A charging pile load monitoring method and system based on AI technology

Abstract

The application relates to the field of charging pile load supervision, in particular to a charging pile load supervision method and system based on AI technology, which comprises the following steps: collecting, through sensors installed in charging piles and a power grid, operation data of the charging piles and load data of the power grid, establishing a charging pile load demand prediction neural network model, and outputting a charging pile load demand prediction result; determining a charging power adjustment range of the charging pile according to the obtained power grid voltage deviation, and adjusting a charging time according to the charging power adjustment range; calculating and determining charging pile load balancing adjustment parameters according to the output result of the charging pile load demand prediction, the charging power adjustment range and charging pile related data information; and establishing a charging pile energy consumption monitoring model according to the optimized charging pile charging rate and the basic fault repair rate, and monitoring the working condition of the charging pile.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of charging pile load supervision, and particularly relates to a charging pile load supervision method and system based on AI technology. BACKGROUND

[0002] With the popularity of electric vehicles, the number of charging piles is also increasing. However, the load management problem of charging piles is increasingly prominent. Unreasonable use of charging piles can lead to excessive local power grid load, affecting the stability of the power grid and the quality of power supply, and even may cause safety accidents. The traditional charging pile load management method is mainly based on artificial experience and fixed rules, which is difficult to respond to complex and variable charging demand and power grid load situation in real time and accurately.

[0003] With the continuous development of artificial intelligence, there has been great progress in charging pile load monitoring, but the existing technology still has the following problems: charging piles and other equipment running at high power at the same time cause power grid load imbalance; lack of ability to adjust charging power in real time according to power grid voltage conditions, unable to effectively control charging cost; unable to guarantee system stability, and affect the economic benefit of the charging system, etc.

[0004] Therefore, a charging pile load supervision method and system based on AI technology are needed. SUMMARY

[0005] The charging pile load supervision method and system based on AI technology provided by the present application aims to monitor and analyze the running state and energy consumption of charging piles in real time through AI technology, improve the management efficiency, energy utilization efficiency and service quality of the charging pile system, reduce operating costs, and promote the sustainable development and intelligent process of the charging industry.

[0006] The technical scheme of the present application is as follows:

[0007] A charging pile load supervision method based on AI technology, comprising the following steps:

[0008] Step S1. Real-time collection of charging pile operation data and power grid load data through sensors installed in the charging pile and the power grid, establishment of a charging pile load demand prediction neural network model, and output of charging pile load demand prediction results;

[0009] Step S2. Determining the charging power adjustment range of the charging pile according to the obtained power grid voltage deviation, and adjusting the charging time according to the charging power adjustment range;

[0010] Step S3. Calculating and determining the charging pile load balancing adjustment parameters through the output results of the charging pile load demand prediction, the charging power adjustment range, and the charging pile related data information;

[0011] Step S4. According to the optimized charging pile charging rate and the basic fault repair rate, a charging pile energy consumption monitoring model is established to monitor the working condition of the charging pile.

[0012] Step S1 specifically includes:

[0013] The charging pile load demand prediction neural network model includes an input gate, a forget gate, and an output gate.

[0014] The current load state is updated according to new information in the input gate; the forget gate controls the charging pile management and control system to forget outdated or no longer relevant load information; the output gate controls the generation of output results based on the current load state, ,

[0015] wherein, represents the output of the forget gate neuron; represents the output result in the output gate; represents the time decay coefficient; represents the bias of the neuron in the output gate; represents the weight of the neuron in the output gate.

[0016] Step S2 specifically includes:

[0017] Define the grid voltage deviation as , set the upper limit voltage deviation threshold in the normal range as , the upper limit voltage deviation threshold in the warning range as , and obtain the current charging power of the charging pile ; the adjusted charging power is ;

[0018] If , the charging power adjustment amplitude is the first charging power adjustment amplitude, and the adjusted charging power is ;

[0019] If , the charging power adjustment amplitude is the second charging power adjustment amplitude, and the adjusted charging power is ;

[0020] If , the charging power adjustment amplitude is the third charging power adjustment amplitude, and the adjusted charging power is ;

[0021] wherein, represents the adjustment coefficient when the voltage deviation is in the normal range; represents the adjustment coefficient when the voltage deviation is in the warning range; represents the adjustment coefficient when the voltage deviation exceeds the warning range.

