A charging pile control method and system under dynamic load

Abstract

The present invention provides a charging pile control method and system under dynamic load, which relates to the field of charging pile control technology, including: obtaining a target charge time sequence, which refers to a sequence of multiple real-time charges of a target power grid at multiple monitoring moments; obtaining a first control moment, obtaining a first predicted charge; when a first predetermined charge threshold is reached, calling a first predetermined step to generate a first control decision; performing control simulation to obtain first simulation information; introducing a decision fitness evaluation function to perform evaluation and analysis to obtain a first fitness; when a predetermined fitness threshold is reached, taking the first control decision as a target control decision; and controlling the output power of a target charging pile in a target power grid. The present invention solves the technical problems in the prior art that charging piles are difficult to adapt to the dynamic changes of power grid loads in different time periods during the power supply process, and lack an intelligent decision-making mechanism, resulting in poor intelligence and adaptability of charging pile control.

Description

Technical Field

[0001] The present invention relates to the technical field of charging pile control, and in particular to a charging pile control method and system under dynamic load. Background Art

[0002] In smart grids, charging piles are used as charging equipment for electric vehicles, and their operation stability is crucial. However, there are still some problems with the existing technology for controlling charging piles. On the one hand, the load of the power grid may change dramatically in different time periods, such as the large difference between peak and trough periods, which makes it difficult for charging piles to adapt to such dynamic changes during the power supply process; on the other hand, traditional charging pile control methods lack intelligent decision-making mechanisms and cannot flexibly adjust control strategies according to actual conditions, resulting in low efficiency or easy failure of charging piles during the power supply process. Summary of the invention

[0003] The present application provides a charging pile control method under dynamic load, aiming to solve the technical problems in the prior art that the charging pile is difficult to adapt to the dynamic changes of the grid load in different time periods during the power supply process, and lacks an intelligent decision-making mechanism, resulting in poor intelligence and adaptability of the charging pile control.

[0004] In view of the above problems, the present application provides a charging pile control method and system under dynamic load.

[0005] The first aspect disclosed in the present application provides a charging pile control method under dynamic load, the method comprising: obtaining a target charge sequence, the target charge sequence refers to a sequence of multiple real-time charges of a target power grid at multiple monitoring moments; obtaining a first control moment, and obtaining a first predicted charge at the first control moment in combination with the target charge sequence; when the first predicted charge reaches a first predetermined charge threshold, calling a first predetermined step to generate a first control decision; based on the first control decision, performing control simulation on the target power grid to obtain first simulation information; introducing a decision fitness evaluation function to evaluate and analyze the first simulation information to obtain a first fitness; when the first fitness reaches a predetermined fitness threshold, using the first control decision as a target control decision; and controlling the output power of a target charging pile in the target power grid according to the target control decision.

[0006] In a second aspect disclosed in the present application, a charging pile control system under dynamic load is provided, and the system is used for the above-mentioned charging pile control method under dynamic load, and the system includes: a target charge timing acquisition module, the target charge timing acquisition module is used to acquire a target charge timing, and the target charge timing refers to a sequence of multiple real-time charges of a target power grid at multiple monitoring moments; a first predicted charge acquisition module, the first predicted charge acquisition module is used to acquire a first control moment, and obtain a first predicted charge at the first control moment in combination with the target charge timing; a first control decision generation module, the first control decision generation module is used to call a first control decision when the first predicted charge reaches a first predetermined charge threshold. A predetermined step generates a first control decision; a first simulation information generation module, the first simulation information generation module is used to perform control simulation on the target power grid based on the first control decision to obtain first simulation information; a first fitness acquisition module, the first fitness acquisition module is used to introduce a decision fitness evaluation function to evaluate and analyze the first simulation information to obtain a first fitness; a target control decision acquisition module, the target control decision acquisition module is used to use the first control decision as a target control decision when the first fitness reaches a predetermined fitness threshold; an output power control module, the output power control module is used to control the output power of a target charging pile in the target power grid according to the target control decision.

[0007] According to a third aspect disclosed in the present application, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, any step of the first aspect disclosed in the present application is implemented.

