Charging pile load supervision method and system based on AI technology

Abstract

The invention relates to the field of charging pile load supervision, in particular to a charging pile load supervision method and system based on the AI technology, and the method comprises the steps: collecting the operation data of a charging pile and the load data of a power grid in real time through sensors installed in the charging pile and the power grid, and building a charging pile load demand prediction neural network model; outputting a charging pile load demand prediction result; the charging power adjustment amplitude of the charging pile is determined according to the obtained power grid voltage deviation, and the charging time is adjusted according to the charging power adjustment amplitude; according to the output result of the charging pile load demand prediction, the charging power adjustment amplitude and the related data information of the charging pile, calculating and determining a charging pile load balance adjustment parameter; and according to the optimized charging rate of the charging pile and the basic fault repair rate, establishing a charging pile energy consumption monitoring model, and monitoring the working condition of the charging pile.

Description

Technical Field

[0001] The present invention relates to the field of charging pile load supervision, and in particular to a charging pile load supervision method and system based on AI technology. Background Art

[0002] With the popularity of electric vehicles, the number of charging piles is also increasing. However, the problem of load management of charging piles is becoming increasingly prominent. Irrational use of charging piles may cause excessive load on the local power grid, affect the stability and power supply quality of the power grid, and may even cause safety accidents. Traditional charging pile load management methods are mainly based on manual experience and fixed rules, which makes it difficult to respond to complex and changing charging needs and power grid load conditions in real time and accurately.

[0003] With the continuous development of artificial intelligence, great progress has been made in the load monitoring of charging piles, but the existing technology still has the following problems: when charging piles and other equipment are running at high power at the same time, it causes unbalanced load on the power grid; there is a lack of ability to adjust the charging power in real time according to the voltage conditions of the power grid, and the charging cost cannot be effectively controlled; the stability of the system cannot be guaranteed, and the economic benefits of the charging system are affected.

[0004] Therefore, a charging pile load supervision method and system based on AI technology is needed. Summary of the invention

[0005] The present invention provides a charging pile load supervision method and system based on AI technology, which aims to monitor and analyze the operating status 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, and reduce operating costs, thereby promoting the sustainable development and intelligent process of the charging industry.

[0006] The technical solution of the present invention is specifically as follows: A charging pile load supervision method based on AI technology includes the following steps: Step S1. Through the sensors installed in the charging pile and the power grid, the operation data of the charging pile and the load data of the power grid are collected in real time, a charging pile load demand prediction neural network model is established, and the charging pile load demand prediction result is output; Step S2. Determine the charging power adjustment range of the charging pile according to the obtained grid voltage deviation, and adjust the charging time according to the charging power adjustment range; Step S3. Calculate and determine 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; Step S4. According to the optimized charging rate and basic fault repair rate of the charging pile, a charging pile energy consumption monitoring model is established to monitor the working condition of the charging pile.

[0007] Step S1 specifically includes: The charging pile load demand prediction neural network model includes input gate, forget gate, and output gate; In the input gate, the current load status is updated according to the new information; 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 according to the current load status. , in, represents the output of the forget gate neuron; Represents the output result in the output gate; represents the time attenuation coefficient; represents the bias of the neuron in the output gate; Represents the weight of the neuron in the output gate.

[0008] Step S2 specifically includes: The grid voltage deviation is defined as , set the normal range upper limit voltage deviation threshold to , the upper limit voltage deviation threshold of the warning range is , get the current charging power of the charging pile ; The adjusted charging power is ; if , the charging power adjustment range is the first charging power adjustment range, then the adjusted charging power is ; if , the charging power adjustment range is the second charging power adjustment range, then the adjusted charging power is ; if , the charging power adjustment range is the third charging power adjustment range, then the adjusted charging power is ; in, Indicates the adjustment coefficient when the voltage deviation is within the normal range; Indicates the adjustment coefficient when the voltage deviation is within the warning range; Indicates the adjustment coefficient when the voltage deviation exceeds the warning range.

[0009] Further, step S2 specifically includes: defining the initial charging power The amount of electricity required to be charged is , the initial charging time is , , in, Indicates the adjustment range of charging power; Indicates the adjusted charging power, ; Indicates Charging time adjustment method, .

