Charging pile cooperative control method and system

Abstract

The invention provides a charging pile cooperative control method and system. According to the method, charging migration sequence data of an electric vehicle user is acquired, and a migration preference matrix and charging interval distribution of cross-service-area charging piles are analyzed and generated; and synchronously measuring sound wave delay data and a charging pile voltage fluctuation sequence. Converting sound wave delay into a delay gradient matrix, and combining the voltage fluctuation correlation coefficient matrix to generate an environment correlation degree matrix. And aggregating the over-threshold charging piles as a charging cluster based on the matrix, and outputting boundary coordinates. And the migration preference, the charging interval distribution and the boundary coordinates are input into a prediction model, a future vehicle density distribution diagram and a predicted value of the average stay duration are output, and a load priority vector is calculated in combination with the environment correlation degree matrix. And by taking the vector as a weight, distributing the total power of the service area to each charging pile, and issuing a power regulation instruction. According to the invention, dynamic matching of power distribution of the power grid, a real physical environment and user requirements is realized.

Description

Technical Field

[0001] This application relates to the technical fields of smart grid and new energy vehicle infrastructure, and particularly to a method and system for collaborative control of charging piles. Background Art

[0002] In scenarios where electric vehicles are concentrated for charging, such as highway service areas and urban fast charging stations, due to the spatio-temporal imbalance of user charging behaviors, there are often resource mismatch problems where some charging piles are queuing and congested while adjacent charging piles are idle. There is an urgent need for a collaborative control method that can perceive the physical environment correlation characteristics between charging piles, accurately predict dynamic charging demands, and automatically optimize the distribution strategy based on the available power of the power grid to improve the overall charging efficiency of the service area and the stability of the power grid.

[0003] Currently, a typical solution uses a time series prediction model based on historical charging data. By collecting the hourly charging power records of each charging pile in the past week, a long short-term memory neural network is trained to predict the single-pile load demand in the future period, and then more power is preferentially allocated to high-load charging piles according to the prediction values. This solution replaces the traditional manual scheduling mode through machine learning and power pre-allocation mechanisms, achieving basic intelligent control.

[0004] However, this solution does not fully consider the physical environment constraints between charging piles, such as the differences in signal propagation characteristics between devices caused by the distribution of obstacles, and the coupling effect of power grid fluctuations in adjacent charging piles; at the same time, it only relies on historical charging volume data and lacks dynamic analysis of user migration path preferences and charging interval distributions, resulting in insufficient accuracy of the prediction model in scenarios of sudden traffic migration. Summary of the Invention

[0005] This application provides a method and system for collaborative control of charging piles to solve the problem of insufficient accuracy in scenarios of sudden traffic migration in the prior art.

[0006] In a first aspect, this application provides a method for collaborative control of charging piles, including: Obtaining the charging migration sequence data of electric vehicle users, parsing the charging migration sequence data to obtain the migration preference matrix and charging interval distribution of users across service area charging piles within a continuous time window, measuring the acoustic wave delay data set at a fixed distance between charging piles, and synchronously collecting the voltage fluctuation value sequences of each charging pile; Converting the acoustic wave delay data set into a delay gradient matrix, and at the same time calculating the correlation coefficient matrix between the voltage fluctuation value sequences, and fusing the delay gradient matrix and the correlation coefficient matrix to generate an environmental correlation degree matrix between charging piles; According to the environmental correlation degree matrix, dynamically aggregating the charging piles with index values exceeding a set threshold into charging cluster sets through a clustering algorithm, and outputting the boundary coordinates of each charging cluster; Input the migration preference matrix, charging interval distribution, and the boundary coordinates into a prediction model together to output the vehicle density distribution map and the predicted average residence duration of each charging cluster in a future time window. Based on the vehicle density distribution map, the predicted average residence duration, and the environmental correlation matrix of the charging cluster set, calculate the load priority vector of each charging cluster; Using the load priority vector as the allocation weight, allocate the total available power of the service area proportionally to each charging pile, generate a charging pile power adjustment instruction and issue it for execution.

[0007] Optionally, input the migration preference matrix, charging interval distribution, and the boundary coordinates into a prediction model together to output the vehicle density distribution map and the predicted average residence duration of each charging cluster in a future time window. Based on the vehicle density distribution map, the predicted average residence duration, and the environmental correlation matrix of the charging cluster set, calculate the load priority vector of each charging cluster, including: Extract the boundary coordinates of each charging cluster, obtain the changing trend of the number of regions where the user group enters and exits the boundary coordinates within consecutive time windows from the migration preference matrix, and extract the interval characteristics of adjacent charging events in the charging interval distribution; Input the boundary coordinates, number changing trend, and interval characteristics into a time series prediction model to output the vehicle density distribution map per unit area and the predicted average residence duration of the charging cluster set in a future time window; Extract the highest density value from the vehicle density distribution map, multiply the highest density value by the predicted average residence duration to obtain the demand heat value, and take the average of the environmental correlation scores of all charging pile combinations within the charging cluster set to obtain the environmental correlation intensity; Superimpose the demand heat value and the environmental correlation intensity according to a preset weight to obtain a comprehensive load index, and normalize the comprehensive load index of all charging cluster sets to obtain the load priority vector.

[0008] Optionally, convert the acoustic wave delay data set into a delay gradient matrix, and at the same time calculate the correlation coefficient matrix between the voltage fluctuation value sequences, and fuse the delay gradient matrix and the correlation coefficient matrix to generate the environmental correlation matrix between charging piles, including: Take any two charging piles as a charging pile combination, and obtain the multiple acoustic wave delay data sets at a fixed distance between the charging pile combinations; Calculate the difference between the maximum delay value and the minimum delay value in the acoustic wave delay data as the acoustic wave delay variation amplitude, and generate a delay gradient matrix according to the acoustic wave delay variation amplitude; Obtain the voltage fluctuation value sequences of the charging pile combinations within the same time window, and calculate the correlation coefficient matrix of the voltage fluctuation value sequences; Weightedly superimpose the values in the delay gradient matrix and the correlation coefficient matrix according to a preset ratio to generate the environmental correlation score of this group of charging piles, and arrange the environmental correlation scores of all the charging pile combinations to form an environmental correlation degree matrix.

[0009] Optionally, weightedly superimpose the values in the delay gradient matrix and the correlation coefficient matrix according to a preset ratio to generate the environmental correlation score of this group of charging piles, and arrange the environmental correlation scores of all the charging pile combinations to form an environmental correlation degree matrix, including: Extract the amplitude of the acoustic wave delay change corresponding to the charging pile combination from the delay gradient matrix, multiply the amplitude of the acoustic wave delay change by a first preset coefficient to obtain an acoustic wave influence component; Extract the fluctuation correlation degree value of two groups of voltage fluctuation value sequences of this charging pile combination from the correlation coefficient matrix, multiply the fluctuation correlation degree value by a second preset coefficient to obtain a voltage influence component; Add the acoustic wave influence component and the voltage influence component to generate the environmental correlation score of the charging pile combination, and arrange the environmental correlation scores of all charging pile combinations in the order of the charging pile numbers as a symmetric square matrix to form the environmental correlation degree matrix.

[0010] Optionally, input the boundary coordinates, quantity change trend and interval characteristics into a time series prediction model, and output the vehicle density distribution map per unit area and the predicted value of the average stay duration of the charging cluster in the future time window, including: Calculate the covered area of the rectangular area surrounded by the boundary coordinates of each charging cluster, convert the quantity change trend into a user quantity change sequence at the same time of each day, and process the interval characteristics into the typical time difference between adjacent charging behaviors; Combine the covered area, user quantity change sequence and typical time difference into an input data block, arrange the input data block in chronological order and send it into the time series prediction model, and obtain the total number of vehicles and the average vehicle occupancy duration values in each future time period through this model; Divide the total number of vehicles in each future time period by the covered area corresponding to the time period to form a sequence of the number of vehicles per unit area arranged in chronological order as the vehicle density distribution map, and use the average vehicle occupancy duration value as the predicted value of the average stay duration.