[0008] The fourth aspect disclosed in the present application provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements any step of the first aspect disclosed in the present application.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] By obtaining the target charge sequence and predicted charge, the corresponding control decision is called when the predetermined charge threshold is triggered, and the real-time adjustment of the output power of the charging pile is realized. In this way, the charging pile can more flexibly respond to the dynamic changes of the power grid load and improve the stability of the power grid; the decision fitness evaluation function is introduced, and the fitness is obtained by evaluating and analyzing the simulation information, and the control decision is made according to the predetermined fitness threshold. This intelligent decision-making mechanism enables the charging pile to better adapt to the changes in the power grid load and improves the intelligence and adaptability of the control. In summary, the charging pile control method under dynamic load solves the technical problems existing in the prior art such as the difficulty in responding to the dynamic changes of the power grid load and the lack of intelligence in the control decision through an intelligent decision-making mechanism, thereby improving the efficiency and reliability of the charging pile control.

[0011] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 A schematic flow chart of a charging pile control method under dynamic load provided in an embodiment of the present application.

[0013] Figure 2 A schematic diagram of the structure of a charging pile control system under dynamic load provided in an embodiment of the present application.

[0014] Figure 3 This is a diagram of the internal structure of a computer device provided in an embodiment of the present application.

[0015] Explanation of the reference numerals: target charge timing acquisition module 10 , first predicted charge acquisition module 20 , first control decision generation module 30 , first simulation information generation module 40 , first fitness acquisition module 50 , target control decision acquisition module 60 , output power control module 70 . DETAILED DESCRIPTION

[0016] The embodiment of the present application provides a charging pile control method under dynamic load, which solves the technical problems in the prior art that the charging pile is difficult to adapt to the dynamic changes of the grid load in different time periods during the power supply process, and lacks an intelligent decision-making mechanism, resulting in poor intelligence and adaptability of the charging pile control.

[0017] After introducing the basic principles of the present application, various non-limiting implementation methods of the present application will be specifically introduced below in conjunction with the accompanying drawings of the specification. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0018] like Figure 1 As shown, an embodiment of the present application provides a charging pile control method under dynamic load, the method comprising:

[0019] Acquire a target charge time sequence, where the target charge time sequence refers to a sequence consisting of multiple real-time charges of a target power grid at multiple monitoring moments;

[0020] Based on the load characteristics of the power grid, the monitoring frequency and time span are determined, and multiple monitoring moments are generated. The monitoring moments can be collected at fixed time intervals or dynamically selected according to the characteristics of the power grid load changes. At the generated multiple monitoring moments, the charge data of the target power grid is collected in real time through sensors, smart meters and other equipment to obtain multiple real-time charge data, and the obtained multiple real-time charge data are processed in a time series, that is, the corresponding charge values ​​are associated according to the timestamp to form a target charge time series.

[0021] Acquire a first control moment, and obtain a first predicted charge at the first control moment in combination with the target charge time sequence;

[0022] Further, the acquiring the first control moment and obtaining the first predicted charge at the first control moment in combination with the target charge timing includes:

[0023] Obtaining a first real-time charge at a first monitoring moment according to the target charge time sequence, wherein the first monitoring moment is any one of the multiple monitoring moments, and the first real-time charge is a real-time charge corresponding to the first monitoring moment among the multiple real-time charges;

[0024] generating a charge scatter plot based on a first corresponding relationship between the first monitoring time and the first real-time charge;

[0025] Analyzing the charge scatter plot and generating a charge polynomial by fitting;

[0026] The first control time is input into the charge polynomial to obtain the first predicted charge.

[0027] The target charge sequence is a sequence of multiple real-time charges of the target power grid at multiple monitoring moments. In the target charge sequence, the first monitoring moment is determined, and this moment can be any moment under the multiple monitoring moments. After the first monitoring moment is determined, the first real-time charge is obtained according to the real-time charge data corresponding to the moment in the target charge sequence. This real-time charge value reflects the actual load situation of the target power grid at the first monitoring moment.

[0028] A coordinate system is constructed, with the horizontal axis representing the monitoring time and the vertical axis representing the charge value. The first monitoring time and the corresponding first real-time charge are used as coordinate values ​​and plotted on the coordinate system to generate a charge coordinate point, which represents the real-time charge value of the target power grid at the first monitoring time. Based on the corresponding relationship between the first monitoring time and the first real-time charge, a charge scatter plot is generated, through which the real-time charge situation of the target power grid at a specific time can be intuitively displayed.

