vehicle traffic data in a service area; dividing the new energy vehicle traffic data into time windows and extracting traffic data in multiple time windows; The traffic flow data of multiple time windows are averaged per unit time, and the average traffic flow per unit time of each time window is extracted; Performing dynamic traffic flow differentiation analysis based on the average traffic flow per unit time, and extracting traffic flow differentiation features of multiple time windows; Identify the current cycle situation based on the new energy vehicle traffic data in the service area; Obtain the service area's historical traffic flow record logs; match the service area's historical traffic flow record logs to the corresponding period according to the current time period, analyze traffic flow changes, and generate periodic change patterns; Traffic flow prediction is performed on the differentiated characteristics of traffic flow according to the periodic variation law to obtain a traffic flow prediction heat map.

4. The service area new energy charging management method based on multi-device data analysis according to claim 1 is characterized in that: The specific steps of step S5 are: Identifying user charging queues based on real-time operation monitoring parameters of the charging piles; Statistics are collected on the queuing time of users charging, and the total time spent in and out of the queue is calculated to obtain the total queue length. Charging demand analysis is performed based on the total queue length and traffic flow prediction heat map to generate user charging demand characteristics; Performing a comprehensive charging power demand forecast on the user's charging demand characteristics based on the power peak congestion state characteristics to generate comprehensive charging power demand forecast data; Based on the comprehensive charging power demand forecast data, intelligent charging power scheduling is carried out in advance to build an intelligent charging power scheduling strategy.

5. The service area new energy charging management method based on multi-device data analysis according to claim 1 is characterized in that: The specific steps of step S6 are: Analyze abnormal voltage fluctuations on the multi-dimensional feature matrix and extract abnormal voltage fluctuation data; Identify abnormal current thermal drift, abnormal plug-in and plug-out frequency, and thermal runaway trigger records based on a multi-dimensional feature matrix; Predict charging pile failures based on abnormal voltage fluctuation data, abnormal current thermal drift, abnormal plugging and unplugging frequency, and thermal runaway trigger records, and mark faulty charging piles. According to the faulty charging pile, the charging power intelligent scheduling strategy is used to shield the faulty charging pile, make global power rescheduling decisions, and build an intelligent charging management engine.

6. A service area new energy charging management system based on multi-device data analysis, characterized in that: The method for managing new energy charging in a service area based on multi-device data analysis according to claim 1 comprises: The multi-dimensional feature perception module is used to obtain real-time operating monitoring parameters of all charging piles in the service area; it also performs multi-dimensional feature perception and charging behavior time heat distribution analysis to construct a dynamic charging behavior hotspot map; The power collaborative path module is used to perform multi-point power sampling based on the dynamic charging behavior hotspot map, and to evolve the power collaborative path topology to build a power collaborative path network; The power trend prediction module is used to predict the power trend of charging piles and the evolution of power peak congestion based on the power cooperative path network, and generate the power peak congestion state characteristics of the charging piles; The traffic flow prediction module is used to obtain the new energy vehicle traffic data in the service area, calculate the average traffic flow per unit time, and perform traffic flow prediction to obtain a traffic flow prediction heat map; A power intelligent scheduling module is used to perform comprehensive charging power demand prediction and pre-charging power intelligent scheduling based on the power peak congestion state characteristics of the vehicle flow prediction heat map, and to build a charging power intelligent scheduling strategy; The fault shielding module is used to shield faulty charging piles from the intelligent charging power scheduling strategy, make global power rescheduling decisions, and build an intelligent charging management engine.

Images