[0010] Step S3 specifically includes: in, Indicates the load balancing adjustment parameters of the charging pile; Indicates the prediction deviation of charging pile load; Indicates the remaining power ratio; Indicates the time period of the forecast; Indicates the total maximum charging power of all charging piles; Indicates the weight ratio of the charging pile load prediction deviation; The weight ratio indicating the remaining power ratio; Indicates the weight ratio of the charging power adjustment range.

[0011] Further, step S3 specifically includes: Adjust parameters according to charging pile load balance Dynamically optimize charging rate and basic fault repair rate; Set the first preset charging pile load balancing adjustment parameter comparison parameter Compare the parameters with the second preset charging pile load balancing adjustment parameters ,and ; Adjust the charging pile load balance parameters Respectively and By comparison, the charging rate of the charging pile and the basic fault repair rate of the charging pile are optimized, and the optimized , .

[0012] The comprehensive index of the charging pile energy consumption monitoring model in step S4 is , the process is as follows: in, , Respectively represent weight coefficients; Indicates the deviation between the actual total energy consumption of the charging pile and the theoretical total energy consumption; Indicates the fault impact parameter.

[0013] A charging pile load supervision system based on AI technology, including the following contents: Charging pile related information collection module, charging pile load demand prediction module, charging power adjustment range module, charging time adjustment module, charging pile load balancing adjustment parameter determination module, charging rate tuning module, basic fault repair rate tuning module, charging pile energy consumption monitoring module; The charging pile related information collection module collects the charging pile related information in real time through sensors installed in the charging pile and the power grid; The charging pile load demand prediction module establishes a charging pile load demand prediction neural network model based on the real-time collection of charging pile operation data and power grid load data, and outputs the charging pile load demand prediction results; The charging power adjustment range module obtains the grid voltage deviation according to the acquired grid voltage condition and determines the charging power adjustment range of the charging pile; 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 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 rate tuning module compares the charging pile load balancing adjustment parameter with the first preset comparison parameter and the second preset comparison parameter respectively, and tunes the charging rate of the charging pile; A basic fault repair rate tuning module compares the charging pile load balancing adjustment parameter with the first preset comparison parameter value and the second preset comparison parameter value respectively, and optimizes the charging pile basic fault repair rate; The charging pile energy consumption monitoring module monitors the energy consumption of the charging pile, detects abnormal energy consumption in time and takes measures.

[0014] Beneficial effects: 1. By introducing the gating unit, 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 management and control of the charging pile and the system operation efficiency; making the charging pile system more intelligent and adaptive, and able to better cope with the ever-changing charging demand and system operation environment.

[0015] 2. The present invention adjusts the charging power through the grid voltage deviation, helps to balance the grid load, improve the grid stability, reduce the grid pressure, and optimize the energy utilization efficiency; the charging power can be adjusted to optimize the charging rate in real time according to the grid voltage conditions, reduce the charging cost, avoid excessive energy consumption, and improve the energy utilization efficiency; the charging time can be flexibly adjusted according to the charging power adjustment range, so that the system is more adaptable and can adjust the charging strategy according to the real-time situation; at the same time, the charging time is reasonably adjusted to avoid damage to the charging equipment caused by overcharging and extend the service life of the equipment.

[0016] 3. The present invention accurately calculates the charging pile load balancing adjustment parameters through the output results of the charging pile load demand prediction and the charging power adjustment range, thereby improving the response speed and efficiency of the charging pile system, optimizing the charging service quality, and enhancing the user experience; at the same time, it avoids overload or idle conditions, optimizes the charging power distribution, improves energy utilization efficiency, and reduces the operating costs of charging stations. The charging rate can be adjusted according to the load balancing adjustment parameters, and can be optimized according to real-time demand and system status to improve charging efficiency; dynamic tuning of the basic fault repair rate can reduce the fault repair time and ensure the stability of the charging pile system.

[0017] 4. The present invention can monitor the energy consumption of charging piles in real time by establishing an energy consumption monitoring model, optimize the energy consumption and control the cost of charging piles, and improve energy utilization efficiency; based on data analysis of the monitoring model, intelligent charging pile management and operation and maintenance optimization can be realized, the system operation efficiency can be improved, the energy consumption cost can be reduced, faults can be discovered in time, faults can be responded to and repaired quickly, the fault repair efficiency can be improved, energy waste can be reduced, and user satisfaction can be enhanced. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 This is a flow chart of a charging pile load supervision method based on AI technology of the present invention; Figure 2 This is a module diagram of a charging pile load supervision system based on AI technology of the present invention. DETAILED DESCRIPTION

[0019] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods. It should also 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.

