Shared charging cabinet charging control method and system based on artificial intelligence

Abstract

The invention relates to the technical field of charging control, in particular to a shared charging cabinet charging control method and system based on artificial intelligence. The method comprises the following steps: acquiring real-time monitoring state data of the shared charging cabinet; performing real-time charging load calculation on the real-time monitoring state data of the shared charging cabinet, and performing short-term load trend evolution so as to generate short-term load trend characteristics; current charge pal storage monitoring is carried out on the shared charging cabinet, and charging shortage priority analysis is carried out, so that the charging shortage priority of each charge pal is obtained; dynamic charging load power distribution is carried out on the charging shortage priority of each power bank according to the short-term load trend characteristics, and a dynamic charging load distribution strategy is constructed; multi-period statistics of power bank taking amount is carried out on the historical operation log of the shared charging cabinet, and a power utilization demand fluctuation curve is constructed. The efficient and rapid charging control method for the shared charging cabinet is realized, so that the method adapts to various user demand scenes.

Description

Technical Field

[0001] The present invention relates to the field of charging control technology, and in particular to a charging control method and system for a shared charging cabinet based on artificial intelligence. Background Art

[0002] With the continuous development of mobile Internet technology, mobile phones have become an indispensable tool for modern people. However, the limited battery life of mobile phones often troubles users, especially when they are out and about. To solve this problem, shared power banks have emerged to provide users with convenient charging services. However, how to effectively manage and control the charging process of shared charging cabinets has always been a difficult problem that needs to be solved urgently.

[0003] Traditional shared charging cabinet systems usually adopt manual management and user autonomous operation. When the demand for power banks of regional users increases, traditional shared charging cabinet systems often cannot meet the needs of a large number of users, and cannot optimize the charging efficiency of the charging cabinet for each power bank by adjusting the charging method. Therefore, there is a situation where the charging efficiency is low and cannot adapt to high user demand. In order to meet the growing charging needs of users and improve the intelligence level of shared charging cabinets, an intelligent charging cabinet charging control method is urgently needed. Summary of the invention

[0004] In order to solve the above-mentioned technical problems, the present invention proposes a charging control method and system for a shared charging cabinet based on artificial intelligence to solve at least one of the above-mentioned technical problems.

[0005] To achieve the above object, the present invention provides a charging control method for a shared charging cabinet based on artificial intelligence, comprising the following steps: Step S1: obtaining the real-time monitoring status data of the shared charging cabinet; performing real-time charging load calculation on the real-time monitoring status data of the shared charging cabinet, and performing short-term load trend evolution, thereby generating short-term load trend characteristics; Step S2: monitoring the current storage of power banks in the shared charging cabinet and performing a priority analysis of charging shortages, thereby obtaining the priority of each power bank; Step S3: dynamically allocate charging load power to each power bank according to the charging shortage priority according to the short-term load trend characteristics, and build a dynamic charging load allocation strategy; Step S4: Obtain the historical operation log of the shared charging cabinet; perform multi-period statistics on the power bank usage in the historical operation log of the shared charging cabinet, perform multi-period demand fluctuation analysis, and construct a power demand fluctuation curve; Step S5: forecasting regional electricity demand based on the electricity demand fluctuation curve, and then dynamically adjusting the charging power to generate a dynamic demand control strategy; Step S6: Conduct in-depth collaborative calculation and analysis on the dynamic demand regulation strategy and the dynamic charging load distribution strategy, and conduct adaptive charging control mining to build an intelligent charging control model.

[0006] The present invention monitors the status data in real time to calculate the charging load, which is helpful to understand the current load situation of the charging cabinet, analyze the evolution of short-term load trends, make predictions and plans for future charging needs, improve the utilization efficiency of the charging cabinet, perform priority analysis based on the current power bank storage monitoring results, ensure the rationality and efficiency of the power bank charging priority, dynamically adjust the charging load of the power bank according to the short-term load trend characteristics, optimize the utilization of charging resources, build an intelligent dynamic charging load distribution strategy, improve charging efficiency and user satisfaction, and perform multi-period demand fluctuation analysis through historical operation logs, which is helpful to understand the changing law of the power bank usage and provide a basis for charging resource allocation. Prediction is made based on the power demand fluctuation curve to achieve dynamic charging power adjustment, improve the adaptability and flexibility of the charging cabinet, generate control strategies for different demand situations, optimize charging resource allocation, and improve the overall efficiency of the charging cabinet. Through deep collaborative calculation and adaptive charging control mining, an intelligent charging control model is built to improve the management intelligence level of shared charging cabinets, optimize dynamic demand control strategies and charging load distribution strategies, and achieve efficient energy utilization and charging service quality.

[0007] Preferably, step S1 comprises the following steps: Step S11: Obtaining real-time monitoring status data of the shared charging cabinet; Step S12: Divide the real-time monitoring status data of the shared charging cabinet into sliding time series windows to obtain multiple time window monitoring status data; Step S13: Calculate the real-time charging load for the monitoring status data of multiple time windows to obtain the real-time charging load for each time window; Step S14: performing a time series load change analysis on the real-time charging loads in all time windows to generate time series load change data; Step S15: Perform short-term load trend evolution on the time-series load change data to generate short-term load trend characteristics.

[0008] The present invention obtains real-time monitoring data of shared charging cabinets, including the real-time charging status, connection status, power information, etc. of the charging cabinets, which provides instant basic data for subsequent steps, so that the charging control system can make accurate decisions based on the latest data. The real-time monitoring data is divided according to time windows, such as dividing the data by hours or minutes, which helps to analyze the data more carefully. The data in each time window can be processed and analyzed independently, so as to better understand the changing trend of the charging load. The real-time charging load calculation is performed for the monitoring data of each time window. By calculating the charging load at the current moment, the system can timely understand the strength of the charging demand, providing an important basis for subsequent optimization and scheduling. The real-time charging load of all time windows is analyzed to reveal the change pattern of the load over time. This analysis can help identify the periodic changes of the load, peak hours and other characteristics, and provide support for the formulation of more effective charging control strategies. The analysis is based on the time series load change data to generate short-term load trend characteristics. These characteristics can help predict the future load change trend, so that the system can make adjustments in advance to more efficiently cope with fluctuations in charging demand.

[0009] Preferably, step S2 comprises the following steps:. Step S21: monitoring the current power bank storage in the shared charging cabinet and identifying the status data of the current power bank storage; Step S22: Calculate the battery capacity of the current stored power bank status data to obtain the battery capacity value of the stored power bank; Step S23: Calculate the remaining battery capacity of the currently stored power bank status data, and extract the remaining battery capacity of each power bank; Step S24: Calculating the charging capacity requirement of each power bank based on the battery capacity value of the stored power bank, so as to generate the charging capacity requirement of each power bank; Step S25: Perform a charging shortage priority analysis based on the charging demand of each power bank, so as to obtain the charging shortage priority of each power bank.