[0011] Optionally, use the load priority vector as the allocation weight, allocate the total available power of the service area to each charging pile according to a ratio, generate a charging pile power adjustment instruction and send it down for execution, including: Obtain the total available power value of the service area power grid, extract the weight coefficient of each charging cluster from the load priority vector, and multiply the available power value by the weight coefficient of each charging cluster to obtain the power allocation value of each charging cluster: Obtain the total number of charging piles in each charging cluster, divide the power distribution value by the total number of charging piles to obtain the power setting value for each charging pile; Create an adjustment instruction containing an identifier and the power setting value for each charging pile, and send the adjustment instruction to the corresponding charging pile controller to execute power adjustment.

[0012] Optionally, according to the environment correlation matrix, dynamically aggregate the charging piles with index values exceeding the set threshold into a charging cluster set through a clustering algorithm, and output the boundary coordinates of each charging cluster, including: Set the minimum connection threshold of the environment correlation score in the environment correlation matrix, and initialize each charging pile as an independent charging cluster; Identify the charging pile association relationships in the environment correlation matrix that are greater than the minimum connection threshold, extract the two charging piles corresponding to each satisfied association relationship. If the two charging piles belong to different charging clusters, merge them into a charging cluster set, and iteratively execute the operation until no new charging cluster set is generated; Obtain the composition information of all current charging cluster sets, extract the geographical coordinates of the charging piles within the charging cluster set, integrate all the geographical coordinates into a geographical coordinate set, calculate the minimum and maximum values of the horizontal and vertical coordinates of the geographical coordinate set to form boundary coordinates, and output the boundary coordinates of each charging cluster.

[0013] In a second aspect, the present application provides a charging pile collaborative control system, including: A collection module that obtains the charging migration sequence data of electric vehicle users, analyzes the charging migration sequence data to obtain the migration preference matrix and charging interval distribution of the charging piles across service areas within a continuous time window, measures the acoustic wave delay data set at a fixed distance between charging piles, and synchronously collects the voltage fluctuation value sequences of each charging pile; A calculation module that converts the acoustic wave delay data set into a delay gradient matrix, and at the same time calculates the correlation coefficient matrix between the voltage fluctuation value sequences, and fuses the delay gradient matrix and the correlation coefficient matrix to generate an environment correlation matrix between charging piles; An aggregation module that dynamically aggregates the charging piles with index values exceeding the set threshold into a charging cluster set through a clustering algorithm according to the environment correlation matrix, and outputs the boundary coordinates of each charging cluster; A prediction module that inputs the migration preference matrix, charging interval distribution, and the boundary coordinates into a prediction model together, outputs the vehicle density distribution map and the average residence duration prediction value of each charging cluster in the future time window, and calculates the load priority vector of each charging cluster based on the vehicle density distribution map, average residence duration prediction value, and the environment correlation matrix of the charging cluster set; A generation module uses the load priority vector as the allocation weight, proportionally allocates the total available power in the service area to each charging pile, generates a charging pile power adjustment instruction and issues it for execution.

[0014] In a third aspect, the present application provides a computing device, including a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a charging pile collaborative control method as described in the first aspect above.

[0015] In a fourth aspect, the present application provides a computer storage medium storing a computer program, which when executed by a computer, implements a charging pile collaborative control method as described in the first aspect.

[0016] The present application obtains the user charging migration sequence and charging pile physical state data to build the basis for environment perception and behavior prediction; then fuses the acoustic wave delay gradient and voltage fluctuation correlation to generate an environment correlation matrix, quantifies the physical space obstacle distribution and grid coupling strength between charging piles, and reveals the implicit association relationship between devices; furthermore, based on this matrix, dynamically aggregates highly correlated charging piles into charging clusters and outputs the boundary coordinates to form a collaborative control physical unit; then combines the migration preference, charging interval distribution and space boundary input into the prediction model to output the future vehicle density distribution map and the estimated residence time value, realizing refined spatio-temporal demand modeling; finally, couples the demand heat and environment correlation strength to calculate the load priority vector, drives the total power in the service area to be accurately allocated to each charging pile according to the weight ratio, and synchronously issues the power adjustment instruction, completely eliminating the resource mismatch problem of coexistence of local overload and idle in the power grid. The whole process breaks through the limitation of the traditional solution that separates environmental variables from user behavior, corrects the demand prediction deviation with acoustic wave / voltage environment correlation data, and realizes the three-dimensional collaborative optimization of physical environment constraints, dynamic load demand and power grid resources.

[0017] Further, by extracting the boundary coordinates of each charging cluster, combining the user number change trend of the migration preference matrix and the adjacent event interval characteristics of the charging interval distribution, inputting into the time series prediction model to output the future vehicle density distribution map and the residence time prediction value; then extracting the highest density value of the density distribution map and multiplying it by the estimated residence time value to obtain the demand heat value, and taking the average value of the environmental correlation scores of all charging pile combinations within the charging cluster to obtain the environment correlation strength, and superposing and normalizing the two according to the weight to form the load priority vector. This measure couples user behavior prediction and physical environment correlation strength under the drive of the space boundary, quantifies the comprehensive load index of the charging cluster, provides a weight basis for power allocation that integrates dynamic demand and environmental constraints, significantly improves the spatio-temporal accuracy of resource allocation, and solves the power grid partition mismatch problem caused by the lack of environmental variables in the traditional solution.

[0018] These aspects or other aspects of the present application will be more clearly understood in the following description of the embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application or in the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0020] Figure 1 The flowchart of a charging pile collaborative control method provided by the present application is shown; Figure 2 The scenario diagram of a charging pile collaborative control method provided by the present application is shown; Figure 3 The structural schematic diagram of a charging pile collaborative control system provided by the present application is shown; Figure 4 The structural schematic diagram of a computing device provided by the present application is shown. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0021] In order to enable those skilled in the art to better understand the solutions of the present application, the following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application.

[0022] In some processes described in the specification and claims of the present application and the above drawings, a plurality of operations that appear in a specific order are included. However, it should be clearly understood that these operations may not be executed in the order in which they appear in this document or may be executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions such as "first" and "second" in this document are used to distinguish different messages, devices, modules, etc., and do not represent a sequence, nor do they limit that "first" and "second" are of different types.

[0023] Researchers found that traditional solutions ignore the signal propagation differences between charging piles caused by the distribution of obstacles, such as the acoustic wave delay characteristics, and the coupling effect of grid fluctuations in adjacent devices, resulting in local overload or resource waste; at the same time, it relies on static historical charging data and lacks dynamic analysis of users' cross-region migration path preferences and charging interval rules. In the case of sudden traffic scenarios, such as the migration peak during holidays, the prediction accuracy is seriously insufficient, leading to power distribution imbalance and grid stability risks. Therefore, there is an urgent need for a collaborative control method that integrates physical environment constraints and user behavior dynamics.

[0024] In view of the above problems, the present invention proposes a cooperative control method for charging piles, the core of which is to construct a dynamic response mechanism through multi-source data fusion. Specifically, first, synchronously collect the acoustic wave delay data set at a fixed distance between charging piles and the voltage fluctuation sequence, fuse them to generate an environmental correlation matrix, and quantify the physical environment between devices and the coupling relationship with the power grid; secondly, analyze the user charging migration sequence data to extract the migration preference matrix and charging interval distribution, combine the charging cluster boundary coordinates and input them into the prediction model, and output the predicted values of vehicle density distribution and residence time in the future period; finally, based on the load priority vector, comprehensively consider the vehicle density, residence time and environmental correlation, and dynamically allocate the total power of the service area. This method completely solves the problem of physical environment constraints, accurately captures the signal propagation difference and the power grid coupling effect, and at the same time realizes the dynamic response to the sudden migration behavior of users. The actual measurement shows that the risk of local overload of the power grid is reduced, breaking through the control bottleneck under the traditional single data dimension.