[0020] See attached Figure 1 This embodiment provides a charging pile load supervision method based on AI technology, including the following steps: S1. Through the sensors installed in the charging piles and the power grid, the operation data of the charging piles and the load data of the power grid are collected in real time, a neural network model for predicting the load demand of the charging piles is established, and the prediction results of the load demand of the charging piles are output.

[0021] The sensors installed in the charging pile and the power grid collect the operation data of the charging pile and the load data of the power grid in real time. The operation data of the charging pile includes the charging power, charging time, charging power, charging pile status, etc. of the charging pile; the load data of the power grid includes the voltage, current, frequency, active power, reactive power, etc. of the power grid. The collected data is preprocessed, including data cleaning, removal of noise data, abnormal data and duplicate data, to ensure the accuracy and integrity of the data; specifically, the noise data, abnormal data and duplicate data generated by sensor failure, communication interruption, etc. are removed for subsequent data analysis and processing.

[0022] Based on the real-time collected charging pile operation data and grid load data, a charging pile load demand prediction neural network model is established. The features related to the charging pile load are extracted from the preprocessed data, including historical charging load data, time features, meteorological features, grid load data, etc. , It represents the number of elements in the sample data, which is used as the input of the charging pile load demand prediction neural network model, and the corresponding charging pile load demand prediction data is used as the output; and the charging pile load demand prediction neural network model includes an input gate, a forget gate, and an output gate.

[0023] In the embodiment of the present invention, Input into the charging pile load demand prediction neural network model and the initial state is , in the input gate, controls the impact 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: in, represents the neuron output of the input gate; Represents the cell state vector at the current moment; Indicates at time The cell state vector of represents the coefficient of variation; Indicates the input status at the current moment; , Represents the weight value adaptively learned in the input gate; Indicates the hidden state at the previous moment; Represents the bias corresponding to the input gate; represents the activation function; Indicates the initial state of the input Weight; Indicates the decision time parameter; The forget gate controls the charging pile management and control system to forget outdated or no longer relevant load information, which determines the impact of the information in the previous state on the current state, so that the system can better adapt to the new load demand situation and avoid the interference of old information on system decision-making. The specific process is as follows: in, represents the output of the forget gate neuron; represents the coefficient of variation of cell renewal; Represents the forget gate bias vector; represents the weight of the forget gate; Indicates at time The corresponding weights; represents the state sensitivity coefficient; The output gate control generates appropriate outputs according to the current load state, determines the impact of the current state on the hidden state of the next time step, and effectively manages the load demand of the charging pile. The specific process is as follows: in, Represents the output result in the output gate; represents the time attenuation coefficient; represents the bias of the neuron in the output gate; Represents the weight of the neuron in the output gate.

[0024] Finally use It represents the output result of the neural network model for predicting the load demand of charging piles, and provides data support for the subsequent charging pile load supervision process.

[0025] By introducing a gating unit, the present invention enables the charging pile load demand prediction neural network model to better control the flow and memory of information, thereby improving the prediction accuracy of load demand and optimizing the load control and system operation efficiency of the charging pile; making the charging pile system more intelligent and adaptive, and better able to cope with the ever-changing charging demand and system operation environment.

[0026] S2. According to the obtained grid voltage The grid voltage deviation is obtained, the charging power adjustment range of the charging pile is determined, and the charging time is adjusted according to the charging power adjustment range.

[0027] In the embodiment of the present invention, the grid voltage deviation is defined as , ,in, Indicates the actual current voltage of the power grid, and sets the upper limit voltage deviation threshold of the normal range to , the upper limit voltage deviation threshold of the warning range is ; Get the current charging power of the charging pile , the charging power adjustment range of the charging pile is determined according to the grid voltage deviation. The specific process is as follows: if , indicating that the voltage deviation is within the normal range, the grid voltage is relatively stable, the charging power adjustment range of the charging pile is small, and the charging power adjustment range is the first charging power adjustment range. The adjusted charging power is ; if , indicating that the voltage deviation is within the warning range, the grid voltage fluctuates, and the charging power of the charging pile needs to be adjusted appropriately. The charging power adjustment range is the second charging power adjustment range. The adjusted charging power is ; if , indicating that the voltage deviation exceeds the warning range and the grid voltage fluctuates greatly. In order to ensure the safety and stability of the grid and charging stations, it is necessary to significantly adjust the charging power of the charging pile. The charging power adjustment range is the third charging power adjustment range. The adjusted charging power is ;in, Indicates the adjustment coefficient when the voltage deviation is within the normal range; Indicates the adjustment coefficient when the voltage deviation is within the warning range; Indicates the adjustment coefficient when the voltage deviation exceeds the warning range.