[0022] Further, step S2 specifically comprises: defining the initial charging power The amount of electricity required for charging is The initial charging time is ,

[0023] , Wherein, represents the charging power adjustment amplitude; represents the adjusted charging power, ; represents the first charging time adjustment mode, .

[0024] Step S3 specifically comprises: Wherein, represents the charging pile load balancing adjustment parameter; represents the charging pile load prediction deviation; represents the remaining proportion of electricity; represents the predicted time period; represents the total maximum charging power of all charging piles; represents the weight proportion of the charging pile load prediction deviation; represents the weight proportion of the remaining proportion of electricity; represents the weight proportion of the charging power adjustment amplitude.

[0025] Further, step S3 specifically comprises:

[0026] According to the charging pile load balancing adjustment parameter , the charging rate and the basic fault repair rate are dynamically optimized;

[0027] The first preset charging pile load balancing adjustment parameter reference value And the second preset charging pile load balancing adjustment parameter reference value , and ; the charging pile load balancing adjustment parameter is compared with and respectively, and the charging pile charging rate and the charging pile basic fault repair rate are optimized, respectively, to obtain the optimized , .

[0028] The comprehensive index of the charging pile energy consumption monitoring model in step S4 is , and the process is as follows:

[0029] Wherein, , respectively represent the weight coefficients; This indicates the deviation between the actual total energy consumption and the theoretical total energy consumption of a charging station. Indicates the parameters affected by the fault.

[0030] A charging pile load monitoring system based on AI technology includes the following:

[0031] The system includes modules for collecting charging pile information, predicting charging pile load demand, adjusting charging power, adjusting charging time, determining charging pile load balancing adjustment parameters, optimizing charging rate, optimizing basic fault repair rate, and monitoring charging pile energy consumption.

[0032] The charging pile information acquisition module collects relevant information about the charging pile in real time through sensors installed in the charging pile and the power grid;

[0033] The charging pile load demand prediction module establishes a neural network model for predicting charging pile load demand based on real-time collected operating data of charging piles and load data of the power grid, and outputs the charging pile load demand prediction results.

[0034] The charging power adjustment module determines the charging power adjustment range of the charging pile based on the obtained grid voltage deviation.

[0035] The charging time adjustment module adjusts the charging time according to different charging power adjustment ranges to ensure charging efficiency and load balance;

[0036] The charging pile load balancing adjustment parameter determination module determines the charging pile load balancing adjustment parameters based on the output results of the charging pile load demand prediction, the charging power adjustment range, and relevant charging pile data.

[0037] The charging rate optimization module compares the charging pile load balancing adjustment parameters with the first preset comparison parameter value and the second preset comparison parameter value respectively, and optimizes the charging rate of the charging pile.

[0038] The basic fault repair rate optimization module compares the charging pile load balancing adjustment parameters with the first preset comparison parameter value and the second preset comparison parameter value respectively, and optimizes the basic fault repair rate of the charging pile.

[0039] The charging pile energy consumption monitoring module monitors the energy consumption of the charging pile, promptly detects energy consumption anomalies, and takes appropriate measures.

[0040] Beneficial effects: 1. The application introduces a gating unit, and the charging pile load demand prediction neural network model can better control the flow and memory of information, thereby improving the prediction accuracy of load demand, optimizing the load control and system operation efficiency of the charging pile, and making the charging pile system more intelligent and adaptive, which can better cope with the changing charging demand and system operation environment.

[0041] 2. The application adjusts the charging power according to the deviation of the grid voltage, helps to balance the grid load, improves the stability of the grid, reduces the pressure of the grid, and optimizes the energy utilization efficiency; adjusting the charging power can optimize the charging rate in real time according to the grid voltage, reduce the charging cost, avoid excessive energy consumption, and improve the energy utilization efficiency; according to the charging power adjustment range, the charging time is flexibly adjusted, so that the system is more adaptive and can adjust the charging strategy according to the real-time situation; at the same time, reasonable adjustment of the charging time can avoid damage to the charging equipment caused by overcharging, and prolong the service life of the equipment.