[0029] Analyze the charge scatter plot and determine the distribution of real-time charge values ​​based on the degree of data dispersion, trend, and whether there is obvious regularity. According to the distribution of the analyzed data, select the corresponding fitting model to fit the charge data. Common fitting models include linear models, polynomial models, exponential models, etc. After selecting the fitting model, use the fitting algorithm to fit the charge scatter data, such as using the least squares method to calculate and generate a charge polynomial.

[0030] Determine the first control moment that needs to be predicted. This moment can be determined according to the power grid operation requirements and is used to predict the charge value at a future moment. The value of the first control moment is input as an independent variable into the charge polynomial to calculate and obtain the first predicted charge value. This value is the predicted value at the first control moment according to the charge polynomial model and is used to predict the charge situation at that moment.

[0031] Furthermore, analyzing the charge scatter diagram and fitting to generate a charge polynomial includes:

[0032] Acquire a first spline scatter point set of the charge scatter diagram based on a random sampling principle;

[0033] Obtaining a first spline curve based on the first spline scattered point set;

[0034] Obtaining a first test scatter point set according to the charge scatter diagram and the first spline scatter point set;

[0035] Testing the first spline curve using the first test scatter point set to obtain a first test result;

[0036] When the first inspection result meets the predetermined constraint, using the first spline curve as the target curve of the target charge time series;

[0037] A target polynomial of the target curve is acquired, and the target polynomial is used as the charge polynomial.

[0038] Based on the random sampling principle, random sampling is performed to obtain the first spline scatter point set of the charge scatter diagram, which means randomly extracting a portion of data points from the original charge scatter diagram as input data for spline interpolation. Spline interpolation is a commonly used numerical method for smooth curve fitting of given data points, including natural spline interpolation, cubic spline interpolation, etc.

[0039] The first spline scatter point set is used as input data, and the spline interpolation method is used to construct a spline interpolation function. This interpolation function can smoothly fit the input scattered data and generate a continuous spline curve. The constructed spline interpolation function is applied to the first spline scatter point set, and the first spline curve is obtained through interpolation calculation. This curve can better fit the scattered data and show the overall trend and characteristics of the data.

[0040] The value of the first spline curve is compared with the actual charge value at the corresponding moment in the charge scatter plot, and the fitting error is calculated. The fitting error is determined by calculating the residual and is used to evaluate the degree of fit of the spline curve to the original data. According to the calculated fitting error, a certain number of test points are selected. These test points can be data points with large fitting errors, or they can be selected according to specific evaluation criteria. The selected test points are used as the first test scatter point set. These points are selected based on the fitting effect between the charge scatter plot and the first spline curve, and are used to further test the fitting results.

[0041] The first spline curve is tested using the selected test indicators, which include fitting error, residual distribution, correlation coefficient, etc. These indicators can evaluate the degree of fit of the spline curve to the original data. Based on the calculated test indicators, the first test result is obtained, which includes information such as the goodness of fit of the spline curve and the degree of conformity with the actual data.

[0042] Determine a predetermined constraint condition, which may be a restriction condition on a test index such as a fitting error, a residual distribution, a correlation coefficient, etc., and is an evaluation standard set according to specific requirements. Evaluate the first test result according to the predetermined constraint condition, that is, determine whether the fitting effect of the first spline curve meets the expected standard. If it meets the predetermined constraint, it can be used as the target curve of the target charge time series.

[0043] According to the characteristics of the target curve, the corresponding target polynomial form is selected. The target polynomial can be a univariate polynomial or a multivariate polynomial, depending on the data characteristics of the target curve. The selected target polynomial form is applied to the data points of the target curve, and the polynomial fitting is performed to obtain the parameters of the target polynomial, including various coefficients and constant terms. The obtained target polynomial is used as a charge polynomial for charge prediction, thereby providing a more accurate reference for power grid operation.

[0044] Furthermore, the testing the first spline curve by using the first test scatter point set to obtain a first test result includes:

[0045] Extracting a first inspection scatter point from the first inspection scatter point set;

[0046] Obtaining a first distance from the first test scatter point to the first spline curve;

[0047] determining whether the first distance is within a predetermined distance threshold;

[0048] If it is, add the first inspection scattered point to the internal point list; if it is not, add the first inspection scattered point to the external point list;

[0049] The ratio of the number of scattered points in the inner point list to the number of scattered points in the outer point list is used as the first test result.