[0010] The present invention monitors the status data of the power bank currently stored in the shared charging cabinet, including the number, type, status and other information of the power bank. This helps the system understand the current available resources and provide basic information for subsequent charging scheduling. According to the status data of the power bank currently stored, the battery capacity value of each power bank is calculated. It can help the system evaluate the overall capacity of available charging resources and provide a basis for the allocation of charging needs. For each power bank, the residual capacity of its battery is calculated. Understanding the power status of each power bank can help the system arrange charging tasks in a targeted manner to avoid insufficient charging. Based on the battery capacity value and the residual capacity of the battery, the charging capacity requirement of each power bank is calculated. This helps the system to arrange charging tasks reasonably, ensure that each power bank can get the appropriate amount of charge, and improve the charging efficiency. According to the charging capacity requirement of each power bank, a charging shortage priority analysis is performed. Determine the charging priority of each power bank to ensure that when resources are limited, those power banks with urgent charging needs can be given priority to improve the charging efficiency of the system.

[0011] Preferably, step S3 specifically comprises the following steps: Step S31: predicting the load peak based on the short-term load trend characteristics, thereby obtaining charging cabinet load peak prediction data; Step S32: Calculate the charging load of the currently stored power bank status data to obtain the charging load data of each power bank; Step S33: performing a dynamic priority analysis on the charging shortage priority of each power bank based on the charging load data of each power bank, thereby obtaining a dynamic charging load priority of each power bank; Step S34: dynamically allocate charging load power to each power bank according to the charging cabinet load peak prediction data, and construct a dynamic charging load allocation strategy.

[0012] The present invention analyzes and predicts short-term load trend characteristics to obtain peak prediction data of the charging cabinet load, which helps the system prepare resources in advance to meet possible high load demands in the future, thereby avoiding resource shortages during the charging process. The charging load data of each power bank is calculated based on the currently stored power bank status data, so that the contribution of each power bank to the overall load of the charging cabinet can be accurately evaluated, which helps to reasonably allocate charging resources. Based on the charging load data of each power bank, a dynamic priority analysis is performed to determine the charging shortage priority of each power bank. This analysis can adjust the charging priority according to real-time conditions to ensure optimal utilization of resources. According to the peak prediction data of the charging cabinet load and the dynamic charging load priority of each power bank, a dynamic charging load power allocation strategy is formulated. By intelligently allocating charging power, each power bank is properly charged, while ensuring the efficient operation of the overall charging process.

[0013] Preferably, the specific steps of step S4 are: Step S41: Obtain the historical operation log of the shared charging cabinet; Step S42: Identify the power bank access behavior in the historical operation log of the shared charging cabinet, and extract all the power bank access behavior data; Step S43: performing statistics on the usage of all power banks for multiple time periods, thereby obtaining user power demand data for multiple time periods; Step S44: mining the electricity demand distribution of users' electricity demand data in multiple time periods to generate electricity demand distribution data for the region; Step S45: performing a multi-period demand fluctuation analysis on the regional power demand distribution data to generate user power demand fluctuation data; Step S46: Perform linear interpolation fitting on the user's electricity demand fluctuation data to construct an electricity demand fluctuation curve.

[0014] The present invention obtains the historical operation log of the shared charging cabinet, records the operation status, usage records and other information of the shared charging cabinet, which helps the system understand the usage and operation mode of the shared charging cabinet, analyzes the historical operation log, identifies the use behavior of the power bank, and extracts relevant data, which can help the system understand the user's charging habits and behavior patterns, and provide a basis for subsequent demand prediction and charging resource allocation. Multi-period statistics are performed on all power bank use behavior data to obtain user power demand data in different time periods, which helps the system analyze the time distribution law of power demand and provide a reference for the reasonable allocation of charging resources. By analyzing the user power demand data and mining the distribution of power demand, this can help the system understand the power demand characteristics of users in different time periods and provide support for formulating more intelligent charging scheduling strategies. Multi-period demand fluctuation analysis is performed on the power demand distribution data to generate user power demand fluctuation data, which helps the system predict the fluctuation of user power demand and prepare and schedule charging resources in advance. The power demand fluctuation data of the user is fitted by linear interpolation to construct a power demand fluctuation curve, which can help the system better understand the changing trend of power demand and provide a more accurate basis for charging control and resource scheduling.

[0015] Preferably, the specific steps of step S5 are: Step S51: extracting multiple power demand nodes based on the power demand fluctuation curve; Step S52: performing demand situation analysis on multiple power demand nodes to generate a power demand situation evolution law; Step S53: simulating the evolution of the electricity demand situation based on the evolution law of the electricity demand situation to generate electricity demand situation simulation data; Step S54: performing regional electricity demand forecasting on the electricity demand situation simulation data, thereby generating regional electricity demand forecasting data; Step S55: Dynamically adjust the charging power of the shared charging cabinet based on the regional electricity demand forecast data to generate a dynamic demand control strategy.

[0016] The present invention extracts multiple electricity demand nodes based on the electricity demand fluctuation curve, which helps the system capture the key time points of electricity demand and provide a basis for subsequent demand analysis and prediction. It performs demand situation analysis on multiple electricity demand nodes and generates the law of electricity demand situation evolution, which can help the system understand the changing trend and law of electricity demand and provide support for the formulation of demand prediction and regulation strategies. It simulates the evolution of electricity situation based on the law of electricity demand situation evolution and generates electricity demand situation simulation data, which helps the system simulate electricity demand situations in different scenarios and provides a reference for prediction and planning. It generates regional electricity demand forecast data by analyzing the electricity demand situation simulation data, which can help the system predict electricity demand situations in a certain period of time in the future and provide guidance for charging resource scheduling and allocation. It dynamically adjusts the charging power of shared charging cabinets based on the regional electricity demand forecast data and generates a dynamic demand regulation strategy, which helps the system adjust the charging power according to the real-time demand situation and improve resource utilization and charging efficiency.

[0017] Preferably, the specific steps of step S55 are: Calculate the current charging power of the shared charging cabinet and extract the current charging power; Calculate the charging power demand based on the regional electricity demand forecast data to obtain the required charging power parameters; Compare the current charging power with the required charging power parameter. When the required charging power parameter is greater than the current charging power, it is determined that the charging cabinet is in a state where the charging demand is not met. Calculate the charging load assigned to each power bank based on the charging demand unsatisfied state; The maximum charging power is calculated according to the charging load assigned to each power bank to obtain the maximum charging power of each power bank; Based on the maximum charging power of each power bank, the maximum charging power of the shared charging cabinet is adjusted to generate a dynamic demand control strategy.

[0018] The present invention calculates and extracts the current charging power to accurately understand the current charging status of the shared charging cabinet, and provides basic data for subsequent charging power regulation, which helps to realize real-time monitoring and management of charging equipment, ensure that the charging equipment is in normal operating state, improve charging efficiency and service quality, and calculate the charging power demand satisfaction based on regional electricity demand forecast data. The system can accurately predict future charging demand and determine the required charging power parameters, which helps to reasonably plan charging resources, respond to charging demand during peak hours in advance, ensure stable operation of charging equipment, and improve charging efficiency. By comparing the required charging power parameters with the current charging power, it is determined whether the charging demand is met. The effectiveness of this step lies in timely discovering whether the charging demand exceeds the current charging capacity, providing accurate judgment for subsequent regulation, and ensuring the continuity of charging service. By calculating the charging load assigned to each power bank, the system can optimize the allocation of charging resources and ensure that each power bank can obtain charging services on demand, which helps to improve the utilization rate of charging equipment, avoid waste of resources, and improve user experience and satisfaction. By calculating the maximum charging power of each power bank, the system can effectively manage charging resources and ensure that each power bank can obtain the required charging capacity in the shortest time, which helps to improve charging efficiency, reduce user waiting time, and optimize the charging service experience. By adjusting the maximum charging power of the shared charging cabinet, the system can dynamically adjust the charging power according to the maximum charging power demand of each power bank and formulate the best dynamic demand control strategy, which helps to flexibly respond to different charging needs, improve the adaptability and intelligence of charging equipment, and optimize the utilization efficiency of charging resources.