[0042] 3. The application accurately calculates the charging pile load balancing adjustment parameter through the output result of the charging pile load demand prediction and the charging power adjustment range, improves the response speed and efficiency of the charging pile system, optimizes the charging service quality, and improves the user experience; at the same time, it avoids overloading or idling, optimizes the charging power distribution, improves the energy utilization efficiency, and reduces the operation cost of the charging station. According to the load balancing adjustment parameter, the charging rate can be adjusted according to the real-time demand and system state, which can improve the charging efficiency; dynamic optimization of the basic fault repair rate can reduce the fault repair time and ensure the stability of the charging pile system.

[0043] 4. The application can monitor the energy consumption of the charging pile in real time through the establishment of an energy consumption monitoring model, optimize the energy consumption of the charging pile and control the cost, and improve the energy utilization efficiency; based on the data analysis of the monitoring model, intelligent charging pile management and operation optimization can be realized, the system operation efficiency is improved, the energy consumption cost is reduced, the fault is found in time, the fault is quickly responded and repaired, the fault repair efficiency is improved, the energy waste is reduced, and the user satisfaction is enhanced. BRIEF DESCRIPTION OF DRAWINGS

[0044] Figure 1 The flowchart of the charging pile load supervision method based on AI technology of the application;

[0045] Figure 2 The module diagram of the charging pile load supervision system based on AI technology of the application. DETAILED DESCRIPTION

[0046] In order to better understand the above technical solutions, the above technical solutions will be described in detail in combination with the drawings in the specification and specific embodiments. It should be understood that the specific embodiments described herein are only used to explain the application and not to limit the application.

[0047] Referring to the drawings Figure 1 The embodiment provides a charging pile load supervision method based on an AI technology, and comprises the following steps:

[0048] S1. Real-time collection of operation data of a charging pile and load data of a power grid through sensors installed in the charging pile and the power grid, establishment of a charging pile load demand prediction neural network model, and output of a charging pile load demand prediction result.

[0049] Real-time collection of operation data of a charging pile and load data of a power grid through sensors installed in the charging pile and the power grid, wherein the operation data of the charging pile comprises charging power, charging duration, charging capacity, charging pile state and the like of the charging pile; and the load data of the power grid comprises voltage, current, frequency, active power, reactive power and the like of the power grid. The collected data is preprocessed, including data cleaning, removal of noise data, abnormal data and repeated data, to ensure the accuracy and integrity of the data; specifically, noise data, abnormal data and repeated data generated due to sensor failure, communication interruption and the like are removed, so as to facilitate subsequent data analysis and processing.

[0050] According to the real-time collected charging pile operation data and power grid load data, a charging pile load demand prediction neural network model is established, and features related to charging pile load are extracted from the preprocessed data, including historical charging load data, time features, weather features, power grid load data and the like, and the extracted feature data , , wherein the number of elements in the sample data is taken as input of the charging pile load demand prediction neural network model, and corresponding charging pile load demand prediction data is taken as output; and the charging pile load demand prediction neural network model comprises an input gate, a forget gate and an output gate.

[0051] In the embodiment of the application, is input into the charging pile load demand prediction neural network model and the initial state is The input gate controls the influence degree of new input information on the current state, helps the charging pile system to better receive and process new charging demand information, updates the current load state according to the new information, and accurately predicts future load demand; the specific process is as follows:

[0052] , wherein, represents the neuron output of the input gate; represents the cell state vector at the current time; represents the cell state vector at time ; and represents a change coefficient. Input state representing the current time; 、 Weight value representing self-adaptive learning in the input gate; Hidden state representing the previous time; Bias representing the input gate; Activation function; Input initial state Weight; Decision time parameter;

[0053] The forget gate controls the charging pile management and control system to forget obsolete or no longer relevant load information, determines the influence of information in the previous state on the current state, so that the system can better adapt to new load demand conditions, avoid interference of old information on system decision-making, and the specific process is as follows:

[0054] Among them, Forget gate neuron output; Cell update change coefficient; Forget gate bias vector; Forget gate weight; Corresponding weight at time State sensitive coefficient;

[0055] The output gate controls to generate appropriate output according to the current load state, determines the influence of the current state on the hidden state of the next time step, and effectively manages the load demand of the charging pile, and the specific process is as follows:

[0056] Among them, Output result in the output gate; Time decay coefficient; Bias of neurons in the output gate; Weight of neurons in the output gate.