[0050] The first test scatter point set contains test points for evaluating the fitting effect. A point is randomly selected from these test points as the first test scatter point. The distance from the first test scatter point to the first spline curve is calculated. This distance can be calculated using Euclidean distance, Manhattan distance or other distance metrics, and the first distance is obtained by calculation.

[0051] A predetermined distance threshold is set according to actual conditions and specific needs, and the calculated first distance is compared with the predetermined distance threshold. If the first distance is less than or equal to the predetermined distance threshold, it is considered that the fit is good; if the first distance is greater than the predetermined distance threshold, it is considered that the fit is poor.

[0052] According to the judgment result, if the first distance is within the predetermined distance threshold, the first test scatter point is added to the internal point list, which usually contains data points with good fitting effect; if the first distance exceeds the predetermined distance threshold, the first test scatter point is added to the external point list, which contains data points with poor fitting effect.

[0053] Count the number of scattered points in the inner point list and the outer point list to obtain the number of inner points and the number of outer points, and calculate the ratio of the number of inner points to the number of outer points. This ratio reflects the fitting effect of the spline curve on the original data. Generally, a larger ratio indicates a better fitting effect, otherwise it indicates a poor fitting effect. The calculated ratio is used as the first test result to quantitatively evaluate the quality of the fitting effect.

[0054] When the first predicted charge reaches a first predetermined charge threshold, calling a first predetermined step to generate a first control decision;

[0055] The first predetermined charge threshold is set according to the actual situation and specific needs to determine how to make a control decision on the predicted charge. The first predetermined step is a set parameter, which indicates the amount of charge adjusted each time after the first predetermined charge threshold is reached. One threshold corresponds to multiple unit steps, and a suitable control step can be determined by simulation. When the first predicted charge reaches the first predetermined charge threshold, a first control decision is generated according to the retrieved first predetermined step, which includes increasing or decreasing the output power of the power grid, or adjusting other relevant parameters to achieve target control, so as to ensure the stable operation of the power grid and meet the charge demand.

[0056] Performing control simulation on the target power grid based on the first control decision to obtain first simulation information;

[0057] Use power system simulation software to establish a simulation model of the target power grid, including information such as simulated power grid topology and power grid load characteristics. Import the first control decision into the simulation model, adjust the output power of the charging pile, control the connection and disconnection of the charging pile, adjust the power grid load, etc. according to the control decision, run the simulation model, simulate the operation of the target power grid under the first control decision, and simulate the dynamic changes of the power grid, including the charging and discharging process, the change of the power grid load, the change of the power grid parameters, etc. During the simulation operation, collect simulation data in real time, including the actual output power of the charging pile, the power grid load, the power grid stability and other data, and generate the first simulation information based on the data obtained from the simulation operation.

[0058] Introducing a decision fitness evaluation function to evaluate and analyze the first simulation information to obtain a first fitness;

[0059] Furthermore, the step of introducing a decision fitness evaluation function to evaluate and analyze the first simulation information to obtain a first fitness includes:

[0060] Sequentially extracting a first charging pile and a second charging pile from the target charging piles;

[0061] Sequentially extracting a first simulated power sequence of the first charging pile and a second simulated power sequence of the second charging pile from the first simulation information;

[0062] Respectively analyzing and obtaining a first stability index of the first simulation power time series and a second stability index of the second simulation power time series;

[0063] Reading a predetermined unit time length, and analyzing the first simulation power time series in combination with the predetermined unit time length to obtain a first unit power sum, and analyzing the second simulation power time series to obtain a second unit power sum;

[0064] Obtaining a first deviation index between the first unit power sum and the second unit power sum;

[0065] The decision fitness evaluation function obtains the first fitness based on the first stability index, the second stability index and the first deviation index.

[0066] Determine the target charging pile, which can be any group of charging piles in the power grid, and extract the first charging pile and the second charging pile from the target charging pile one by one. Extract the power of the first charging pile in the first simulation information, sort the power by time, obtain the first simulation power sequence, extract the power sequence of the second charging pile, sort the power by time, and obtain the second simulation power sequence.