[0019] Preferably, the specific steps of step S6 are: Step S61: performing deep collaborative calculation analysis on the dynamic demand control strategy and the dynamic charging load distribution strategy to obtain a deep collaborative strategy; Step S62: identifying multiple demand scenarios based on the electricity demand fluctuation curve, thereby generating multiple electricity demand scenarios; Step S63: Based on multiple power demand scenarios, the deep collaborative strategy is used to conduct multi-scenario adaptive charging control mining and build an intelligent charging control model to complete the charging control operation of the shared charging cabinet.

[0020] The present invention analyzes dynamic demand regulation strategies and charging load distribution strategies through deep collaborative calculations. The system can achieve more accurate collaborative control and improve the operating efficiency and resource utilization of charging equipment, which helps to reduce energy waste, optimize charging load distribution, and improve the response speed and quality of charging services, thereby providing a more intelligent and efficient charging control solution. By identifying multiple power demand scenarios, the system can better understand the changes in charging demand in different time periods, and provide a more accurate reference for subsequent control strategy formulation, which helps to flexibly adjust charging strategies according to different scenarios, improve resource utilization efficiency, and meet users' diverse charging needs. Through multi-scenario adaptive charging control mining and intelligent model construction, the system can flexibly adjust deep collaborative strategies according to different scenarios to achieve intelligent charging control, which helps to improve the system's adaptability and response speed to different charging needs, optimize charging resource allocation, improve the overall efficiency and performance of charging equipment, and provide users with a more personalized and high-quality charging experience.

[0021] In this specification, a shared charging cabinet charging control system based on artificial intelligence is provided, which is used to execute the shared charging cabinet charging control method based on artificial intelligence as described above, including: The load trend module is used to obtain the real-time monitoring status data of the shared charging cabinet; perform real-time charging load calculation on the real-time monitoring status data of the shared charging cabinet, and perform short-term load trend evolution to generate short-term load trend characteristics; The charging priority module is used to monitor the current storage of power banks in the shared charging cabinet and perform charging shortage priority analysis to obtain the charging shortage priority of each power bank; The load distribution module is used to dynamically distribute charging load power to each power bank according to the charging shortage priority of the short-term load trend characteristics, and build a dynamic charging load distribution strategy; The demand fluctuation module is used to obtain the historical operation log of the shared charging cabinet; perform multi-period statistics on the power bank usage in the historical operation log of the shared charging cabinet, and perform multi-period demand fluctuation analysis to construct a power demand fluctuation curve; The demand control module is used to predict regional electricity demand based on the electricity demand fluctuation curve, and then dynamically adjust the charging power to generate a dynamic demand control strategy; The intelligent charging control module is used to conduct in-depth collaborative calculation and analysis of dynamic demand regulation strategies and dynamic charging load distribution strategies, and to conduct adaptive charging control mining to build an intelligent charging control model.

[0022] The present invention can provide accurate charging cabinet load information through real-time monitoring status data, help to realize real-time monitoring of charging cabinets, real-time charging load calculation and short-term load trend evolution are helpful to predict future load changes, make resource scheduling and planning in advance, generate short-term load trend characteristics, can provide important reference for subsequent load optimization and regulation, improve the utilization rate and efficiency of charging equipment, power bank storage monitoring and charging shortage priority analysis are helpful to determine the priority of each power bank, improve charging efficiency, obtain the charging shortage priority of each power bank, can optimize the allocation of charging resources, ensure that the charging needs at critical moments are met, through charging priority analysis, can improve user satisfaction, ensure that the power bank obtains timely charging service when demand is tight, dynamic charging load power distribution is optimized and distributed according to short-term load trend characteristics and charging shortage priority of power bank, improve charging efficiency, construct dynamic charging load distribution strategy, help avoid resource waste, ensure that each power bank obtains appropriate charging amount, dynamic load distribution can adjust charging power distribution according to actual conditions, improve resource utilization efficiency, optimize charging service quality, share charging cabinet historical operation The analysis of travel logs can help understand the changing patterns of charging demand and provide a basis for formulating more effective charging strategies. The analysis of multi-period demand fluctuations can better predict future fluctuations in charging demand and help optimize the allocation and distribution of charging resources. The construction of a power demand fluctuation curve can improve the understanding of charging demand and further optimize charging strategies and control measures. The regional power demand forecast based on the power demand fluctuation curve can more accurately predict future charging demand and realize dynamic charging power adjustment. The generation of dynamic demand control strategies can help to reasonably allocate charging resources, meet charging needs in different time periods, and improve charging efficiency. Dynamic demand control strategies can ensure that charging equipment operates stably during peak hours, improve service quality, and meet user needs. Deep collaborative calculation analysis and adaptive charging control mining can help optimize charging strategies and improve the intelligence of charging equipment. The construction of an intelligent charging control model can dynamically adjust the charging control strategy according to actual conditions, improve the adaptability and response speed of the system, and the intelligent charging control model can improve the intelligence level of the system, realize more efficient and intelligent charging control of shared charging cabinets, and improve user experience and service quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 This is a schematic diagram of the steps of a charging control method for a shared charging cabinet based on artificial intelligence in the present invention; Figure 2 Detailed implementation flow chart of step S1; Figure 3 Detailed implementation flow chart of step S2; Figure 4 Detailed implementation flow chart of step S3. DETAILED DESCRIPTION

[0024] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0025] The present application example provides a shared charging cabinet charging control method and system based on artificial intelligence. The execution subject of the shared charging cabinet charging control method and system based on artificial intelligence includes but is not limited to: mechanical equipment, data processing platform, cloud server node, network upload device, etc. equipped with the system can be regarded as the general computing node of the present application, and 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.

[0026] See also Figures 1 to 4 The present invention provides a shared charging cabinet charging control method based on artificial intelligence, and the shared charging cabinet charging control method based on artificial intelligence includes the following steps: Step S1: obtaining the real-time monitoring status data of the shared charging cabinet; performing real-time charging load calculation on the real-time monitoring status data of the shared charging cabinet, and performing short-term load trend evolution, thereby generating short-term load trend characteristics; Step S2: monitoring the current storage of power banks in the shared charging cabinet and performing a priority analysis of charging shortages, thereby obtaining the priority of each power bank; Step S3: dynamically allocate charging load power to each power bank according to the charging shortage priority according to the short-term load trend characteristics, and build a dynamic charging load allocation strategy; Step S4: Obtain the historical operation log of the shared charging cabinet; perform multi-period statistics on the power bank usage in the historical operation log of the shared charging cabinet, perform multi-period demand fluctuation analysis, and construct a power demand fluctuation curve; Step S5: forecasting regional electricity demand based on the electricity demand fluctuation curve, and then dynamically adjusting the charging power to generate a dynamic demand control strategy; Step S6: Conduct in-depth collaborative calculation and analysis on the dynamic demand regulation strategy and the dynamic charging load distribution strategy, and conduct adaptive charging control mining to build an intelligent charging control model.