[0057] Finally, the output result of the charging pile load demand prediction neural network model is represented by

[0058] The charging pile load demand prediction neural network model can better control the flow and memory of information by introducing the gating unit, thereby improving the prediction accuracy of the load demand, optimizing the load management and control of the charging pile and the system operation efficiency; The charging pile system is more intelligent and adaptive, and can better cope with the changing charging demand and system operation environment.

[0059] S2. According to the acquired power grid voltage condition​​ obtaining a power grid voltage deviation, determining a charging power adjustment range of the charging pile, and adjusting the charging time according to the charging power adjustment range.

[0060] In the embodiment of the present application, the power grid voltage deviation is defined as , wherein represents the current actual voltage of the power grid, the upper limit voltage deviation threshold of the normal range is set as , and the upper limit voltage deviation threshold of the warning range is set as ; the current charging power of the charging pile is obtained , the charging power adjustment range of the charging pile is determined according to the power grid voltage deviation, and the specific process is as follows:

[0061] If , it indicates that the voltage deviation is in the normal range, the power grid voltage is relatively stable, the charging power adjustment range of the charging pile is small, the charging power adjustment range is the first charging power adjustment range, and the adjusted charging power is .

[0062] If , it indicates that the voltage deviation is in the warning range, the power grid voltage fluctuates, the charging power of the charging pile needs to be adjusted moderately, the charging power adjustment range is the second charging power adjustment range, and the adjusted charging power is .

[0063] If , it indicates that the voltage deviation exceeds the warning range, the power grid voltage fluctuates greatly, in order to ensure the safety and stability of the power grid and the charging station, the charging power of the charging pile needs to be adjusted greatly, the charging power adjustment range is the third charging power adjustment range, and the adjusted charging power is ; wherein represents the adjustment coefficient when the voltage deviation is in the normal range; represents the adjustment coefficient when the voltage deviation is in the warning range; represents the adjustment coefficient when the voltage deviation exceeds the warning range.

[0064] Meanwhile, the charging time is adjusted according to different charging power adjustment ranges, the electric quantity that needs to be charged under the initial charging power is defined as , and the initial charging time is , and the specific process is as follows:

[0065] , wherein represents the charging power adjustment range; represents the adjusted charging power, .​ represents the first charging time adjustment mode, ;

[0066] Specifically, when the adjusted charging power is , the first charging time adjustment mode is ;

[0067] When the adjusted charging power is , the second charging time adjustment mode is ;

[0068] When the adjusted charging power is , the third charging time adjustment mode is .

[0069] The application adjusts the charging power according to the grid voltage deviation, helps to balance the grid load, improves the grid stability, reduces the grid pressure, and optimizes the energy utilization efficiency; adjusting the charging power can optimize the charging rate in real time according to the grid voltage condition, reduce the charging cost, avoid excessive energy consumption, and improve the energy utilization efficiency; the charging time is flexibly adjusted according to the charging power adjustment range, so that the system is more adaptable and can adjust the charging strategy in combination with the real-time situation; at the same time, the charging time is reasonably adjusted to avoid damage to the charging equipment caused by excessive charging, and the service life of the equipment is prolonged.

[0070] S3. According to the output result of the charging pile load demand prediction , the charging power adjustment range and the charging pile related data information, the charging pile load balancing adjustment parameter is determined; the charging rate and the basic fault repair rate are dynamically optimized according to the charging pile load balancing adjustment parameter.

[0071] In the embodiment of the application, the total number of charging piles is , the total charging power of all charging piles in the station is , represents the current charging power of the first charging pile, , the total remaining power is , represents the current remaining power of the first charging pile, the total maximum charging power of all charging piles is , represents the maximum charging power of the first charging pile, the total maximum power is , represents the maximum power of the first charging pile, and the power remaining ratio is , The relationship between the current total remaining power and the total maximum power is reflected, and the charging pile load prediction deviation is defined , The charging pile load balancing adjustment parameter is determined The specific process is as follows:

[0072] Among them, represents the predicted time period; represents the weight proportion of the charging pile load prediction deviation; represents the weight proportion of the power remaining proportion; represents the weight proportion of the charging power adjustment amplitude; represents the charging power adjustment amplitude.