[0067] The stability index is calculated for the first simulation power sequence and the second simulation power sequence. The calculation method is, for example, to calculate the standard deviation. The smaller the standard deviation, the smaller the power fluctuation and the higher the stability; to calculate the variance. The smaller the variance, the smaller the power fluctuation and the higher the stability; to calculate the mean absolute deviation. The smaller the deviation, the smaller the power fluctuation and the higher the stability. According to the above calculation method, the first stability index of the first simulation power sequence and the second stability index of the second simulation power sequence are calculated. These indexes reflect the stability of the power output of the charging pile.

[0068] Determine the predetermined unit duration, which can be one hour, half an hour, ten minutes, etc., and is set as needed. According to the set predetermined unit duration, the first simulation power time series is divided according to the unit duration, and the total power in each unit duration is calculated to obtain the first unit power sum, which represents the total power of the first charging pile within the predetermined unit duration. Similarly, according to the set predetermined unit duration, the second simulation power time series is divided and calculated to obtain the second unit power sum, which represents the total power of the second charging pile within the predetermined unit duration.

[0069] Calculate the deviation between the first unit power sum and the second unit power sum, for example, directly calculate the absolute difference between the first unit power sum and the second unit power sum, convert the calculated deviation value into a percentage form, and obtain a first deviation index, which is used to represent the degree of deviation between the first unit power sum and the second unit power sum.

[0070] A decision fitness evaluation function is defined, and the calculated first stability index, second stability index and first deviation index are used as input parameters of the fitness evaluation function. The fitness evaluation function is operated to obtain a first fitness, which is used to evaluate the performance and stability of the first charging pile and the second charging pile.

[0071] Further, the respectively analyzing and obtaining a first stability index of the first simulation power time series and a second stability index of the second simulation power time series includes:

[0072] The first simulation power sequence includes a plurality of simulation powers;

[0073] Obtaining a first simulated power average value of the multiple simulated powers;

[0074] The first stability index is obtained by adding the first simulation power mean and the first power deviation of the first simulation power, wherein the first simulation power is any one of the multiple simulation powers.

[0075] Acquire multiple simulated power data included in the first simulated power time series, which are collected according to the simulated time series and record the simulated power output of the charging pile at different time points. For multiple simulated power data, calculate their average value, that is, add all simulated power data to obtain the sum, and then divide the sum by the number of simulated power data to obtain the first simulated power mean value.

[0076] One of the multiple simulated powers is randomly selected as the first simulated power, and the power deviation between the first simulated power and the first simulated power mean is calculated, that is, the difference between the first simulated power and the first simulated power mean is calculated to generate the first power deviation. The multiple simulated powers are traversed to generate multiple first power deviations, and all the first power deviation values ​​are added up to obtain a first stability index.

[0077] Furthermore, the expression of the decision fitness evaluation function is as follows:

[0078] ;

[0079] in, characterizing the first fitness of the first control decision, Characterizing the i-th stability index of the i-th charging pile under the first control decision, the target charging piles include m charging piles, Characterize the deviation index of the unit power sum of two adjacent charging piles under the first control decision, the target power grid includes n deviation indexes, and n=m-1, a and b respectively represent the first weight and the second weight, and a+b=1.

[0080] Specifically, the purpose of this function is to comprehensively consider the stability of the charging pile and the deviation of the unit power and, by adjusting the weight coefficients a and b, to balance the impact of these two indicators on the decision-making fitness. Among them, a larger weight will increase the contribution of the corresponding indicator, and vice versa. The function designed in this way can comprehensively evaluate the different performance indicators of the charging pile according to specific needs, thereby achieving reasonable control decisions.

[0081] When the first fitness reaches a predetermined fitness threshold, taking the first control decision as a target control decision;

[0082] A predetermined fitness threshold is set. This threshold can be determined according to the operation requirements and performance requirements of the target power grid. Reaching this threshold means that the control decision has achieved the expected effect. The fitness value is compared with the threshold. When the first fitness value reaches the predetermined fitness threshold, the condition is met to enter the next step; if it does not reach it, the next round of fitness calculation is continued until the threshold is reached. When the first fitness reaches the predetermined fitness threshold, the first control decision is used as the target control decision, which means that the first control decision is determined to be an effective control strategy in simulation and evaluation and can be applied to actual power grid control.