[0028] At the same time, the charging time is adjusted according to the different charging power adjustment ranges, and the initial charging power is defined. The amount of electricity required to be charged is , the initial charging time is , the specific process is as follows: , in, Indicates the adjustment range of charging power; Indicates the adjusted charging power, ; Indicates Charging time adjustment method, ; Specifically, when the adjusted charging power is When , it corresponds to the first charging time adjustment method, and the first charging time adjustment method is ; When the adjusted charging power is When , the corresponding second charging time adjustment method is: ; When the adjusted charging power is When , it corresponds to the third charging time adjustment method, and the third charging time adjustment method is .

[0029] The present invention adjusts the charging power through the grid voltage deviation, helps to balance the grid load, improve the grid stability, reduce the grid pressure, and optimize the energy utilization efficiency; the charging power can be adjusted to optimize the charging rate in real time according to the grid voltage conditions, 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 according to the real-time situation; at the same time, the charging time is reasonably adjusted to avoid damage to the charging equipment caused by overcharging, thereby extending the service life of the equipment.

[0030] S3. Output results based on charging pile load demand prediction , charging power adjustment range and charging pile related data information, determine the charging pile load balancing adjustment parameters; determine the dynamic adjustment of charging rate and basic fault repair rate according to the charging pile load balancing adjustment parameters.

[0031] In the embodiment of the present invention, the total number of charging piles is set to , the total charging power of all charging piles in the station is , Indicates The current charging power of each charging pile, The total remaining power is , Indicates The current remaining power of the charging piles, the total maximum charging power of all charging piles is , Indicates The maximum charging power of the charging piles, the total maximum power is , Indicates The maximum power of the charging pile, the remaining power ratio is , It reflects the relationship between the current total remaining power and the total maximum power, and defines the charging pile load prediction deviation , ; Determine the charging pile load balancing adjustment parameters , the specific process is as follows: in, Indicates the time period of the forecast; Indicates the weight ratio of the charging pile load prediction deviation; The weight ratio indicating the remaining power ratio; Indicates the weight ratio of the charging power adjustment range; Indicates the charging power adjustment range.

[0032] Dynamically optimize the charging rate and basic fault repair rate according to the load balancing adjustment parameters of the charging pile; 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 be successfully repaired when a basic fault occurs; by dynamically tuning these two parameters, the system performance can be optimized according to the changes in the load balancing adjustment parameters of the charging pile.

[0033] Set the first preset charging pile load balancing adjustment parameter comparison parameter Compare the parameters with the second preset charging pile load balancing adjustment parameters ,and ; Adjust the charging pile load balance parameters Respectively and Compare and optimize the charging rate of the charging pile to obtain , , the initial charging rate of the charging pile is , the specific process is as follows: if , then adjust the charging rate of the charging pile to , i.e. the first charging rate ; if , then adjust the charging rate of the charging pile to , i.e. the first charging rate ; if , then adjust the charging rate of the charging pile to , i.e. the first charging rate ; in, represents a tuning coefficient corresponding to the first charging rate; represents a tuning coefficient corresponding to the second charging rate; Indicates the tuning coefficient corresponding to the third charging rate.

[0034] Adjust the parameters of charging pile load balance Respectively and By comparison, the basic fault repair rate of charging piles is optimized, and the , The standard basic fault repair rate of charging pile is , the specific process is as follows: if , then the charging pile basic fault repair rate is optimized to , that is, the first basic fault repair rate ; if , then the charging pile basic fault repair rate is optimized to , which is the second basic fault repair rate ; if , then the charging pile basic fault repair rate is optimized to , that is, the third basic fault repair rate ; in, Indicates the first basic fault repair rate tuning coefficient; Indicates the second basic fault repair rate tuning coefficient; Indicates the third basic fault repair rate tuning coefficient.

[0035] The present invention accurately calculates the charging pile load balancing adjustment parameters through the output results of the charging pile load demand prediction and the charging power adjustment range, thereby improving the response speed and efficiency of the charging pile system, optimizing the charging service quality, and enhancing the user experience; at the same time, it avoids overload or idle conditions, optimizes the charging power distribution, improves energy utilization efficiency, and reduces the operating costs of charging stations. The charging rate can be adjusted according to the load balancing adjustment parameters, and can be optimized according to real-time demand and system status to improve charging efficiency; dynamic tuning of the basic fault repair rate can reduce the fault repair time and ensure the stability of the charging pile system.