[0073] The charging rate and the basic fault repair rate are dynamically tuned according to the charging pile load balancing adjustment parameter;

[0074] Specifically, the charging rate refers to the speed at which the charging pile charges the electric vehicle, usually expressed in power; the basic fault repair rate refers to the probability that the charging pile can successfully repair when a basic fault occurs; by dynamically tuning these two parameters, the performance of the system can be optimized according to the changes in the charging pile load balancing adjustment parameter.

[0075] Set the first preset charging pile load balancing adjustment parameter comparison value and the second preset charging pile load balancing adjustment parameter comparison value , and ; compare the charging pile load balancing adjustment parameter with and respectively, and tune the charging rate of the charging pile to obtain , The initial charging rate of the charging pile is , and the specific process is as follows:

[0076] If , the charging rate of the charging pile is adjusted to , that is, the first charging rate ;

[0077] If , the charging rate of the charging pile is adjusted to , that is, the first charging rate ;

[0078] If , the charging rate of the charging pile is adjusted to , that is, the first charging rate ;

[0079] wherein, represents the tuning coefficient corresponding to the first charging rate; represents the tuning coefficient corresponding to the second charging rate; represents the tuning coefficient corresponding to the third charging rate.

[0080] The charging pile load balancing adjustment parameter is calculated according to the output result of the charging pile load demand prediction and the charging power adjustment range. respectively compared with and , the charging pile basic fault repair rate is tuned to obtain , , the charging pile standard basic fault repair rate is , and the specific process is as follows:

[0081] If , the charging pile basic fault repair rate is tuned to , that is, the first basic fault repair rate ;

[0082] If , the charging pile basic fault repair rate is tuned to , that is, the second basic fault repair rate ;

[0083] If , the charging pile basic fault repair rate is tuned to , that is, the third basic fault repair rate ;

[0084] wherein, represents the first basic fault repair rate tuning coefficient; represents the second basic fault repair rate tuning coefficient; represents the third basic fault repair rate tuning coefficient.

[0085] The charging pile load balancing adjustment parameter is calculated according to the output result of the charging pile load demand prediction and the charging power adjustment range.

[0086] S4. According to the tuned charging pile charging rate and the basic fault repair rate, a charging pile energy consumption monitoring model is established to monitor the working condition of the charging pile.

[0087] In this embodiment of the invention, early warning monitoring is performed based on the energy consumption of charging piles, and the monitoring period of the charging pile energy consumption monitoring model is set as follows: Based on the optimized charging rate Based on the number of charging cycles, calculate the theoretical total energy consumption of the charging station under fault-free conditions. , ,in, Indicates the first Duration of each charge ; Calculate the deviation between the actual total energy consumption and the theoretical total energy consumption of the charging pile. , , among which, if This indicates that actual energy consumption is higher than theoretical energy consumption, which may indicate energy waste or other problems. This indicates that the actual energy consumption is lower than the theoretical energy consumption, which may be due to incomplete charging caused by faults during the charging process; based on the optimized charging pile foundation fault repair rate. Calculate the parameters affecting the fault. , .

[0088] Specifically, the comprehensive index of the charging pile energy consumption monitoring model is: The process is as follows:

[0089] in, , These represent weighting coefficients, used to adjust the importance of energy consumption deviation indicators and fault impact indicators in comprehensive monitoring.

[0090] Will Compared with a preset threshold, if If the value is greater than or equal to the threshold, the charging pile is considered to be working well, and energy consumption and fault conditions are within a controllable range; otherwise, a system alarm will be triggered, and management personnel will take appropriate measures in a timely manner.

[0091] This invention establishes an energy consumption monitoring model to monitor the energy consumption of charging piles in real time, optimize energy consumption and control costs, and improve energy utilization efficiency. Based on the data analysis of the monitoring model, intelligent management and operation and maintenance optimization of charging piles can be achieved, improving system operating efficiency, reducing energy costs, timely detecting faults, quickly responding to and repairing faults, improving fault repair efficiency, reducing energy waste, and enhancing user satisfaction.