[0083] The output power of the target charging pile in the target power grid is controlled according to the target control decision.

[0084] Based on the target control decision, the specific strategy for output power control of the target charging pile is determined, including increasing or decreasing the output power of the charging pile, adjusting the charging period or charging mode, and other operations. According to the determined control strategy, the actual output power control of the target charging pile is carried out to achieve effective regulation and management of the grid load, meet charging needs and ensure the stability of grid operation.

[0085] In summary, the charging pile control method under dynamic load provided by the embodiment of the present application has the following technical effects:

[0086] 1. By obtaining the target charge sequence and predicted charge, the corresponding control decision is called when the predetermined charge threshold is triggered, so that the output power of the charging pile can be adjusted in real time. In this way, the charging pile can respond to the dynamic changes of the grid load more flexibly and improve the stability of the grid;

[0087] 2. A decision fitness evaluation function is introduced to evaluate and analyze the simulation information to obtain the fitness and make control decisions based on the predetermined fitness threshold. This intelligent decision-making mechanism enables the charging pile to better adapt to changes in grid load and improves the intelligence and adaptability of the control.

[0088] In summary, the charging pile control method under dynamic load solves the technical problems existing in the prior art such as difficulty in coping with dynamic changes in grid load and insufficient intelligence of control decisions through an intelligent decision-making mechanism, thereby improving the efficiency and reliability of charging pile control.

[0089] Based on the same inventive concept as the charging pile control method under dynamic load in the above-mentioned embodiment, Figure 2 As shown, the present application provides a charging pile control system under dynamic load, the system comprising:

[0090] A target charge time sequence acquisition module 10, wherein the target charge time sequence acquisition module 10 is used to acquire a target charge time sequence, wherein the target charge time sequence refers to a sequence composed of multiple real-time charges of a target power grid at multiple monitoring moments;

[0091] A first predicted charge acquisition module 20, the first predicted charge acquisition module 20 is used to acquire a first control moment, and obtain a first predicted charge at the first control moment in combination with the target charge time sequence;

[0092] A first control decision generating module 30, wherein the first control decision generating module 30 is configured to call a first predetermined step to generate a first control decision when the first predicted charge reaches a first predetermined charge threshold;

[0093] A first simulation information generating module 40, the first simulation information generating module 40 is used to perform control simulation on the target power grid based on the first control decision to obtain first simulation information;

[0094] A first fitness acquisition module 50, the first fitness acquisition module 50 is used to introduce a decision fitness evaluation function to evaluate and analyze the first simulation information to obtain a first fitness;

[0095] A target control decision acquisition module 60, wherein the target control decision acquisition module 60 is configured to use the first control decision as a target control decision when the first fitness reaches a predetermined fitness threshold;

[0096] The output power control module 70 is used to control the output power of the target charging pile in the target power grid according to the target control decision.

[0097] Furthermore, the system further includes obtaining a first predicted charge module to perform the following operation steps:

[0098] Obtaining a first real-time charge at a first monitoring moment according to the target charge time sequence, wherein the first monitoring moment is any one of the multiple monitoring moments, and the first real-time charge is a real-time charge corresponding to the first monitoring moment among the multiple real-time charges;

[0099] generating a charge scatter plot based on a first corresponding relationship between the first monitoring time and the first real-time charge;

[0100] Analyzing the charge scatter plot and generating a charge polynomial by fitting;

[0101] 240 Input the first control time into the charge polynomial to obtain the first predicted charge.

[0102] Furthermore, the system further includes a charge polynomial acquisition module to perform the following operation steps:

[0103] Acquire a first spline scatter point set of the charge scatter diagram based on a random sampling principle;

[0104] Obtaining a first spline curve based on the first spline scattered point set;

[0105] Obtaining a first test scatter point set according to the charge scatter diagram and the first spline scatter point set;

[0106] Testing the first spline curve using the first test scatter point set to obtain a first test result;

[0107] When the first inspection result meets the predetermined constraint, using the first spline curve as the target curve of the target charge time series;

[0108] A target polynomial of the target curve is acquired, and the target polynomial is used as the charge polynomial.