[0036] S4. According to the optimized charging rate and basic fault repair rate of the charging pile, a charging pile energy consumption monitoring model is established to monitor the working condition of the charging pile.

[0037] In the embodiment of the present invention, early warning monitoring is performed through the energy consumption of the charging pile, and the monitoring period of the charging pile energy consumption monitoring model is set to , according to the optimized charging rate and charging times, calculate the theoretical total energy consumption of the charging pile under no fault conditions , ,in, Indicates Duration of a charge, ; Calculate the deviation between the actual total energy consumption of the charging pile and the theoretical total energy consumption , , where if , indicating that the actual energy consumption is higher than the theoretical energy consumption, there may be energy waste or other problems. , indicating that the actual energy consumption is lower than the theoretical energy consumption, which may be due to a fault during the charging process leading to incomplete charging, etc. According to the basic fault repair rate of the charging pile after optimization , calculate the fault impact parameters , .

[0038] Specifically, the comprehensive indicators of the charging pile energy consumption monitoring model are: , the process is as follows: in, , They represent weight coefficients, respectively, which are used to adjust the importance of energy consumption deviation index and fault impact index in comprehensive monitoring.

[0039] Will Compared with the pre-set threshold, if If it is greater than or equal to the threshold, the charging pile is considered to be working well, and the energy consumption and fault conditions are within the controllable range; otherwise, the system alarm is issued and the management personnel take corresponding measures in time.

[0040] The present invention can monitor the energy consumption of charging piles in real time by establishing an energy consumption monitoring model, optimize the energy consumption of charging piles and control costs, and improve energy utilization efficiency; data analysis based on the monitoring model can realize intelligent charging pile management and operation and maintenance optimization, improve system operation efficiency, reduce energy consumption costs, discover faults in time, respond to and repair faults quickly, improve fault repair efficiency, reduce energy waste, and enhance user satisfaction.

[0041] Refer to the attached Figure 2 , this embodiment provides a charging pile load supervision system based on AI technology, including the following contents: Charging pile related information collection module, charging pile load demand prediction module, charging power adjustment range module, charging time adjustment module, charging pile load balancing adjustment parameter determination module, charging rate tuning module, basic fault repair rate tuning module, charging pile energy consumption monitoring module; The charging pile related information collection module collects the relevant information of the charging pile in real time through sensors installed in the charging pile and the power grid, including the status of the charging pile, charging power, charging time, load conditions and other data; The charging pile load demand prediction module establishes a charging pile load demand prediction neural network model based on the real-time collection of charging pile operation data and power grid load data, and outputs the charging pile load demand prediction results; The charging power adjustment range module obtains the grid voltage deviation according to the acquired grid voltage condition and determines the charging power adjustment range of the charging pile; 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 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 rate tuning module compares the charging pile load balancing adjustment parameter with the first preset charging pile load balancing adjustment parameter comparison parameter and the second preset charging pile load balancing adjustment parameter comparison parameter to optimize the charging pile charging rate; The basic fault repair rate tuning module compares the charging pile load balancing adjustment parameter with the first preset charging pile load balancing adjustment parameter comparison parameter value and the second preset charging pile load balancing adjustment parameter comparison parameter value, and optimizes the charging pile basic fault repair rate; The charging pile energy consumption monitoring module monitors the energy consumption of the charging pile, promptly detects energy consumption anomalies and makes optimization adjustments to reduce energy waste and improve energy utilization efficiency.

[0042] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0043] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0044] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0045] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0046] The above contents are only for explaining the technical idea of ​​the present invention and cannot be used to limit the protection scope of the present invention. Any changes made on the basis of the technical solution in accordance with the technical idea proposed by the present invention shall fall within the protection scope of the claims of the present invention.

Claims

1. A charging pile load supervision method based on AI technology, characterized in that: The following steps are involved: Step S1. Through the sensors installed in the charging pile and the power grid, the operation data of the charging pile and the load data of the power grid are collected in real time, a charging pile load demand prediction neural network model is established, and the charging pile load demand prediction result is output; Step S2. Determine the charging power adjustment range of the charging pile according to the obtained grid voltage deviation, and adjust the charging time according to the charging power adjustment range; Step S3. Calculate and determine 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; Step S4. According to the optimized charging rate and basic fault repair rate of the charging pile, a charging pile energy consumption monitoring model is established to monitor the working condition of the charging pile.