[0027] The present invention monitors the status data in real time to calculate the charging load, which is helpful to understand the current load situation of the charging cabinet, analyze the evolution of short-term load trends, make predictions and plans for future charging needs, improve the utilization efficiency of the charging cabinet, perform priority analysis based on the current power bank storage monitoring results, ensure the rationality and efficiency of the power bank charging priority, dynamically adjust the charging load of the power bank according to the short-term load trend characteristics, optimize the utilization of charging resources, build an intelligent dynamic charging load distribution strategy, improve charging efficiency and user satisfaction, and perform multi-period demand fluctuation analysis through historical operation logs, which is helpful to understand the changing law of the power bank usage and provide a basis for charging resource allocation. Prediction is made based on the power demand fluctuation curve to achieve dynamic charging power adjustment, improve the adaptability and flexibility of the charging cabinet, generate control strategies for different demand situations, optimize charging resource allocation, and improve the overall efficiency of the charging cabinet. Through deep collaborative calculation and adaptive charging control mining, an intelligent charging control model is built to improve the management intelligence level of shared charging cabinets, optimize dynamic demand control strategies and charging load distribution strategies, and achieve efficient energy utilization and charging service quality.

[0028] In the embodiment of the present invention, refer to Figure 1 , is a schematic flow chart of the steps of a shared charging cabinet charging control method based on artificial intelligence of the present invention. In this example, the steps of the shared charging cabinet charging control method based on artificial intelligence include: Step S1: obtaining the real-time monitoring status data of the shared charging cabinet; performing real-time charging load calculation on the real-time monitoring status data of the shared charging cabinet, and performing short-term load trend evolution, thereby generating short-term load trend characteristics; In this embodiment, sensors (such as current sensors, voltage sensors, and temperature sensors) are installed in the shared charging cabinet to monitor the charging status of the power bank in real time. Ensure the compatibility of the monitoring system with the charging cabinet hardware and be able to transmit data to the back-end server through a network (such as Wi-Fi or Bluetooth). Use an embedded controller (such as Arduino or Raspberry Pi) for data acquisition and read sensor data regularly. The data includes voltage (V), current (A), charging status (charged / uncharged), and the status of the power bank (such as the remaining power). The data acquisition frequency can be set to once per second to ensure real-time performance.

[0029] The acquired monitoring data is organized into structured data (such as JSON or CSV format) by timestamp and stored in a real-time database (such as InfluxDB or MongoDB) for subsequent query and analysis. Based on the collected voltage and current data, the real-time charging power (W) is calculated using the following formula: Charging power = voltage × current This calculation can be completed in real time by the code in the embedded controller. Load data recording: The calculation result (charging power) is stored in the database together with the corresponding timestamp to track historical load data. The charging power data for the most recent period (such as the past 30 minutes or 1 hour) is extracted from the database to form a time series data set. The extracted data is smoothed using statistical methods (such as moving average or weighted moving average) to remove short-term fluctuations and identify more stable trends. By analyzing the smoothed data, short-term load trend characteristics are extracted, including: Peak load: the highest power value in a short period of time. Valley load: the lowest power value in a short period of time. Average load: the average power value in a short period of time. Load change rate: the change of load over time (such as the rate of increase or decrease). Use data visualization tools (such as Matplotlib or Tableau) to draw short-term load trend graphs to intuitively display the changes in real-time charging load. Store the extracted short-term load trend feature data in the database, and set up a feedback mechanism to regularly update the trend analysis in order to optimize the charging control strategy.

[0030] Step S2: monitoring the current storage of power banks in the shared charging cabinet and performing a priority analysis of charging shortages, thereby obtaining the priority of each power bank; In this embodiment, a charging status sensor is deployed to collect the power bank information of each charging slot in real time, and the collected data, such as battery capacity, power percentage, charging time, etc., is stored in the charging cabinet status database. IoT device access, data stream processing and other technical means can be used to complete the monitoring task. A multi-attribute decision scoring model is designed, such as the analytic hierarchy process (AHP) or TOPSIS method. The model input parameters include power percentage, charging time, battery health status, etc. The comprehensive priority score of each power bank is calculated based on these parameters, and the scoring results are sorted to determine the charging sequence priority.

[0031] Step S3: dynamically allocate charging load power to each power bank according to the charging shortage priority according to the short-term load trend characteristics, and build a dynamic charging load allocation strategy; In this embodiment, the charging load data of the shared charging cabinet in the recent period is collected, and time series analysis methods such as ARIMA and exponential smoothing are used for modeling and prediction. According to the prediction results, the fluctuation characteristics of the load, such as peak hours, valley hours, etc., are identified, and an optimization algorithm based on heuristic rules, such as a genetic algorithm or an ant colony algorithm, is designed. The algorithm input includes: power bank priority, load prediction data, power limit and other constraints. The algorithm output is a dynamic charging power allocation plan for each power bank. The goal is to maximize peak shaving and valley filling while meeting the needs of each power bank. The load trend analysis and power allocation algorithm are integrated into an intelligent decision-making module, which can monitor the status of the charging cabinet in real time, predict short-term load trends, and dynamically adjust the charging power of each power bank according to the prediction results and the priority of the power bank, so as to construct a set of adaptive dynamic charging load distribution strategies.

[0032] Step S4: Obtain the historical operation log of the shared charging cabinet; perform multi-period statistics on the power bank usage in the historical operation log of the shared charging cabinet, perform multi-period demand fluctuation analysis, and construct a power demand fluctuation curve; In this embodiment, the system of the shared charging cabinet is ensured to be able to record detailed operation logs, including the access time, return time, charging status, user ID and other information of the power bank, and the operation logs are stored in a database (such as MySQL, PostgreSQL or MongoDB) to ensure the structuring of the log data for subsequent query and analysis. The required historical operation log data is extracted from the database using SQL queries or appropriate APIs. The fields that can be extracted include: access time, return time, power bank ID, charging status, and the historical operation log data is divided into multiple time periods (such as hours, half a day, and full day) by time. The appropriate time granularity is selected according to the needs. The following time periods can be selected: peak time periods (such as morning peak and evening peak), normal time periods (such as daytime and night), and the access behavior in each time period is counted, and the amount of power bank access in each time period is calculated. The following method can be used to traverse each time period and calculate the number of times the electricity is taken within the time period. The Pandas library in Python is used for data processing. The statistical results of the electricity consumption in each time period are stored in the database for subsequent analysis and visualization. The changes in demand in different time periods are analyzed from the extracted statistical data of the electricity consumption in multiple time periods. The demand change rate of each time period can be calculated. Data visualization tools (such as Matplotlib, Seaborn, or Plotly) are used to draw the electricity demand fluctuation curve to show the changes in electricity consumption in different time periods. Sample code: Analyze the trend of demand through the fluctuation curve, identify peak and trough periods, and provide a basis for subsequent optimization of charging strategies. The constructed electricity demand fluctuation curve data and analysis results are recorded in the database, and a feedback mechanism is set up to regularly update the fluctuation analysis in order to optimize the charging control strategy.