[0109] Furthermore, the system further includes a first test result acquisition module to perform the following operation steps:

[0110] Extracting a first inspection scatter point from the first inspection scatter point set;

[0111] Obtaining a first distance from the first test scatter point to the first spline curve;

[0112] determining whether the first distance is within a predetermined distance threshold;

[0113] If it is, add the first inspection scattered point to the internal point list; if it is not, add the first inspection scattered point to the external point list;

[0114] The ratio of the number of scattered points in the inner point list to the number of scattered points in the outer point list is used as the first test result.

[0115] Furthermore, the system further includes obtaining a first fitness module to perform the following operation steps:

[0116] Sequentially extracting a first charging pile and a second charging pile from the target charging piles;

[0117] Sequentially extracting a first simulated power sequence of the first charging pile and a second simulated power sequence of the second charging pile from the first simulation information;

[0118] Respectively analyzing and obtaining a first stability index of the first simulation power time series and a second stability index of the second simulation power time series;

[0119] Reading a predetermined unit time length, and analyzing the first simulation power time series in combination with the predetermined unit time length to obtain a first unit power sum, and analyzing the second simulation power time series to obtain a second unit power sum;

[0120] Obtaining a first deviation index between the first unit power sum and the second unit power sum;

[0121] The decision fitness evaluation function obtains the first fitness based on the first stability index, the second stability index and the first deviation index.

[0122] Furthermore, the system further includes a first stability index acquisition module to perform the following operation steps:

[0123] The first simulation power sequence includes a plurality of simulation powers;

[0124] Obtaining a first simulated power average value of the multiple simulated powers;

[0125] The first stability index is obtained by adding the first simulation power mean and the first power deviation of the first simulation power, wherein the first simulation power is any one of the multiple simulation powers.

[0126] Furthermore, the expression of the decision fitness evaluation function is as follows:

[0127] ;

[0128] in, characterizing the first fitness of the first control decision, Characterizing the i-th stability index of the i-th charging pile under the first control decision, the target charging piles include m charging piles, Characterize the deviation index of the unit power sum of two adjacent charging piles under the first control decision, the target power grid includes n deviation indexes, and n=m-1, a and b respectively represent the first weight and the second weight, and a+b=1.

[0129] Through the above detailed description of a charging pile control method under a dynamic load in this specification, those skilled in the art can clearly understand a charging pile control system under a dynamic load in this embodiment. Since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0130] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 3As shown. The computer device includes a processor, a memory and a network interface connected through a system bus, wherein the processor of the computer device is used to provide computing and control capabilities; the memory of the computer device includes a non-volatile storage medium and an internal memory, wherein the non-volatile storage medium stores an operating system, a computer program and a database, and the internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium; the network interface of the computer device is used to communicate with an external terminal through a network connection. The computer program is executed by the processor to implement a charging pile control method under dynamic load.

[0131] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0132] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0133] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A charging pile control method under dynamic load, characterized in that: The method comprises: Acquire a target charge time sequence, where the target charge time sequence refers to a sequence consisting of multiple real-time charges of a target power grid at multiple monitoring moments; Acquire a first control moment, and obtain a first predicted charge at the first control moment in combination with the target charge time sequence; When the first predicted charge reaches a first predetermined charge threshold, calling a first predetermined step to generate a first control decision; Performing control simulation on the target power grid based on the first control decision to obtain first simulation information; Introducing a decision fitness evaluation function to evaluate and analyze the first simulation information to obtain a first fitness; When the first fitness reaches a predetermined fitness threshold, taking the first control decision as a target control decision; Controlling the output power of a target charging pile in the target power grid according to the target control decision; The step of introducing a decision fitness evaluation function to evaluate and analyze the first simulation information to obtain a first fitness includes: Sequentially extracting a first charging pile and a second charging pile from the target charging piles; Sequentially extracting a first simulated power sequence of the first charging pile and a second simulated power sequence of the second charging pile from the first simulation information; Respectively analyzing and obtaining a first stability index of the first simulation power time series and a second stability index of the second simulation power time series; Reading a predetermined unit time length, and analyzing the first simulation power time series in combination with the predetermined unit time length to obtain a first unit power sum, and analyzing the second simulation power time series to obtain a second unit power sum; Obtaining a first deviation index between the first unit power sum and the second unit power sum; The decision fitness evaluation function obtains the first fitness based on the first stability index, the second stability index and the first deviation index; The respectively analyzing and obtaining a first stability index of the first simulation power time series and a second stability index of the second simulation power time series comprises: The first simulation power sequence includes a plurality of simulation powers; Obtaining a first simulated power average value of the multiple simulated powers; Adding the first simulation power mean and the first power deviation of the first simulation power to obtain the first stability index, wherein the first simulation power is any one of the multiple simulation powers; The expression of the decision fitness evaluation function is as follows: ； in, characterizing the first fitness of the first control decision, Characterizing the i-th stability index of the i-th charging pile under the first control decision, the target charging piles include m charging piles, Characterize the deviation index of the unit power sum of two adjacent charging piles under the first control decision, the target power grid includes n deviation indexes, and n=m-1, a and b respectively represent the first weight and the second weight, and a+b=1.