[0025] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present application.

[0026] Figure 1 The following is a flowchart of a cooperative control method for charging piles provided by an embodiment of the present application, as Figure 1 shown. The method includes: 101. Obtain the charging migration sequence data of electric vehicle users, analyze the charging migration sequence data to obtain the migration preference matrix and charging interval distribution of users across service area charging piles within a continuous time window, measure the acoustic wave delay data set at a fixed distance between charging piles, and synchronously collect the voltage fluctuation value sequences of each charging pile; In the above steps, the charging migration sequence data of electric vehicle users refers to the historical data set that records the charging operations of electric vehicle users at different time points, including the charging pile location information, the start and end time stamps of charging, and the service area identifier. The migration preference matrix refers to the mathematical matrix statistically generated based on the user's charging behavior within a continuous time window, representing the probability or preference degree of the user migrating from the charging pile in the current service area to the charging piles in other service areas. The charging interval distribution refers to the statistical probability distribution of the time intervals between adjacent charging events of users, used to describe the random characteristics of the charging frequency. The acoustic wave delay data set refers to the set of sound propagation time delay data measured under the condition of setting a fixed physical distance between multiple charging piles, reflecting the influence of the propagation speed of sound waves in the air medium. The voltage fluctuation value sequence refers to the continuous data sequence that records the voltage values of the charging pile changing with time under the working state, capturing the dynamic characteristics of the power supply stability.

[0027] In the embodiments of this application, first, the system collects the detailed historical records of each charging of electric vehicle users. These records include who the user is, at which specific location of the charging pile the user charges, the specific start and end time points of charging, and which service area this charging pile belongs to. For example, the system finds the record of user U123, showing that he charged from 8 am to 10 am on October 1, 2023, using the charging pile numbered P1 (the location coordinates are known). The system sorts all such charging records of users in chronological order and forms a structured data set.

[0028] Next, the system analyzes two key pieces of information from this data set: one is the preference rule of the user "jumping" between the charging piles in different service areas, and the other is the distribution rule of the time intervals between two chargings of the user.

[0029] When analyzing the "jump" preference, the system regards each service area as a point, and then calculates how likely it is for the user to go to another service area for the next charging after charging in one service area. This likelihood is represented by a numerical matrix, that is, the migration preference matrix. The specific calculation method is: count the number of times the user directly goes from service area i to service area j for charging, and then divide it by the total number of times the user departs from service area i to all places, to obtain the probability of jumping from i to j. Among them, the specific formula is: , where is the probability of migrating from the starting service area i to the target service area j, is the number of migrations, and k represents the indices of all possible target service areas.

[0030] When analyzing the charging interval pattern, the system will count how long the time interval is between two adjacent chargings for all users (e.g., from the end of the first charging to the start of the second charging), and then use a specific mathematical curve (gamma distribution) to describe the overall distribution characteristics of these time intervals, and find the most likely interval time and the fluctuation range. For example, when calculating the charging interval distribution, a gamma distribution fitting algorithm is adopted. Specifically, a time interval data set of adjacent charging events is extracted and the shape parameter is estimated by the maximum likelihood estimation method. and the scale parameter to generate the cumulative distribution function (CDF). The formula for the gamma distribution probability density function is expressed as , where t is the time interval value (unit: minute), is the shape parameter that controls the distribution shape, is the scale parameter representing the distribution expansion factor, is the gamma function value used to normalize the distribution, and the calculation results are saved for subsequent use. Once the optimal and are found, this "gamma mold" becomes the best mathematical model to describe the charging interval pattern of this group of users. The abscissa (time value) corresponding to the highest point of this model curve is the charging interval time with the highest frequency in statistics, and the width of this model curve intuitively reflects the fluctuation range of the interval time.

[0031] At the same time, in order to understand the influence of the physical environment around the charging pile, the system will install sound transmitting and receiving devices between the selected charging piles (e.g., fixed 50 meters apart); the system makes one pile emit a sound signal and the other pile receive it, accurately measures how long it takes for the sound to travel from transmission to reception (delay), and repeats the measurement multiple times (e.g., 30 times) and takes the average value to obtain a reliable sound propagation time data set.

[0032] Finally, in order to monitor the power supply status during charging, the system will install a voltmeter at the connection point of the charging pile and ensure that this voltage measurement and the sound measurement are synchronized (marked with the same clock for time); this voltmeter will record the change of the voltage value at a very high speed (e.g., 1000 times per second), and then calculate the average amplitude (standard deviation) of the voltage value fluctuating up and down within a short period of time (a window) to obtain a voltage stability data sequence that changes with time. In this way, the system synchronously obtains the charging behavior habits of users (jump preferences and interval patterns), physical environment characteristics (sound propagation delay), and power conditions (voltage fluctuations), providing a basis for subsequent comprehensive analysis.

[0033] For example, in a research project involving 300 electric vehicle owners, the system first collected complete records of approximately 10 charging events for each of them over a certain period (e.g., 15 consecutive weeks). Then, the system analyzed these records: it counted the charging transfers between 8 different service areas, calculating an 8-by-8 matrix (migration preference matrix), where each number in the matrix represents the probability of a user moving from one service area to another after charging at a particular service area (e.g., the probability of jumping from service area A to service area B is 0.3). At the same time, from a total of more than 18,000 charging intervals of all users (e.g., the interval between the end of the first charge and the start of the second charge for user U123 was 2 days, and for user U456 it was 5 hours), the system used a mathematical method (gamma distribution) to fit a typical distribution model for the charging intervals, such as finding that the probability was highest for intervals between 8 hours and 24 hours. In terms of physical environment measurement, the researchers selected a pair of charging piles 50 meters apart, had one emit a sound and the other receive it, and repeated the experiment 30 times, precisely recording how long it took for the sound to travel each time (e.g., an average of 0.147 seconds), obtaining a stable dataset of acoustic wave delays. Finally, while measuring the sound, a voltmeter also recorded the voltage values at the charging pile connection points at a rate of 1000 times per second (e.g., sometimes it was 219.5 volts and sometimes 220.1 volts), and then calculated the average severity of voltage fluctuations (standard deviation, e.g., calculating that the standard deviation within a certain 0.1-second window was 0.3 volts) for each small time segment (e.g., every 0.1 second), forming a voltage fluctuation change curve with 500 points (voltage fluctuation value sequence). All these data - the probability matrix of user jumps, the distribution model of charging intervals, the sound propagation time over a 50-meter distance, and the synchronized voltage fluctuation curve - were collected and prepared for subsequent analysis such as optimizing the charging network.

[0034] In the overall solution of step 101 above, the ability to comprehensively analyze electric vehicle charging behavior is achieved by obtaining the charging migration sequence data of users and parsing this data to obtain the migration preference matrix and charging interval distribution of users across service area charging piles within consecutive time windows, simultaneously measuring the acoustic wave delay dataset at a fixed distance between charging piles, and synchronously collecting the voltage fluctuation value sequences of each charging pile. These integrated data streams jointly support the efficient monitoring and optimization of the dynamic behavior and potential problems of the charging system, improving the reliability and prediction accuracy of the entire system.

[0035] 102. Convert the acoustic wave delay dataset into a delay gradient matrix, and at the same time calculate the correlation coefficient matrix between the voltage fluctuation value sequences, and fuse the delay gradient matrix and the correlation coefficient matrix to generate an environmental correlation matrix between charging piles; Optionally, step 102 may specifically include the following steps: 1021. Take any two charging piles as a group of charging pile combinations, and obtain multiple acoustic wave delay datasets at a fixed distance between the charging pile combinations; 1022. Calculate the difference between the maximum delay value and the minimum delay value in the acoustic wave delay data as the amplitude of the acoustic wave delay variation, and generate a delay gradient matrix according to the amplitude of the acoustic wave delay variation; 1023. Obtain the voltage fluctuation value sequence of the charging pile combination within the same time window, and calculate the correlation coefficient matrix of the voltage fluctuation value sequence; 1024. Weight and superimpose the values in the delay gradient matrix and the correlation coefficient matrix according to a preset ratio to generate the environmental correlation score of this group of charging piles, and arrange the environmental correlation scores of all the charging pile combinations to form an environmental correlation degree matrix.