[0033] Step S5: forecasting regional electricity demand based on the electricity demand fluctuation curve, and then dynamically adjusting the charging power to generate a dynamic demand control strategy; In this embodiment, time series analysis techniques, such as wavelet analysis and Fourier analysis, are applied to model the electricity demand data, identify key fluctuation nodes in the electricity demand curve, analyze the changing laws of the electricity consumption situation behind them, and build a Monte Carlo simulation model based on the identified evolution law of the electricity consumption situation. Multiple simulations are run to generate a data sequence of electricity demand forecast for a period of time in the future. Machine learning methods such as ARIMA and neural networks are used to further analyze and calibrate the forecast data. The electricity demand forecast data is compared and analyzed with the real-time load data of the charging cabinet. A dynamic charging power adjustment strategy based on an optimization algorithm, such as a genetic algorithm or a particle swarm algorithm, is designed. According to the predicted demand and the current load, the overall charging power output of the charging cabinet is adjusted in real time. The links such as electricity demand prediction and dynamic charging power adjustment are integrated into an adaptive control system. The system can perceive the changes in regional electricity demand in real time, dynamically optimize the charging power output of the charging cabinet, and finally generate a set of intelligent charging control strategies that can adapt to fluctuations in electricity demand.

[0034] Step S6: Conduct in-depth collaborative calculation and analysis on the dynamic demand regulation strategy and the dynamic charging load distribution strategy, and conduct adaptive charging control mining to build an intelligent charging control model.

[0035] In this embodiment, a collaborative model based on multi-objective optimization is designed, and the strategies in steps S5 and S3 are combined. The model input includes key parameters such as power demand forecast data and charging load distribution scheme. Through iterative optimization, the best coordination point between the two strategies is found to maximize the overall performance. Heuristic optimization methods such as genetic algorithm and particle swarm algorithm can be used to solve the problem. Various types of data generated during the operation of the charging cabinet, such as power demand and charging load, are collected. Machine learning technologies such as reinforcement learning and neural networks are applied to deeply analyze these data to mine the key factors affecting the charging control strategy and their complex relationships. Based on the analysis results, the parameters and algorithms of the control strategy are dynamically adjusted to improve adaptability. The charging control strategy that has undergone collaborative optimization and adaptive mining is integrated into an intelligent model. The model can perceive the status of the charging cabinet in real time, predict the trend of future power demand changes, and dynamically adjust the charging load distribution to ensure that the needs of each power bank are always met. The model also has the ability of continuous learning and self-optimization, and can continuously improve performance over time.

[0036] In this embodiment, refer to Figure 2 , is a flowchart of detailed implementation steps of step S1. In this embodiment, the detailed implementation steps of step S1 include: Step S11: Obtaining real-time monitoring status data of the shared charging cabinet; Step S12: Divide the real-time monitoring status data of the shared charging cabinet into sliding time series windows to obtain multiple time window monitoring status data; Step S13: Calculate the real-time charging load for the monitoring status data of multiple time windows to obtain the real-time charging load for each time window; Step S14: performing a time series load change analysis on the real-time charging loads in all time windows to generate time series load change data; Step S15: Perform short-term load trend evolution on the time-series load change data to generate short-term load trend characteristics.

[0037] In this embodiment, sensors and monitoring equipment are deployed to collect status data of the charging cabinet in real time, such as current, voltage, temperature, charging time, etc. The Internet of Things (IoT) technology is used to send the data to a central server or cloud platform to ensure that the collected data format is unified, such as using JSON or CSV format for subsequent processing. The MQTT or HTTP protocol is used to achieve real-time data transmission to ensure timely update and acquisition of data. The acquired real-time monitoring status data is stored in a database (such as MySQL or MongoDB) for subsequent analysis and calculation. The size of the time window is determined, such as every 5 minutes or every 10 minutes as a window. The window size should be determined according to the frequency of data collection and analysis requirements. The real-time monitoring data is divided using a sliding window algorithm to generate multiple time windows. The algorithm can be implemented by looping through the data set, moving a fixed time step each time, extracting and storing the data in each time window, ensuring the data integrity and availability of each window, and storing the data of each window in a data structure, such as a list or a dictionary. For subsequent calculation and analysis, determine the calculation formula of real-time charging load, real-time load = voltage × current, get the power load of each time window, traverse the data of each time window, use the above formula to calculate the real-time charging load of each window, organize the real-time charging load data of all time windows into time series data, ensure that the timestamp and load value correspond clearly, calculate the load change between each time window, usually by calculating the load difference between adjacent windows, perform statistical analysis, calculate the mean, standard deviation, maximum and minimum values ​​of the load change and other indicators to evaluate the range and trend of the load change, select appropriate time series analysis methods, such as moving average method, exponential smoothing method or ARIMA model, perform short-term trend analysis on the load change data, use historical load change data to train the analysis model, predict the load trend in the next few time windows, extract short-term load trend characteristics from the analysis results, such as growth rate, fluctuation range, etc., to facilitate subsequent decision-making, record the short-term load trend characteristics, and generate a report for subsequent reference and optimization of the load management strategy of the charging cabinet.

[0038] In this embodiment, refer to Figure 3 , is a flowchart of detailed implementation steps of step S2. In this embodiment, the detailed implementation steps of step S2 include: Step S21: monitoring the current power bank storage in the shared charging cabinet and identifying the status data of the current power bank storage; Step S22: Calculate the battery capacity of the current stored power bank status data to obtain the battery capacity value of the stored power bank; Step S23: Calculate the remaining battery capacity of the currently stored power bank status data, and extract the remaining battery capacity of each power bank; Step S24: Calculating the charging capacity requirement of each power bank based on the battery capacity value of the stored power bank, so as to generate the charging capacity requirement of each power bank; Step S25: Perform a charging shortage priority analysis based on the charging demand of each power bank, so as to obtain the charging shortage priority of each power bank.

[0039] In this embodiment, sensors and monitoring devices are integrated in the shared charging cabinet, which can monitor the plug-in status and charging status of the power bank in real time. The status data of the power bank is collected by using an embedded system or a microcontroller (such as Arduino or Raspberry Pi), including the connection status and charging status of each power bank. The collected power bank status data is formatted into a unified form, such as JSON format, for subsequent processing. The monitored power bank status data is stored in a database (such as MySQL or MongoDB) for subsequent access and analysis. The battery capacity value of the power bank is determined, which is usually provided by the manufacturer in milliampere hours (mAh) or watt-hours (Wh). The status data of the power bank currently stored is extracted, including the model and specifications of the power bank. If the battery capacity value of the power bank is not directly available, it can be estimated based on its specifications and charging status. For example, if the power bank is charging, it can be calculated based on the charging current and time. The remaining battery capacity is usually expressed as the ratio of the current power of the power bank to its total power, usually expressed as a percentage. The current power data of each power bank is extracted, which may be directly provided by the monitoring device. The remaining battery capacity of each power bank is provided or calculated by an algorithm. The remaining battery capacity of each power bank is associated with its unique identifier and stored in a database for subsequent analysis. The charging demand represents the amount of electricity required to fully charge the power bank. The calculation formula is: charging demand = battery capacity − current power. Each power bank is traversed and the charging demand is calculated by the above formula. The charging demand of each power bank is associated with its unique identifier and stored in a database. The evaluation criteria for charging shortage priority are determined. Factors such as battery remaining capacity, charging demand and frequency of use are usually considered. A scoring system is defined. A high score is given when the remaining capacity is less than 20%, a high score is given when the charging demand is high, and a high score is given when the frequency of use is high. A comprehensive priority score is calculated for each power bank. All power banks are sorted according to the calculated priority score to obtain a charging shortage priority list. The priority analysis results are generated into a report or a visual chart to facilitate managers to understand the charging demand and priority of the power bank.