2. The charging pile load supervision method based on AI technology according to claim 1 is characterized in that: The step S1 specifically includes: The charging pile load demand prediction neural network model includes input gate, forget gate, and output gate; In the input gate, the current load status is updated according to the new information; 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 according to the current load status. ,in, represents the output of the forget gate neuron; Represents the output result in the output gate; represents the time attenuation coefficient; represents the bias of the neuron in the output gate; Represents the weight of the neuron in the output gate.

3. The charging pile load supervision method based on AI technology according to claim 1 is characterized in that: The step S2 specifically includes: The grid voltage deviation is defined as , set the normal range upper limit voltage deviation threshold to , the upper limit voltage deviation threshold of the warning range is , get the current charging power of the charging pile ; The adjusted charging power is ; if , the charging power adjustment range is the first charging power adjustment range, then the adjusted charging power is ; if , the charging power adjustment range is the second charging power adjustment range, then the adjusted charging power is ; if , the charging power adjustment range is the third charging power adjustment range, then the adjusted charging power is ; in, Indicates the adjustment coefficient when the voltage deviation is within the normal range; Indicates the adjustment coefficient when the voltage deviation is within the warning range; Indicates the adjustment coefficient when the voltage deviation exceeds the warning range.

4. The charging pile load supervision method based on AI technology according to claim 3 is characterized in that: The step S2 specifically includes: defining the initial charging power The amount of electricity required to be charged is , the initial charging time is , , in, Indicates the adjustment range of charging power; Indicates the adjusted charging power, ; Indicates Charging time adjustment method, .

5. The charging pile load supervision method based on AI technology according to claim 1 is characterized in that: The step S3 specifically includes: in, Indicates the load balancing adjustment parameters of the charging pile; Indicates the prediction deviation of charging pile load; Indicates the remaining power ratio; Indicates the time period of the forecast; Indicates the total maximum charging power of all charging piles; Indicates the weight ratio of the charging pile load prediction deviation; The weight ratio indicating the remaining power ratio; Indicates the weight ratio of the charging power adjustment range.

6. The charging pile load supervision method based on AI technology according to claim 5 is characterized in that: The step S3 specifically includes: Adjust parameters according to charging pile load balance Dynamically optimize charging rate and basic fault repair rate; Set the first preset charging pile load balancing adjustment parameter comparison parameter Compare the parameters with the second preset charging pile load balancing adjustment parameters ,and ; Adjust the charging pile load balance parameters Respectively and By comparison, the charging rate of the charging pile and the basic fault repair rate of the charging pile are optimized, and the optimized , .

7. The charging pile load supervision method based on AI technology according to claim 1 is characterized in that: The comprehensive index of the charging pile energy consumption monitoring model in step S4 is , the process is as follows: in, , Represent the weight coefficients Indicates the deviation between the actual total energy consumption of the charging pile and the theoretical total energy consumption; Indicates the fault impact parameter.

8. A charging pile load supervision system based on AI technology, applied to the charging pile load supervision method based on AI technology described in claim 1, characterized in that: Includes the following: Charging pile related information collection module, charging pile load demand prediction module, charging power adjustment range module, charging time adjustment module, charging pile load balancing adjustment parameter determination module, charging rate tuning module, basic fault repair rate tuning module, charging pile energy consumption monitoring module; The charging pile related information collection module collects the relevant information of 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 charging pile load demand prediction neural network model based on real-time collection of charging pile operation data and power grid load data, and outputs a charging pile load demand prediction result; The charging power adjustment range module obtains the grid voltage deviation according to the acquired grid voltage condition and determines the charging power adjustment range of the charging pile; 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 parameter 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 rate tuning module compares the charging pile load balancing adjustment parameter with the first preset comparison parameter and the second preset comparison parameter respectively, and tunes the charging rate of the charging pile; The basic fault repair rate tuning module compares the charging pile load balancing adjustment parameter with the first preset comparison parameter value and the second preset comparison parameter value respectively, and optimizes the charging pile basic fault repair rate; The charging pile energy consumption monitoring module monitors the energy consumption of the charging pile, detects energy consumption anomalies in a timely manner and takes measures.

Images