[0092] See attached document Figure 2 This embodiment provides a charging pile load monitoring system based on AI technology, including the following:

[0093] The charging pile related information collection module, the charging pile load demand prediction module, the charging power adjustment range module, the charging time adjustment module, the charging pile load balancing adjustment parameter determination module, the charging rate optimization module, the basic fault repair rate optimization module, and the charging pile energy consumption monitoring module;

[0094] The charging pile related information collection module collects real-time charging pile related information through sensors installed in the charging pile and the power grid, including charging pile status, charging power, charging time, load conditions, and other data.

[0095] The charging pile load demand prediction module establishes a charging pile load demand prediction neural network model based on real-time collected charging pile operation data and power grid load data, and outputs charging pile load demand prediction results.

[0096] The charging power adjustment range module determines the charging power adjustment range of the charging pile based on the obtained power grid voltage deviation.

[0097] The charging time adjustment module adjusts the charging time according to different charging power adjustment ranges to ensure charging efficiency and load balancing.

[0098] The charging pile load balancing adjustment parameter determination module determines the charging pile load balancing adjustment parameters based on the output results of the charging pile load demand prediction, the charging power adjustment range, and the charging pile related data information.

[0099] The charging rate optimization module compares the charging pile load balancing adjustment parameters with the first preset charging pile load balancing adjustment parameter comparison value and the second preset charging pile load balancing adjustment parameter comparison value, and optimizes the charging rate of the charging pile.

[0100] The basic fault repair rate optimization module compares the charging pile load balancing adjustment parameters with the first preset charging pile load balancing adjustment parameter comparison value and the second preset charging pile load balancing adjustment parameter comparison value, and optimizes the basic fault repair rate of the charging pile.

[0101] The charging pile energy consumption monitoring module monitors the energy consumption of the charging pile, discovers energy consumption abnormalities in a timely manner, and optimizes and adjusts to reduce energy waste and improve energy utilization efficiency.

[0102] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flowcharts and / or blocks Figure 1 means for functionally implementing the steps listed in the flowchart block or blocks.

[0103] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the function specified in the flowchart block or blocks. Figure 1 one or more flowcharts and / or blocks Figure 1 means for functionally implementing the steps listed in the flowchart block or blocks.

[0104] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flowcharts and / or blocks Figure 1 means for functionally implementing the steps listed in the flowchart block or blocks.

[0105] While the preferred embodiments of the application have been described, additional variations and modifications can be made to the embodiments by those skilled in the art once they learn of the basic inventive concepts. Therefore, the appended claims are intended to cover all such additional variations and modifications as fall within the scope of the application.

[0106] The above merely illustrates the technical concept of the present application, and cannot be used to limit the protection scope of the present application. Any modification made according to the technical concept of the present application on the basis of the technical scheme falls within the protection scope of the claims of the present application.

Claims

1. A charging pile load monitoring method based on AI technology, characterized in that, Includes the following steps: Step S1. By using sensors installed in the charging piles and the power grid, real-time data on the operation of the charging piles and the load data of the power grid are collected, a neural network model for predicting the load demand of the charging piles is established, and the predicted load demand of the charging piles is output. Step S2. Determine the charging power adjustment range of the charging pile based on the obtained grid voltage deviation, and adjust the charging time according to the charging power adjustment range; Define the grid voltage deviation as Set the upper limit voltage deviation threshold within the normal range as follows: The upper limit voltage deviation threshold of the warning range is Get the current charging power of the charging station The adjusted charging power is ; if If the charging power adjustment range is the first charging power adjustment range, then the adjusted charging power is ; if If the charging power adjustment range is the second charging power adjustment range, then the adjusted charging power is ; if If the charging power adjustment range is the third charging power adjustment range, then the adjusted charging power is: ; in, This represents the adjustment factor when the voltage deviation is within the normal range; This indicates the adjustment factor when the voltage deviation is within the warning range; This indicates the adjustment factor when the voltage deviation exceeds the warning range; Defined in the initial charging power The amount of electricity needed to charge is The initial charging time is , , in, Indicates the adjustment range of charging power; This indicates the adjusted charging power. ; Indicates the first Charging time adjustment method ; Step S3. Calculate and determine the charging pile load balancing adjustment parameters based on the output results of the charging pile load demand forecast, the charging power adjustment range, and relevant charging pile data. According to the charging pile load balancing adjustment parameters Dynamically optimize charging rate and basic fault recovery rate; Step S4. Based on the optimized charging rate and basic fault repair rate of the charging pile, establish a charging pile energy consumption monitoring model to monitor the working status of the charging pile. The comprehensive index of the charging pile energy consumption monitoring model is: The process is as follows: in, , These represent the weighting coefficients; This indicates the deviation between the actual total energy consumption and the theoretical total energy consumption of a charging station. Indicates the parameters affected by the fault.