[0036] Among them, step 1024 may specifically include the following process: Extract the amplitude of the acoustic wave delay variation corresponding to the charging pile combination from the delay gradient matrix, multiply the amplitude of the acoustic wave delay variation by a first preset coefficient to obtain an acoustic wave influence component; Extract the fluctuation correlation degree value of the two voltage fluctuation value sequences of this charging pile combination from the correlation coefficient matrix, multiply the fluctuation correlation degree value by a second preset coefficient to obtain a voltage influence component; Add the acoustic wave influence component and the voltage influence component to generate the environmental correlation score of the charging pile combination, and arrange the environmental correlation scores of all the charging pile combinations in the order of the charging pile numbers as a symmetric square matrix to form the environmental correlation degree matrix.

[0037] In the above steps, the acoustic wave delay data set refers to the set of sound propagation time delay data measured at a fixed distance, reflecting the dynamic characteristics of sound propagation. The delay gradient matrix refers to the data structure generated based on the amplitude change of the acoustic wave delay, representing the difference matrix of the acoustic wave influence degree between charging piles. The voltage fluctuation value sequence refers to the continuous data sequence of the voltage values collected at the charging pile end changing with time. The correlation coefficient matrix refers to the numerical matrix calculated through the voltage fluctuation value sequence, representing the fluctuation correlation degree between different sequences. The environmental correlation degree matrix refers to the symmetric score matrix describing the comprehensive environmental correlation degree between charging piles, used to quantify the mutual influence degree of environmental and power factors. The charging pile combination refers to the data processing unit formed by pairwise selection of two charging piles. The amplitude change of the acoustic wave delay refers to the difference between the maximum value and the minimum value in multiple acoustic wave delay measurements under a specific charging pile combination, characterizing the stability of acoustic wave propagation. The fluctuation correlation degree value refers to the numerical element in the correlation coefficient matrix, reflecting the correlation strength between two voltage sequences. The environmental correlation score refers to the single value calculated for each charging pile combination, comprehensively measuring the influence of acoustic wave and voltage factors. The first preset coefficient refers to the fixed weight coefficient when acoustic wave factors are weighted and superimposed. The second preset coefficient refers to the fixed weight coefficient when voltage factors are weighted and superimposed. The acoustic wave influence component refers to the part obtained by multiplying the amplitude change of the acoustic wave delay by the first preset coefficient, quantifying the size of the acoustic wave contribution. The voltage influence component refers to the part obtained by multiplying the fluctuation correlation degree value by the second preset coefficient, quantifying the contribution of voltage fluctuation. The preset ratio refers to the weight setting rule of the first preset coefficient and the second preset coefficient in the weighted superposition process, used to adjust the influence proportion of each component.

[0038] In the embodiment of the present application, first, the purpose of describing the whole process is to generate a matrix representing the environmental correlation degree between charging piles, which can help understand the positions and mutual influence degrees of charging piles in the physical environment. The solution starts from the stored measurement data: The first step is to obtain data for the combination of charging piles through step 1021. Specifically, any two charging piles are paired into a group (for example, charging piles A and B), and the delay measurement values of multiple sound propagations between them (the time required for sound to travel from one charging pile to another) are extracted. Here, it is assumed that each combination has multiple measurement data for analyzing stability. For example, the delay data of charging piles A and B may be three measurements: 150 milliseconds, 180 milliseconds, and 130 milliseconds.

[0039] The second step is to calculate the variation magnitude of these delay data through step 1022, which is called the acoustic wave delay variation amplitude. It is obtained by subtracting the minimum value from the maximum value in the delay data (for example, in the above delay values 150, 180, 130, the maximum value 180 minus the minimum value 130 equals 50 milliseconds). The variation amplitudes of all combinations will be filled into a symmetric matrix (called the delay gradient matrix), where the charging pile numbers correspond to the rows and columns. For example, the variation amplitude of 50 between charging piles A - B is filled in the cell at the intersection of row A and column B of the matrix.

[0040] The third step is to obtain the numerical sequence of voltage changes for the same combination of charging piles through step 1023 (recording the voltage fluctuation values of each charging pile within the same period of time), and calculate the degree of correlation between these sequences (called the fluctuation correlation degree). Here, the Pearson correlation coefficient formula is used for calculation. The formula involves dividing the covariance by the product of the standard deviations of the two sequences. The covariance measures the degree of co - variation of the sequences, and the standard deviation represents the fluctuation magnitude of the sequences (for example, the voltage sequence of charging pile A within the same period is [0.5V, 0.6V, 0.55V], and the sequence of charging pile B is [0.52V, 0.58V, 0.53V]. First, calculate the average value of sequence A as 0.55V and the average value of sequence B as 0.543V. The covariance is calculated by finding the sum of the products of the sequence values minus the average value and dividing by the number of points minus one: ((0.5 - 0.55)×(0.52 - 0.543)+(0.6 - 0.55)×(0.58 - 0.543)+(0.55 - 0.55)×(0.53 - 0.543)) / 2 is approximately equal to 0.00155. The square of the standard deviation of sequence A is [(0.5 - 0.55)^2+(0.6 - 0.55)^2+(0.55 - 0.55)^2] / 2≈0.0025, and the square root is 0.05V. The standard deviation of sequence B is calculated similarly to be approximately 0.04V. The correlation coefficient is the covariance 0.00155 divided by (0.05×0.04) which equals 0.775). The results of calculating each combination will be arranged into a symmetric matrix (the correlation coefficient matrix). For example, the correlation coefficient of 0.775 between charging piles A - B is filled in the corresponding position of the matrix.

[0041] The fourth step is to generate an environment correlation matrix by fusing two parts of information through step 1024: First, extract the change amplitude of this charging pile combination from the delay gradient matrix (such as 50 for A - B), multiply it by the first weight coefficient (for example, the first coefficient α is set to 0.4) to obtain the acoustic wave influence component S (S = 50×0.4 = 20). Secondly, extract the fluctuation correlation degree value from the correlation coefficient matrix (such as 0.775 for A - B), multiply it by the second weight coefficient (for example, the second coefficient β is set to 0.6) to obtain the voltage influence component V (V = 0.775×0.6≈0.465). Then, simply add S and V to generate the environment correlation score of this combination (20 + 0.465≈20.465). After repeating all charging pile combinations (such as A - C, B - C, etc.), arrange these scores in the order of charging pile numbers into a symmetric square matrix (the rows and columns correspond to the charging pile numbers, and the values are the corresponding scores). For example, fill the environment correlation score of the charging pile combination into the B column of the A row to become a part of the environment correlation matrix and store it for future use. The entire process realizes the transformation from raw measurement to meaningful correlation output through loop processing of data, ensuring that each charging pile combination is evaluated consistently for subsequent analysis of its environmental relevance.

[0042] In the overall solution of step 102 above, by collecting the acoustic wave delay data at a fixed distance between charging piles and converting it into a delay gradient matrix, and simultaneously calculating the correlation coefficient matrix of the voltage fluctuation value sequence, and then weighted - fusing the core parameters in the two matrices, the acoustic wave delay change amplitude and the voltage fluctuation correlation degree value, according to a preset ratio to generate the environment correlation score of the charging pile combination. Finally, by systematically arranging the scores of all combinations to construct an environment correlation matrix in the form of a symmetric square matrix, the three - dimensional quantization diagnosis ability of the environmental interference coupling intensity of the charging pile cluster is realized. First, reflect the environmental interference conduction path through the change of acoustic wave propagation stability. Secondly, capture the abnormal correlation of the power grid state by using the voltage fluctuation synchronization characteristics. Finally, establish an acoustic - electric joint diagnosis model based on the multi - physical quantity fusion analysis to simultaneously reveal the fault conduction risk and electromagnetic compatibility characteristics, providing the charging network with the ability of fault traceability and positioning and environmental risk early warning, and greatly improving the collaborative operation reliability and risk active defense accuracy of the charging facility group under complex working conditions.