[0040] In this embodiment, refer to Figure 4 , is a flowchart of detailed implementation steps of step S3. In this embodiment, the detailed implementation steps of step S3 include: Step S31: predicting the load peak based on the short-term load trend characteristics, thereby obtaining charging cabinet load peak prediction data; Step S32: Calculate the charging load of the currently stored power bank status data to obtain the charging load data of each power bank; Step S33: performing a dynamic priority analysis on the charging shortage priority of each power bank based on the charging load data of each power bank, thereby obtaining a dynamic charging load priority of each power bank; Step S34: dynamically allocate charging load power to each power bank according to the charging cabinet load peak prediction data, and construct a dynamic charging load allocation strategy.

[0041] In this embodiment, the recent load data of the charging cabinet, including the number of power banks, power status and other indicators, are collected, and a time series analysis method, such as an ARIMA model, is used to perform short-term prediction of these load data. Based on the prediction results, the load peak period that may occur in the future is identified, thereby obtaining the recent load peak prediction data of the charging cabinet, and the status of the power banks in each charging cabinet is monitored in real time, including battery capacity, remaining power, etc. The charging load demand of each power bank at this time is calculated according to the power status of the power bank, and the real-time charging load data of each power bank in the charging cabinet is summarized. According to the charging load demand of each power bank and the remaining battery power and other factors, a multi-attribute decision analysis method, such as a hierarchical analysis method, is used to calculate the charging priority of each power bank, thereby obtaining the dynamic charging load priority ranking of each power bank, and the load peak prediction data of the charging cabinet is compared and analyzed with the dynamic priority of each power bank, and a dynamic charging load power allocation algorithm is designed, such as an optimization algorithm based on heuristic rules, and the dynamic allocation of charging power among the power banks is realized according to the peak prediction and priority, and finally a complete set of dynamic charging load allocation strategies is constructed.

[0042] In this embodiment, step S4 includes the following steps: Step S41: Obtain the historical operation log of the shared charging cabinet; Step S42: Identify the power bank access behavior in the historical operation log of the shared charging cabinet, and extract all the power bank access behavior data; Step S43: performing statistics on the usage of all power banks for multiple time periods, thereby obtaining user power demand data for multiple time periods; Step S44: mining the electricity demand distribution of users' electricity demand data in multiple time periods to generate electricity demand distribution data for the region; Step S45: performing a multi-period demand fluctuation analysis on the regional power demand distribution data to generate user power demand fluctuation data; Step S46: Perform linear interpolation fitting on the user's electricity demand fluctuation data to construct an electricity demand fluctuation curve.

[0043] In this embodiment, the system of the shared charging cabinet is ensured to be able to record detailed operation logs, including the use, return, charging status, timestamp and other information of the power bank, store the operation logs in a database (such as MySQL or MongoDB), and ensure the structure of the logs to facilitate subsequent query and analysis, use SQL query or data extraction tools to extract the required historical operation log data from the database, format the extracted log data into a unified format, such as CSV or JSON, for subsequent processing and analysis, traverse the historical operation logs, identify all the use behaviors, and determine the correspondence between use and return through timestamp, user ID and power bank ID. Extract the identified use behavior data, record the use time, user ID, power bank ID and other information, and store it in a new data table or data structure, divide the daily use behavior data into multiple time periods (such as hours, half a day, full day), select the appropriate time granularity according to the needs, count the use behavior in each time period, calculate the power bank use in each time period, and extract the user power demand data for multiple time periods. It is organized into a structured data set. The electricity demand data is analyzed using statistical analysis or machine learning methods (such as K-means clustering) to identify the distribution characteristics of the demand. Based on the analysis results, a distribution model of the electricity demand is constructed, and the electricity demand distribution data of the area is generated. The demand distribution is visualized using chart tools (such as Matplotlib or Seaborn) to help intuitively understand the user's electricity demand. The standards for demand fluctuations, including the rise, fall, and stable state of demand, are defined. The electricity demand distribution data is extracted and the demand changes in each time period are calculated. The demand fluctuations are analyzed using statistical methods (such as standard deviation and coefficient of variation) to identify the amplitude and frequency of demand fluctuations. The analysis results are recorded to form the user's electricity demand fluctuation data for subsequent analysis and decision-making. The linear interpolation method (such as the interp1d function in the SciPy library) is selected to fit the demand fluctuation data. Linear interpolation calculations are performed for each time period to generate a smooth electricity demand fluctuation curve. The interpolation results are visualized and the electricity demand fluctuation curve is drawn for easy analysis and display.

[0044] In this embodiment, step S5 includes the following steps: Step S51: extracting multiple power demand nodes based on the power demand fluctuation curve; Step S52: performing demand situation analysis on multiple power demand nodes to generate a power demand situation evolution law; Step S53: simulating the evolution of the electricity demand situation based on the evolution law of the electricity demand situation to generate electricity demand situation simulation data; Step S54: performing regional electricity demand forecasting on the electricity demand situation simulation data, thereby generating regional electricity demand forecasting data; Step S55: Dynamically adjust the charging power of the shared charging cabinet based on the regional electricity demand forecast data to generate a dynamic demand control strategy.

[0045] In this embodiment, the electricity demand data of various users in the area are collected, and a fluctuation curve of electricity demand is drawn. A peak and trough recognition algorithm is used to extract multiple significant electricity demand nodes from the curve. These nodes represent the key change points of electricity demand in the area. For each electricity demand node, the corresponding indicators such as electricity consumption and the number of electricity users are analyzed. The electricity demand situation behind each demand node is excavated by using time series analysis and other methods, and the evolution law of the electricity demand situation in the area is summarized. A simulation model of the evolution of the electricity demand situation is established to simulate the changes in the electricity demand situation in the future. Monte Carlo method and other methods are used to perform multiple simulation runs to generate a simulated data sequence of electricity demand situation, analyze the potential laws and trends contained in the simulated data of electricity demand situation, use time series prediction, machine learning and other methods to predict future regional electricity demand, and obtain the forecast data of regional electricity demand in the future. The predicted regional electricity demand data is compared with the real-time load data of the shared charging cabinet, and a dynamic charging power adjustment algorithm is designed. According to the electricity demand prediction results, the power output of the charging cabinet is dynamically adjusted, and finally a set of dynamic demand control strategies that can adapt to changes in electricity demand are generated.

[0046] In this embodiment, the specific steps of step S55 are: Calculate the current charging power of the shared charging cabinet and extract the current charging power; Calculate the charging power demand based on the regional electricity demand forecast data to obtain the required charging power parameters; Compare the current charging power with the required charging power parameter. When the required charging power parameter is greater than the current charging power, it is determined that the charging cabinet is in a state where the charging demand is not met. Calculate the charging load assigned to each power bank based on the charging demand unsatisfied state; The maximum charging power is calculated according to the charging load assigned to each power bank to obtain the maximum charging power of each power bank; Based on the maximum charging power of each power bank, the maximum charging power of the shared charging cabinet is adjusted to generate a dynamic demand control strategy.