2. The charging pile load monitoring method based on AI technology according to claim 1, characterized in that, Step S1 specifically includes: The neural network model for predicting the load demand of charging piles includes an input gate, a forget gate, and an output gate. The input gate updates the current load status based on new information; the forget gate controls the charging pile management system to forget outdated or no longer relevant load information; the output gate controls the generation of output results based on the current load status. , in, This represents the output of the forgetting gate neuron; This indicates the output result of the output gate; Indicates the time decay coefficient; This indicates the bias of the neuron in the output gate; This represents the weight of the neuron in the output gate.

3. The charging pile load monitoring method based on AI technology according to claim 1, characterized in that, Step S3 specifically includes: in, This indicates the load balancing adjustment parameters for charging piles; This indicates the deviation in the charging pile load prediction. Indicates the remaining battery percentage; Indicates the time period for the forecast; This represents the total maximum charging power of all charging stations; This indicates the weighting proportion of the load forecast deviation for charging piles; The weighting percentage represents the remaining battery capacity. This indicates the weighting ratio of the charging power adjustment range.

4. The charging pile load monitoring method based on AI technology according to claim 3, characterized in that, Step S3 specifically includes: According to the charging pile load balancing adjustment parameters Dynamically optimize charging rate and basic fault recovery rate; Set the first preset charging pile load balancing adjustment parameter comparison value Comparison of parameters between the second preset charging pile load balancing adjustment parameters ,and Adjust the load balancing parameters of the charging piles. respectively with and By comparing and optimizing the charging pile charging rate and the charging pile basic fault repair rate, the optimized charging pile charging rate was obtained. Optimized charging pile foundation fault repair rate .

5. A charging pile load monitoring system based on AI technology, applied to the charging pile load monitoring method based on AI technology as described in claim 1, characterized in that, Includes the following: The system includes modules for collecting charging pile information, predicting charging pile load demand, adjusting charging power, adjusting charging time, determining charging pile load balancing adjustment parameters, optimizing charging rate, optimizing basic fault repair rate, and monitoring charging pile energy consumption. The charging pile related information acquisition module collects relevant information about the charging pile in real time through sensors installed in the charging pile and the power grid. The charging pile load demand prediction module establishes a neural network model for predicting charging pile load demand based on real-time collected operating data of charging piles and load data of the power grid, and outputs the charging pile load demand prediction results. The charging power adjustment module determines the charging power adjustment range of the charging pile based on the obtained grid voltage deviation. The charging time adjustment module adjusts the charging time according to different charging power adjustment ranges to ensure charging efficiency and load balance. The charging pile load balancing adjustment parameter determination module determines the charging pile load balancing adjustment parameters based on the output results of the charging pile load demand prediction, the charging power adjustment range, and relevant charging pile data. The charging rate optimization module compares the charging pile load balancing adjustment parameters with the first preset comparison parameter value and the second preset comparison parameter value respectively to optimize the charging rate of the charging pile. The basic fault repair rate optimization module compares the charging pile load balancing adjustment parameters with the first preset comparison parameter value and the second preset comparison parameter value respectively to optimize the basic fault repair rate of the charging pile. The charging pile energy consumption monitoring module monitors the energy consumption of the charging pile, promptly detects energy consumption anomalies, and takes appropriate measures.

Images