[0043] 103. According to the environment correlation matrix, dynamically aggregate the charging piles with index values exceeding the set threshold into charging clusters through a clustering algorithm, and output the boundary coordinates of each charging cluster; Optionally, step 103 may specifically include the following steps: 1031. Set the minimum connection threshold of the environment correlation scores in the environment correlation matrix, and initialize each charging pile as an independent charging cluster; 1032. Identify the charging pile association relationships in the environment correlation matrix that are greater than the minimum connection threshold, extract the two charging piles corresponding to each qualified association relationship. If the two charging piles belong to different charging clusters, merge them into a charging cluster set, and iteratively execute the operation until no new charging cluster sets are generated; 1033. Obtain the composition information of all current charging cluster sets, extract the geographical coordinates of the charging piles within the charging cluster set, integrate all the geographical coordinates into a geographical coordinate set, calculate the minimum and maximum values of the horizontal and vertical coordinates of the geographical coordinate set to form boundary coordinates, and output the boundary coordinates of each charging cluster.

[0044] In the above steps, the environment correlation matrix refers to the symmetric score matrix output from step 102 that describes the comprehensive environment correlation between charging piles. The clustering algorithm refers to the calculation method for data grouping, which forms groups through the relationships between data points. The index value refers to the environmental correlation score value in the environment correlation matrix. The set threshold refers to a preset fixed numerical boundary used to determine whether the association strength meets the conditions. The charging pile refers to the electric vehicle charging facility equipment. Dynamic aggregation refers to the process of combining data points according to rules. The charging cluster set refers to a group of charging piles generated by the clustering algorithm. The boundary coordinates refer to the position coordinate data that describes the spatial range of the charging cluster set, usually including the extreme values of longitude and latitude. The minimum connection threshold refers to the specific lower limit value of the environmental correlation score set in step 1031. The independent charging cluster refers to the group state in which each charging pile is regarded as an independent individual initially. The charging pile association relationship refers to a pair of charging pile objects whose environmental correlation score exceeds the threshold. The geographical coordinate refers to the position information data of the charging pile, such as longitude and latitude values. The geographical coordinate set refers to the summary data of all the geographical coordinates of the charging piles within the charging cluster set. The minimum and maximum values of the horizontal and vertical coordinates refer to the position boundary values of all points in the coordinate axis direction, used to define the spatial range.

[0045] In the embodiment of the present application, first, based on the association score table (environment correlation matrix) that describes the environmental similarity between charging piles through step 1031, a minimum connection score (minimum connection threshold) is set, and each charging pile is regarded as an independent group (independent charging cluster).

[0046] Secondly, identify the charging pile association relationships greater than the minimum connection threshold in the environment correlation matrix through step 1032 and dynamically aggregate the charging clusters. Based on the matrix data with thresholds, the initial charging cluster list data, and the thresholds, use the matrix scanning algorithm to traverse all the charging pile pair elements in the environment correlation matrix, detect whether the environmental correlation score is greater than the minimum connection threshold, use the charging cluster relationship detection technology to extract the charging pile pair objects that meet the conditions. If the pair of charging piles belongs to different charging clusters, apply the cluster merging algorithm to merge their charging clusters, and loop and iterate this process until no new merges occur, and output the updated charging cluster set data. That is to say, find all the charging pile pairing relationships with scores exceeding the set minimum score in the correlation score table of step 1031; for each pair of eligible charging piles, check whether they belong to different groups. If so, merge these two groups into a large group (charging cluster set).

[0047] Finally, through step 1033, obtain the composition information of all current charging clusters, extract the integrated set of geographical coordinates, and calculate the boundary coordinates. Based on the charging cluster set data, use the data query technology to read the charging pile composition list of each charging cluster, apply the coordinate extraction algorithm to obtain the geographical coordinate values of all members from the stored geographical information of the charging piles, use the coordinate integration technology to summarize all the coordinates into a geographical coordinate set, and use the boundary calculation algorithm to calculate the minimum and maximum values of the abscissa and the minimum and maximum values of the ordinate of this set to form the boundary coordinate data, and finally output the boundary coordinates of each charging cluster to the data storage system. That is to say, repeat the above process of step 1032 to find eligible pairs and merge groups until no new pairs that can be merged are found. Then, for each final large group, obtain the specific location information (geographical coordinates) of all the charging piles within the group, collect all these location points; find the longitude values (minimum and maximum abscissas) of the easternmost and westernmost points, and the latitude values (minimum and maximum ordinates) of the northernmost and southernmost points among these location points; use these four values (east-west longitude boundary, north-south latitude boundary) to determine the rectangular area range (boundary coordinates) occupied by this charging pile large group on the map, and finally output the range data of each large group.

[0048] In the overall solution of the above step 103, the spatial mapping ability of the charging facility network environment correlation is realized. By setting the minimum connection threshold of the environment correlation matrix, each charging pile is initialized as an independent charging cluster, and the correlation relationships above the threshold in the matrix are dynamically scanned. When strongly correlated charging pile pairs are identified, iterative merging operations are performed on the nodes belonging to different charging clusters until a stable charging cluster set architecture is formed; on this basis, the geographical coordinate set of all the charging piles within the cluster is extracted, and the rectangular boundary box coordinates are generated using the abscissa and ordinate extreme value extraction algorithm, and finally the charging cluster boundary range with spatial clarity is output.

[0049] 104. Input the migration preference matrix, charging interval distribution, and the boundary coordinates into a prediction model to output the vehicle density distribution map and the predicted average residence duration of each charging cluster in a future time window. Based on the vehicle density distribution map, the predicted average residence duration, and the environmental correlation matrix of the charging cluster set, calculate the load priority vector of each charging cluster; Optionally, step 104 may specifically include the following steps: 1041. Extract the boundary coordinates of each charging cluster, obtain the change trend of the number of regions where the user group enters and exits the boundary coordinates within consecutive time windows from the migration preference matrix, and extract the interval characteristics of adjacent charging events from the charging interval distribution; 1042. Input the boundary coordinates, the number change trend, and the interval characteristics into a time series prediction model to output the vehicle density distribution map per unit area and the predicted average residence duration of the charging cluster set in a future time window; Among them, step 1042 may specifically include the following process: Calculate the covered area of the rectangular region enclosed by the boundary coordinates of each charging cluster, convert the number change trend into a sequence of user number changes at the same time period every day, and process the interval characteristics into the typical time difference between adjacent charging behaviors; Combine the covered area, the user number change sequence, and the typical time difference into an input data block, arrange the input data block in chronological order and then send it into the time series prediction model, and obtain the total number of vehicles and the average vehicle occupancy duration values for each future time period through this model; Divide the total number of vehicles in each future time period by the covered area corresponding to that time period to form a sequence of the number of vehicles per unit area arranged in chronological order as the vehicle density distribution map, and use the average vehicle occupancy duration value as the predicted average residence duration;

[0050] 1043. Extract the highest density value from the vehicle density distribution map, multiply the highest density value by the predicted average residence duration to obtain the demand heat value, and take the average of the environmental correlation scores of all charging pile combinations in the charging cluster set to obtain the environmental correlation intensity; 1044. Superimpose the demand heat value and the environmental correlation intensity according to a preset weight to obtain a comprehensive load index, and normalize the comprehensive load index of all charging cluster sets to obtain the load priority vector.