[0047] In this embodiment, the current charging power data is obtained in real time from the monitoring system of the shared charging cabinet. The charging power is usually provided by the power sensor of each power bank. The current charging power (for example, 80W) is used to extract the charging power of all power banks and summarize them to calculate the total charging power of the current charging cabinet: power bank A: 30W, power bank B: 25W, power bank C: 25W, total charging power = 30W + 25W + 25W = 80W. The regional electricity demand forecast data is used to predict the required charging power (for example, 100W). According to the predicted data, the charging power parameters that the charging cabinet needs to meet are determined, and the required charging power parameters are recorded for subsequent comparison. The current charging power (80W) and the required charging power (100W) are determined to determine whether the required charging power is greater than the current charging power: if 100W>80W, the charging cabinet is determined to be in a "charging demand unmet state", and the charging load of each power bank in the charging demand unmet state is calculated: dynamic load distribution is performed according to the priority and current state of each power bank, and power banks A, B, and C are allocated to the same power bank. The priorities are 1, 2, and 3 respectively, then the possible allocated loads are: power bank A: 40W, power bank B: 30W, power bank C: 10W. The maximum charging power of each power bank is calculated, usually based on the maximum power limit of the device: assuming that the maximum power of each power bank is 50W, if the allocated load is 40W, the maximum charging power is 50W. Based on the maximum charging power of each power bank, a dynamic adjustment strategy is designed: when the charging demand is not met, the charging power is dynamically adjusted according to the allocated load and maximum power. If the current charging power is 80W and the required charging power is 100W, it can be increased to 100W. Implement a dynamic adjustment strategy to adjust the output power of the charging cabinet in real time to meet the user's charging needs, monitor the adjustment effect, and ensure that the charging cabinet can stably output the required power.

[0048] In this embodiment, the specific steps of step S6 are: Step S61: performing deep collaborative calculation analysis on the dynamic demand control strategy and the dynamic charging load distribution strategy to obtain a deep collaborative strategy; Step S62: identifying multiple demand scenarios based on the electricity demand fluctuation curve, thereby generating multiple electricity demand scenarios; Step S63: Based on multiple power demand scenarios, the deep collaborative strategy is used to conduct multi-scenario adaptive charging control mining and build an intelligent charging control model to complete the charging control operation of the shared charging cabinet.

[0049] In this embodiment, relevant data of the dynamic demand regulation strategy and the dynamic charging load distribution strategy are collected to ensure that the data includes the input parameters, output results and their mutual relationship of the strategy, select a suitable mathematical or computational model (such as a multi-objective optimization model, a game theory model or a system dynamics model) to analyze the synergistic relationship between the dynamic demand regulation strategy and the load distribution strategy, use a simulation tool (such as MATLAB, Simulink or the SciPy library in Python) to simulate the model, analyze the mutual influence of the strategies under different conditions, set multiple scenarios (such as high demand, low demand, stable demand, etc.) for calculation, observe the system response, extract the calculation results, analyze the performance of the deep coordination strategy, identify the best strategy combination, optimize the strategy parameters according to the analysis results, form a comprehensive deep coordination strategy, and define the standards for multiple demand scenarios, for example: peak period: electricity demand is significantly higher than the average level, valley period: electricity demand is significantly lower than the average Level, stable period: Electricity demand fluctuates within a relatively stable range. Apply clustering algorithms (such as K-means algorithm) or segmented regression analysis to classify the fluctuation curves and identify multiple electricity demand scenarios. The identified multiple electricity demand scenarios and their characteristics are recorded in the database for subsequent analysis and model building. Select a suitable adaptive control algorithm (such as fuzzy control, PID control or reinforcement learning) to realize intelligent charging control. Use historical data and identified scenarios for model training to ensure that the model can adaptively adjust the charging strategy under different electricity demand scenarios. Perform model verification, test its performance in actual scenarios, adjust parameters to improve accuracy, embed the trained intelligent charging control model into the control system of the shared charging cabinet, monitor the electricity demand in real time and automatically adjust the charging strategy, continuously monitor the charging status of the charging cabinet and user feedback, and adjust the intelligent charging control model in real time according to actual conditions.

[0050] In this embodiment, a shared charging cabinet charging control system based on artificial intelligence is provided, which is used to execute the shared charging cabinet charging control method based on artificial intelligence as described above, including: The load trend module is used to obtain the real-time monitoring status data of the shared charging cabinet; perform real-time charging load calculation on the real-time monitoring status data of the shared charging cabinet, and perform short-term load trend evolution to generate short-term load trend characteristics; The charging priority module is used to monitor the current storage of power banks in the shared charging cabinet and perform charging shortage priority analysis to obtain the charging shortage priority of each power bank; The load distribution module is used to dynamically distribute charging load power to each power bank according to the charging shortage priority of the short-term load trend characteristics, and build a dynamic charging load distribution strategy; The demand fluctuation module is used to obtain the historical operation log of the shared charging cabinet; perform multi-period statistics on the power bank usage in the historical operation log of the shared charging cabinet, and perform multi-period demand fluctuation analysis to construct a power demand fluctuation curve; The demand control module is used to predict regional electricity demand based on the electricity demand fluctuation curve, and then dynamically adjust the charging power to generate a dynamic demand control strategy; The intelligent charging control module is used to conduct in-depth collaborative calculation and analysis of dynamic demand regulation strategies and dynamic charging load distribution strategies, and to conduct adaptive charging control mining to build an intelligent charging control model.

[0051] The present invention can provide accurate charging cabinet load information through real-time monitoring status data, help to realize real-time monitoring of charging cabinets, real-time charging load calculation and short-term load trend evolution are helpful to predict future load changes, make resource scheduling and planning in advance, generate short-term load trend characteristics, can provide important reference for subsequent load optimization and regulation, improve the utilization rate and efficiency of charging equipment, power bank storage monitoring and charging shortage priority analysis are helpful to determine the priority of each power bank, improve charging efficiency, obtain the charging shortage priority of each power bank, can optimize the allocation of charging resources, ensure that the charging needs at critical moments are met, through charging priority analysis, can improve user satisfaction, ensure that the power bank obtains timely charging service when demand is tight, dynamic charging load power distribution is optimized and distributed according to short-term load trend characteristics and charging shortage priority of power bank, improve charging efficiency, construct dynamic charging load distribution strategy, help avoid resource waste, ensure that each power bank obtains appropriate charging amount, dynamic load distribution can adjust charging power distribution according to actual conditions, improve resource utilization efficiency, optimize charging service quality, share charging cabinet historical operation The analysis of travel logs can help understand the changing patterns of charging demand and provide a basis for formulating more effective charging strategies. The analysis of multi-period demand fluctuations can better predict future fluctuations in charging demand and help optimize the allocation and distribution of charging resources. The construction of a power demand fluctuation curve can improve the understanding of charging demand and further optimize charging strategies and control measures. The regional power demand forecast based on the power demand fluctuation curve can more accurately predict future charging demand and realize dynamic charging power adjustment. The generation of dynamic demand control strategies can help to reasonably allocate charging resources, meet charging needs in different time periods, and improve charging efficiency. Dynamic demand control strategies can ensure that charging equipment operates stably during peak hours, improve service quality, and meet user needs. Deep collaborative calculation analysis and adaptive charging control mining can help optimize charging strategies and improve the intelligence of charging equipment. The construction of an intelligent charging control model can dynamically adjust the charging control strategy according to actual conditions, improve the adaptability and response speed of the system, and the intelligent charging control model can improve the intelligence level of the system, realize more efficient and intelligent charging control of shared charging cabinets, and improve user experience and service quality.