2. According to the charging pile control method under dynamic load as described in claim 1, it is characterized in that: The obtaining of the first control moment and obtaining a first predicted charge at the first control moment in combination with the target charge timing includes: Obtaining a first real-time charge at a first monitoring moment according to the target charge time sequence, wherein the first monitoring moment is any one of the multiple monitoring moments, and the first real-time charge is a real-time charge corresponding to the first monitoring moment among the multiple real-time charges; generating a charge scatter plot based on a first corresponding relationship between the first monitoring time and the first real-time charge; Analyzing the charge scatter plot and generating a charge polynomial by fitting; The first control time is input into the charge polynomial to obtain the first predicted charge.

3. According to the charging pile control method under dynamic load as described in claim 2, it is characterized in that: The step of analyzing the charge scatter diagram and fitting and generating a charge polynomial comprises: Acquire a first spline scatter point set of the charge scatter point diagram based on a random sampling principle; Obtaining a first spline curve based on the first spline scattered point set; Obtaining a first test scatter point set according to the charge scatter diagram and the first spline scatter point set; Testing the first spline curve using the first test scatter point set to obtain a first test result; When the first inspection result meets the predetermined constraint, using the first spline curve as the target curve of the target charge time series; A target polynomial of the target curve is acquired, and the target polynomial is used as the charge polynomial.

4. According to the charging pile control method under dynamic load as claimed in claim 3, it is characterized in that: The step of testing the first spline curve by using the first test scatter point set to obtain a first test result includes: Extracting a first inspection scatter point from the first inspection scatter point set; Obtaining a first distance from the first test scatter point to the first spline curve; determining whether the first distance is within a predetermined distance threshold; If it is, add the first inspection scattered point to the internal point list; if it is not, add the first inspection scattered point to the external point list; The ratio of the number of scattered points in the inner point list to the number of scattered points in the outer point list is used as the first test result.

5. A charging pile control system under dynamic load, characterized in that: For implementing a charging pile control method under dynamic load according to any one of claims 1 to 4, the system comprises: A target charge timing acquisition module, which is used to acquire a target charge timing, wherein the target charge timing refers to a sequence composed of multiple real-time charges of a target power grid at multiple monitoring moments; A first predicted charge acquisition module, the first predicted charge acquisition module is used to acquire a first control moment, and obtain a first predicted charge at the first control moment in combination with the target charge time sequence; A first control decision generating module, the first control decision generating module is used to call a first predetermined step to generate a first control decision when the first predicted charge reaches a first predetermined charge threshold; A first simulation information generating module, the first simulation information generating module is used to perform control simulation on the target power grid based on the first control decision to obtain first simulation information; A first fitness acquisition module, wherein the first fitness acquisition module is used to introduce a decision fitness evaluation function to evaluate and analyze the first simulation information to obtain a first fitness; a target control decision acquisition module, wherein the target control decision acquisition module is used to use the first control decision as a target control decision when the first fitness reaches a predetermined fitness threshold; An output power control module, wherein the output power control module is used to control the output power of a target charging pile in the target power grid according to the target control decision.

6. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of a charging pile control method under dynamic load described in any one of claims 1 to 4 are implemented.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of a charging pile control method under dynamic load described in any one of claims 1 to 4 are implemented.

Images