[0051] In the above steps, the migration preference matrix refers to a mathematical matrix statistically generated based on users' charging behaviors within consecutive time windows, representing the probability distribution of users migrating from the charging piles in the current service area to those in other service areas. The charging interval distribution refers to the statistical probability distribution of the time intervals between adjacent charging events of users. The boundary coordinates refer to the spatial position range data of the charging clusters, represented by the minimum and maximum values of the horizontal and vertical coordinates. The prediction model refers to a time series prediction algorithm used for future trend analysis. The vehicle density distribution map refers to the sequence of the number of vehicles per unit area in each future time period output by the prediction model, reflecting the vehicle distribution density within the charging cluster area. The predicted value of the average stay duration refers to the numerical value of the average occupancy time of future vehicles within the charging cluster area output by the prediction model. The charging cluster refers to the set of charging piles generated after clustering. The environmental correlation matrix refers to a symmetric score matrix describing the comprehensive environmental correlation between charging piles in the step description. The load priority vector refers to the vector obtained by normalizing the priority scores of each charging cluster calculated finally, used to represent the order of charging demand processing. The trend of the change in the number of regions refers to the sequence of the number of users in the user group entering and leaving the boundary coordinate region changing over time. The interval feature refers to the typical time difference data between adjacent charging events in the charging interval distribution. The demand heat value refers to the product of the highest density value in the vehicle density distribution map and the predicted value of the average stay duration, reflecting the peak demand intensity. The environmental correlation intensity refers to the numerical value obtained by averaging the environmental correlation scores of all charging pile combinations within the charging cluster, representing the environmental stability index. The comprehensive load index refers to the comprehensive score obtained by weighted superposition of the demand heat value and the environmental correlation intensity. Normalization refers to the mathematical processing process of converting the comprehensive load index into relative priorities.

[0052] In the embodiment of the present application, the core of this step is to combine three types of data: user behavior, charging habits, and spatial range, predict the vehicle density and usage duration in each future charging area, and finally calculate the priority ranking of different areas.

[0053] First, for each divided charging cluster (i.e., the charging pile group formed in step 103), extract its boundary coordinates (the rectangular area range occupied by this group on the map, such as the easternmost / westernmost longitude and the southernmost / northernmost latitude). At the same time, extract the change trend of the number of users entering and leaving this area within multiple consecutive time periods (such as 24 hours a day) from the migration preference matrix (a table recording the flow rules of the user group among different regions) (for example, 10 people enter at 8 am and 5 people leave at 9 am), and extract the typical interval features (such as most users charge once every 45 minutes) from the charging interval distribution (the statistical data of the time difference between two charges of users).

[0054] Next, input these three types of data into the time series prediction model: First, calculate the area of the rectangle enclosed by the boundary coordinates of the cluster (for example, east-west span 100 meters × north-south span 60 meters = 6,000 square meters). Convert the change in the number of users into a quantity sequence at the same time period every day (such as the number of users in the area at 9 am for three consecutive days [20, 22, 19]), and combine the typical charging interval (45 minutes) as the input data block. The model (such as LSTM) will output the estimated total number of vehicles and the average stay duration in this area for future time periods (such as predicting 25 vehicles staying for 30 minutes at 9:00 on the fourth day); divide the predicted total number of vehicles by the area of the cluster to obtain the vehicle density distribution map for different time periods (such as 25 vehicles / 6000m 2 ≈ 4.17 vehicles per thousand square meters), and the average stay duration is directly output as the predicted value (30 minutes). Subsequently, calculate the demand heat value: Extract the highest density value in the density distribution map (such as 12 vehicles per thousand square meters during the morning peak) and multiply it by the average stay duration (30 minutes) to get 360 vehicle-minutes per thousand square meters, reflecting the cumulative impact of high-load time periods in the area; at the same time, calculate the average value of the environmental correlation scores of all pairs of charging piles within the cluster (environmental correlation strength, such as an average value of 18.5 points).

[0055] Finally, superimpose the demand heat value and the environmental correlation strength according to the preset weights (such as 360 × 0.7 weight + 18.5 × 0.3 weight = 252 + 5.55 = 257.55) to obtain the comprehensive load index of the cluster; the indicators of all charging clusters are normalized (compressed to the 0-1 range) to form a load priority vector (such as the two cluster indicators 257.55 and 180, normalized to 0.82 and 0.57), and the higher the value, the higher the scheduling priority.

[0056] In the overall solution of step 104 above, the pre-diagnosis optimization ability of intelligent charging load regulation is realized. By jointly inputting the charging cluster boundary coordinates, user migration preference matrix, and charging interval distribution characteristics into the time series prediction model, first, the predicted values of vehicle density distribution and average stay duration for future time periods are output; subsequently, the demand heat index is obtained based on the product of the peak density and stay duration in the vehicle density distribution map, and the average value of the environmental correlation matrix within the charging cluster set is calculated as the coupling strength of the facility group; finally, the two core parameters are fused into a comprehensive load index according to the preset weights, and a load priority vector is generated after normalization processing.

[0057] 105. Using the load priority vector as the allocation weight, allocate the total available power in the service area proportionally to each charging pile, generate a charging pile power adjustment instruction and send it down for execution.

[0058] Optionally, step 105 may specifically include the following steps: 1051. Obtain the total available power value of the service area power grid, extract the weight coefficient of each charging cluster from the load priority vector, multiply the total available power value by the weight coefficient of each charging cluster to obtain the power allocation value of each charging cluster: 1052. Obtain the total number of charging piles in each charging cluster, divide the power allocation value by the total number of charging piles to obtain the power setting value of each charging pile; 1053. Create an adjustment instruction containing the identifier and the power setting value for each charging pile, and send the adjustment instruction to the corresponding charging pile controller to execute power adjustment.

[0059] In the above steps, the load priority vector refers to the normalized priority vector output in step 104, which represents the weight coefficient of the urgency degree of each charging cluster's demand. The total available power of the service area refers to the maximum total power supply value that the power grid system can allocate to the charging piles. The allocation weight refers to the normalized coefficient value corresponding to each charging cluster in the load priority vector. The charging cluster refers to the dynamic charging pile group set generated in step 103. The power allocation value refers to the numerical value of the power resources allocated to each charging cluster. The total number of charging piles refers to the number of charging facilities included in a single charging cluster. The power setting value refers to the specific power value finally allocated to a single charging pile. The adjustment instruction refers to the control command data packet containing the charging pile identifier and the power setting value. The charging pile controller refers to the hardware control module inside the charging pile that executes power adjustment. The identifier refers to the encoded data that uniquely identifies the charging pile. The power adjustment refers to the operation process in which the charging pile changes the power input according to the set value.

[0060] In the embodiment of the present application, first, obtain the total available power value of the service area power grid through step 1051, and extract the power allocation weight coefficient value of the charging cluster based on the load priority vector: adopt data extraction technology to read the normalized weight coefficient of each charging cluster from the load priority vector. Taking the charging cluster number C1 as an example, its weight coefficient is 0.9, and the weight coefficient of the charging cluster number C2 is 0.5; apply the multiplication algorithm to multiply the total available power value of the service area by the weight coefficient of each charging cluster respectively. The formula is expressed as the charging cluster power allocation value = , where is the total available power value of the power grid and the power unit is kW, is the normalized weight coefficient of the corresponding charging cluster in the load priority vector and is a dimensionless value. A specific example of generating the power allocation value set is that when the total power is 100 kW, the allocation value of charging cluster C1 is 100 multiplied by 0.9 to get 90 kW, and the allocation value of charging cluster C2 is 100 multiplied by 0.5 to get 50 kW.

[0061] Secondly, calculate the single-pile power setting value through step 1052: Use the cluster information query technology based on the power distribution value set to obtain the total number of charging piles in each charging cluster. For example, charging cluster C1 contains 3 charging piles and charging cluster C2 contains 5 charging piles; apply the division algorithm to divide the power distribution value by the total number of charging piles. The formula is expressed as power setting value = , where is the charging cluster power distribution value output by step 1051, is the total number of charging piles in the corresponding cluster. The calculation result is used as the single-pile power regulation reference value. Specifically, the single-pile setting value of charging cluster C1 is calculated as 90kW divided by 3 to get 30kW, and the single-pile setting value of charging cluster C2 is calculated as 50kW divided by 5 to get 10kW. This process realizes a typical case of hierarchical distribution of the total grid power to the single-pile power: Taking the execution process of charging cluster C1 as an example, extract the weight 0.9 from the load priority vector and multiply it by the total power of 100kW to get the cluster-level distribution of 90kW. Then, according to the 3 charging piles in the cluster, each pile is evenly allocated a setting value of 30kW, thus completing the refined scheduling of power resources according to the load priority.