[0052] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0053] The above is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be 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 will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A charging control method for a shared charging cabinet based on artificial intelligence, characterized in that: The following steps are involved: Step S1: Obtaining real-time monitoring status data of the shared charging cabinet; Real-time charging load calculation is performed on the real-time monitoring status data of the shared charging cabinet, and short-term load trend evolution is performed to generate short-term load trend characteristics; Step S2: monitoring the current storage of power banks in the shared charging cabinet and performing a priority analysis of charging shortages, thereby obtaining the priority of each power bank; Step S3: dynamically allocate charging load power to each power bank according to the charging shortage priority according to the short-term load trend characteristics, and build a dynamic charging load allocation strategy; Step S4: Obtain the historical operation log of the shared charging cabinet; perform multi-period statistics on the power bank usage in the historical operation log of the shared charging cabinet, perform multi-period demand fluctuation analysis, and construct a power demand fluctuation curve; Step S5: forecasting regional electricity demand based on the electricity demand fluctuation curve, and then dynamically adjusting the charging power to generate a dynamic demand control strategy; Step S6: Conduct in-depth collaborative calculation and analysis on the dynamic demand regulation strategy and the dynamic charging load distribution strategy, and conduct adaptive charging control mining to build an intelligent charging control model.

2. The artificial intelligence-based shared charging cabinet charging control method according to claim 1 is characterized in that: The specific steps of step S1 are: Step S11: Obtaining real-time monitoring status data of the shared charging cabinet; Step S12: Divide the real-time monitoring status data of the shared charging cabinet into sliding time series windows to obtain multiple time window monitoring status data; Step S13: Calculate the real-time charging load for the monitoring status data of multiple time windows to obtain the real-time charging load for each time window; Step S14: performing a time series load change analysis on the real-time charging loads in all time windows to generate time series load change data; Step S15: Perform short-term load trend evolution on the time-series load change data to generate short-term load trend characteristics.

3. The charging control method of a shared charging cabinet based on artificial intelligence according to claim 1 is characterized in that: The specific steps of step S2 are: Step S21: monitoring the current power bank storage in the shared charging cabinet and identifying the status data of the current power bank storage; Step S22: Calculate the battery capacity of the current stored power bank status data to obtain the battery capacity value of the stored power bank; Step S23: Calculate the remaining battery capacity of the currently stored power bank status data, and extract the remaining battery capacity of each power bank; Step S24: Calculating the charging capacity requirement of each power bank based on the battery capacity value of the stored power bank, so as to generate the charging capacity requirement of each power bank; Step S25: Perform a charging shortage priority analysis based on the charging demand of each power bank, so as to obtain the charging shortage priority of each power bank.

4. The charging control method of a shared charging cabinet based on artificial intelligence according to claim 1 is characterized in that: The specific steps of step S3 are: Step S31: predicting the load peak based on the short-term load trend characteristics, thereby obtaining charging cabinet load peak prediction data; Step S32: Calculate the charging load of the currently stored power bank status data to obtain the charging load data of each power bank; Step S33: performing a dynamic priority analysis on the charging shortage priority of each power bank based on the charging load data of each power bank, thereby obtaining a dynamic charging load priority of each power bank; Step S34: dynamically allocate charging load power to each power bank according to the charging cabinet load peak prediction data, and construct a dynamic charging load allocation strategy.

5. The charging control method of a shared charging cabinet based on artificial intelligence according to claim 1 is characterized in that: The specific steps of step S4 are: Step S41: Obtain the historical operation log of the shared charging cabinet; Step S42: Identify the power bank access behavior in the historical operation log of the shared charging cabinet, and extract all the power bank access behavior data; Step S43: performing statistics on the usage of all power banks for multiple time periods, thereby obtaining user power demand data for multiple time periods; Step S44: mining the electricity demand distribution of users' electricity demand data in multiple time periods to generate electricity demand distribution data for the region; Step S45: performing a multi-period demand fluctuation analysis on the regional power demand distribution data to generate user power demand fluctuation data; Step S46: Perform linear interpolation fitting on the user's electricity demand fluctuation data to construct an electricity demand fluctuation curve.

6. The artificial intelligence-based shared charging cabinet charging control method according to claim 1 is characterized in that: The specific steps of step S5 are: Step S51: extracting multiple power demand nodes based on the power demand fluctuation curve; Step S52: performing demand situation analysis on multiple power demand nodes to generate a power demand situation evolution law; Step S53: simulating the evolution of the electricity demand situation based on the evolution law of the electricity demand situation to generate electricity demand situation simulation data; Step S54: performing regional electricity demand forecasting on the electricity demand situation simulation data, thereby generating regional electricity demand forecasting data; Step S55: Dynamically adjust the charging power of the shared charging cabinet based on the regional electricity demand forecast data to generate a dynamic demand control strategy.

7. The artificial intelligence-based shared charging cabinet charging control method according to claim 6 is characterized in that: The specific steps of step S55 are: Calculate the current charging power of the shared charging cabinet and extract the current charging power; Calculate the charging power demand based on the regional electricity demand forecast data to obtain the required charging power parameters; Compare the current charging power with the required charging power parameter. When the required charging power parameter is greater than the current charging power, it is determined that the charging cabinet is in a state where the charging demand is not met. Calculate the charging load assigned to each power bank based on the charging demand unsatisfied state; The maximum charging power is calculated according to the charging load assigned to each power bank to obtain the maximum charging power of each power bank; Based on the maximum charging power of each power bank, the maximum charging power of the shared charging cabinet is adjusted to generate a dynamic demand control strategy.

8. The artificial intelligence-based shared charging cabinet charging control method according to claim 1 is characterized in that: The specific steps of step S6 are: Step S61: performing deep collaborative calculation analysis on the dynamic demand control strategy and the dynamic charging load distribution strategy to obtain a deep collaborative strategy; Step S62: identifying multiple demand scenarios based on the electricity demand fluctuation curve, thereby generating multiple electricity demand scenarios; Step S63: Based on multiple power demand scenarios, the deep collaborative strategy is used to conduct multi-scenario adaptive charging control mining and build an intelligent charging control model to complete the charging control operation of the shared charging cabinet.

9. A shared charging cabinet charging control system based on artificial intelligence, characterized in that: The method for controlling the charging of a shared charging cabinet based on artificial intelligence according to claim 1 comprises: The load trend module is used to obtain the real-time monitoring status data of the shared charging cabinet; perform real-time charging load calculation on the real-time monitoring status data of the shared charging cabinet, and perform short-term load trend evolution to generate short-term load trend characteristics; The charging priority module is used to monitor the current storage of power banks in the shared charging cabinet and perform charging shortage priority analysis to obtain the charging shortage priority of each power bank; The load distribution module is used to dynamically distribute charging load power to each power bank according to the charging shortage priority of the short-term load trend characteristics, and build a dynamic charging load distribution strategy; The demand fluctuation module is used to obtain the historical operation log of the shared charging cabinet; perform multi-period statistics on the power bank usage in the historical operation log of the shared charging cabinet, and perform multi-period demand fluctuation analysis to construct a power demand fluctuation curve; The demand control module is used to predict regional electricity demand based on the electricity demand fluctuation curve, and then dynamically adjust the charging power to generate a dynamic demand control strategy; The intelligent charging control module is used to conduct in-depth collaborative calculation and analysis of dynamic demand regulation strategies and dynamic charging load distribution strategies, and to conduct adaptive charging control mining to build an intelligent charging control model.

Images