[0062] Finally, through step 1053, create an adjustment instruction for each charging pile that includes an identifier and the power setting value, and send the adjustment instruction to the corresponding charging pile controller to execute the power adjustment. Based on the power setting value, use the instruction construction technology to generate a data structure that includes the unique identifier of the charging pile and the power setting value, and apply the communication protocol encapsulation algorithm to form a transmissible adjustment instruction data packet, which is sent to the target charging pile controller through the network transmission module. Finally, the charging pile controller executes the power adjustment operation to change the power input level.

[0063] In the overall solution of step 105 above, by obtaining the available total power value of the service area power grid, extracting the weight coefficient of each charging cluster from the load priority vector, multiplying the available total power by the weight coefficient to generate the power distribution value of each charging cluster; secondly, identifying the total number of charging piles in each charging cluster, and evenly distributing the power distribution value to each charging pile to obtain the power setting value; finally, creating a digital adjustment instruction for each charging pile that includes a unique device identifier and the setting value, and sending it to the charging pile controller through the control network to execute the power adjustment operation, forming a closed-loop control link from decision-making to execution.

[0064] The following is a complete embodiment for steps 101 to 105: As Figure 2As shown, in the collaborative control implementation of an electric vehicle charging service area, we first obtain the charging migration sequence data of 300 users. After parsing, an 8×8 migration preference matrix is generated and a charging interval distribution is constructed based on 18,000 time interval samples. At the same time, a dataset of 30 acoustic wave delays between charging piles at a fixed distance of 50 meters is measured, and a voltage fluctuation sequence of 500 points for each pile is synchronously collected. Subsequently, the acoustic wave delay data is converted into a delay gradient matrix reflecting the change amplitude. For example, for a certain pile, the delay difference is 5 milliseconds. Calculate the correlation coefficient matrix of the voltage fluctuation sequence. For example, for a certain pile pair, the correlation coefficient is 0.85. A weighted fusion of 0.4 times the delay change amplitude and 0.6 times the correlation coefficient is used to generate an environmental correlation degree matrix. For example, for a certain pile pair, the score is 1.02. Then, a threshold of 0.8 is set, and 8 charging piles are aggregated into two charging cluster sets through dynamic clustering. C1 contains 5 piles, and C2 contains 3 piles. The boundary area is calculated based on the geographical coordinates of the pile groups.

[0065] Furthermore, the migration preference matrix, charging interval distribution, and boundary coordinates are input into the prediction model: Using a 3,000-square-meter area, the daily vehicle number sequence in each time period, and the typical charging interval characteristics of 180 minutes, the vehicle density distribution in the next three time periods [0.016, 0.017, 0.0167] vehicles per square meter and the average stay duration of 45 minutes are output. The product of the density peak value of 0.017 and the stay duration is obtained as the demand heat value of 0.765. Combining the average environmental correlation score value of 0.93 within the charging cluster, a charging cluster load index of 0.8175 is obtained by superimposing according to a weight of 0.7:0.3. Finally, it is normalized to form a load priority vector [0.56, 0.44]. Finally, based on the total grid power of 5,000 kW for distribution: C1 obtains 2,800 kW (5,000×0.56), and each of its 5 piles is set to 560 kW; C2 obtains 2,200 kW (5,000×0.44), and each of the 3 piles is set to 733.3 kW. The system generates a power setting instruction and issues it for execution through the communication protocol to achieve dynamic collaborative regulation of charging resources.

[0066] Figure 3 The accompanying drawing is a schematic structural diagram of a charging pile collaborative control system provided by an embodiment of the present application, as Figure 3 shown. The system includes: A collection module 31, which obtains the charging migration sequence data of electric vehicle users, parses the charging migration sequence data to obtain a migration preference matrix and a charging interval distribution of users across service area charging piles within a continuous time window, measures a dataset of acoustic wave delays between charging piles at a fixed distance, and synchronously collects a voltage fluctuation value sequence of each charging pile; A calculation module 32, which converts the acoustic wave delay dataset into a delay gradient matrix, calculates the correlation coefficient matrix between the voltage fluctuation value sequences at the same time, and fuses the delay gradient matrix and the correlation coefficient matrix to generate an environmental correlation degree matrix between charging piles; The aggregation module 33, according to the environment correlation matrix, dynamically aggregates the charging piles with indicator values exceeding the set threshold into charging clusters through a clustering algorithm, and outputs the boundary coordinates of each charging cluster; The prediction module 34 inputs the migration preference matrix, the charging interval distribution, and the boundary coordinates into a prediction model, outputs the vehicle density distribution map and the predicted average residence duration of each charging cluster in a future time window, and calculates the load priority vector of each charging cluster based on the vehicle density distribution map, the predicted average residence duration, and the environment correlation matrix of the charging cluster set; The generation module 35, using the load priority vector as the allocation weight, distributes the total available power in the service area proportionally to each charging pile, generates a charging pile power adjustment instruction, and issues it for execution.

[0067] Figure 3 The described charging pile collaborative control system can execute Figure 1 The charging pile collaborative control method described in the illustrated embodiment, and its implementation principle and technical effects will not be elaborated further. For the charging pile collaborative control system in the above embodiment, the specific ways in which each module and unit perform operations have been described in detail in the embodiment related to the method, and will not be elaborated here.

[0068] In a possible design, Figure 3 A charging pile collaborative control system of the illustrated embodiment can be implemented as a computing device, such as Figure 4 shown, and this computing device can include a storage component 41 and a processing component 42; The storage component 41 stores one or more computer instructions, and among them, the one or more computer instructions are called and executed by the processing component 42.

[0069] The processing component 42 is used for the Figure 1 charging pile collaborative control method of the above

[0070] embodiment. Among them, the processing component 42 can include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component can also be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components for executing the above method.

[0071] The storage component 41 is configured to store various types of data to support the operation of the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0072] Of course, the computing device may also necessarily include other components, such as input / output interfaces, display components, communication components, etc.

[0073] The input / output interface provides an interface between the processing component and the peripheral interface module, and the above-mentioned peripheral interface module can be an output device, an input device, etc.

[0074] The communication component is configured to facilitate communication between the computing device and other devices in a wired or wireless manner, etc.

[0075] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. At this time, the computing device can refer to a cloud server, and the above-mentioned processing component, storage component, etc. can be basic server resources leased or purchased from a cloud computing platform.

[0076] The embodiment of the present application also provides a computer storage medium storing a computer program, and when the computer program is executed by a computer, it can implement the above Figure 1 a charging pile collaborative control method shown in the above embodiment.

[0077] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described systems, devices, and units can refer to the corresponding processes in the foregoing method embodiments, and will not be described herein again.

[0078] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement without creative efforts.

[0079] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to enable a computer device (which can be a personal computer, server, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0080] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for collaborative control of a charging pile, characterized in that, Including: Obtain the charging migration sequence data of electric vehicle users, parse the charging migration sequence data to obtain the migration preference matrix and charging interval distribution of the users across service area charging piles within a continuous time window, measure the acoustic wave delay data set at a fixed distance between charging piles, and synchronously collect the voltage fluctuation value sequences of each charging pile; Convert the acoustic wave delay data set into a delay gradient matrix, and at the same time calculate the correlation coefficient matrix between the voltage fluctuation value sequences, and fuse the delay gradient matrix and the correlation coefficient matrix to generate the environmental correlation degree matrix between charging piles; According to the environmental correlation degree matrix, dynamically aggregate the charging piles with index values exceeding the set threshold into charging clusters through a clustering algorithm, and output the boundary coordinates of each charging cluster; Input the migration preference matrix, charging interval distribution, and the boundary coordinates into a prediction model, output the vehicle density distribution map and the predicted average residence time of each charging cluster in the future time window, and calculate the load priority vector of each charging cluster based on the vehicle density distribution map, the predicted average residence time, and the environmental correlation degree matrix of the charging cluster set; Using the load priority vector as the allocation weight, allocate the total available power in the service area proportionally to each charging pile, generate a charging pile power adjustment instruction and issue it for execution.

2. The method according to claim 1, wherein Input the migration preference matrix, charging interval distribution, and the boundary coordinates into a prediction model, output the vehicle density distribution map and the predicted average residence time of each charging cluster in the future time window, and calculate the load priority vector of each charging cluster based on the vehicle density distribution map, the predicted average residence time, and the environmental correlation degree matrix of the charging cluster set, including: Extract the boundary coordinates of each charging cluster, obtain the change trend of the number of regions where the user group enters and exits the boundary coordinates within a continuous time window from the migration preference matrix, and extract the interval characteristics of adjacent charging events in the charging interval distribution; Input the boundary coordinates, number change trend, and interval characteristics into a time series prediction model, and output the vehicle density distribution map per unit area and the predicted average residence time of the charging cluster set in the future time window; Extract the highest density value in the vehicle density distribution map, multiply the highest density value by the predicted average residence time to obtain the demand heat value, and take the average of the environmental correlation scores of all charging pile combinations within the charging cluster set to obtain the environmental correlation intensity; Superimpose the demand heat value and the environmental correlation intensity according to a preset weight to obtain a comprehensive load index, and normalize the comprehensive load index of all charging cluster sets to obtain a load priority vector.

3. The method according to claim 1, wherein Convert the acoustic wave delay data set into a delay gradient matrix, and at the same time calculate the correlation coefficient matrix between the voltage fluctuation value sequences, and fuse the delay gradient matrix and the correlation coefficient matrix to generate the environmental correlation degree matrix between charging piles, including: Take any two charging piles as a charging pile combination, and obtain the multiple acoustic wave delay data sets at the fixed distance between the charging pile combinations; Calculate the difference between the maximum delay value and the minimum delay value in the acoustic wave delay data as the acoustic wave delay variation amplitude, and generate a delay gradient matrix according to the acoustic wave delay variation amplitude; Obtain the voltage fluctuation value sequence of the charging pile combination within the same time window, and calculate the correlation coefficient matrix of the voltage fluctuation value sequence; Weightedly superimpose the values in the delay gradient matrix and the correlation coefficient matrix according to a preset ratio to generate the environmental correlation score of this group of charging piles, and arrange the environmental correlation scores of all the charging pile combinations to form an environmental correlation degree matrix.

4. The method according to claim 3, characterized in that, Weightedly superimpose the values in the delay gradient matrix and the correlation coefficient matrix according to a preset ratio to generate the environmental correlation score of this group of charging piles, and arrange the environmental correlation scores of all the charging pile combinations to form an environmental correlation degree matrix, including: Extract the acoustic wave delay change amplitude corresponding to the charging pile combination from the delay gradient matrix, multiply the acoustic wave delay change amplitude by a first preset coefficient to obtain an acoustic wave influence component; Extract the fluctuation correlation degree value of the two voltage fluctuation value sequences of this charging pile combination from the correlation coefficient matrix, multiply the fluctuation correlation degree value by a second preset coefficient to obtain a voltage influence component; Add the acoustic wave influence component and the voltage influence component to generate the environmental correlation score of the charging pile combination, and arrange the environmental correlation scores of all charging pile combinations in the order of charging pile numbers as a symmetric square matrix to form the environmental correlation degree matrix.

5. The method according to claim 2, wherein Input the boundary coordinates, quantity change trend, and interval characteristics into a time series prediction model, and output the vehicle density distribution map per unit area and the predicted value of the average residence time of the charging cluster in the future time window, including: Calculate the coverage area of the rectangular area enclosed by the boundary coordinates of each charging cluster, convert the quantity change trend into a user quantity change sequence at the same time period every day, and process the interval characteristics into the typical time difference between adjacent charging behaviors; Combine the coverage area, user quantity change sequence, and typical time difference into an input data block, arrange the input data block in chronological order and send it into the time series prediction model, and obtain the total number of vehicles and the average vehicle occupancy duration values for each future time period through this model; Divide the total number of vehicles in each future time period by the coverage area corresponding to that time period to form a sequence of the number of vehicles per unit area arranged in chronological order as the vehicle density distribution map, and use the average vehicle occupancy duration value as the predicted value of the average residence time.

6. The method according to claim 1, wherein Using the load priority vector as the allocation weight, allocate the total available power of the service area to each charging pile proportionally, generate a charging pile power adjustment command and send it down for execution, including: Obtain the total available power value of the service area power grid, extract the weight coefficient of each charging cluster from the load priority vector, and multiply the total available power value by the weight coefficient of each charging cluster to obtain the power allocation value of each charging cluster: Obtain the total number of charging piles in each charging cluster, divide the power allocation value by the total number of charging piles to obtain the power setting value of each charging pile; Create an adjustment command containing an identifier and the power setting value for each charging pile, and send the adjustment command to the corresponding charging pile controller to execute power adjustment.

7. The method according to claim 1, wherein According to the environment correlation matrix, the charging piles with indicator values exceeding the set threshold are dynamically aggregated into charging clusters through a clustering algorithm, and the boundary coordinates of each charging cluster are output, including: Set the minimum connection threshold of the environment correlation score in the environment correlation matrix, and initialize each charging pile as an independent charging cluster; Identify the charging pile association relationships in the environment correlation matrix that are greater than the minimum connection threshold, extract the two charging piles corresponding to each satisfied association relationship. If the two charging piles belong to different charging clusters, they are merged into a charging cluster set, and the operation is iteratively executed until no new charging cluster set is generated; Obtain the composition information of all current charging cluster sets, extract the geographical coordinates of the charging piles within the charging cluster sets, integrate all the geographical coordinates into a geographical coordinate set, calculate the minimum and maximum values of the horizontal and vertical coordinates of the geographical coordinate set to form boundary coordinates, and output the boundary coordinates of each charging cluster.

8. A charging pile collaborative control system, characterized in that, Including: A collection module for obtaining the charging migration sequence data of electric vehicle users, parsing the charging migration sequence data to obtain the migration preference matrix and charging interval distribution of the charging piles across service areas within a continuous time window, measuring the acoustic wave delay data set at a fixed distance between charging piles, and synchronously collecting the voltage fluctuation value sequences of each charging pile; A calculation module for converting the acoustic wave delay data set into a delay gradient matrix, calculating the correlation coefficient matrix between the voltage fluctuation value sequences at the same time, and fusing the delay gradient matrix and the correlation coefficient matrix to generate an environment correlation matrix between charging piles; An aggregation module for dynamically aggregating the charging piles with indicator values exceeding the set threshold into charging cluster sets through a clustering algorithm according to the environment correlation matrix, and outputting the boundary coordinates of each charging cluster; A prediction module for jointly inputting the migration preference matrix, charging interval distribution, and the boundary coordinates into a prediction model, outputting the vehicle density distribution map and the predicted average residence duration value of each charging cluster in a future time window, and calculating the load priority vector of each charging cluster based on the vehicle density distribution map, the predicted average residence duration value, and the environment correlation matrix of the charging cluster set; A generation module for using the load priority vector as the allocation weight, proportionally allocating the total available power of the service area to each charging pile, generating a charging pile power adjustment instruction and sending it for execution.

9. A computing device, characterized in that, It includes a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a charging pile collaborative control method according to any one of claims 1 to 7.

10. A computer storage medium, characterized in that, A computer program is stored, and when the computer program is executed by a computer, it implements a charging pile collaborative control method according to any one of claims 1 to 7.

Images