New energy automobile charging power dynamic optimization method and system, terminal and medium

Abstract

The invention discloses a new energy automobile charging power dynamic optimization method and system, a terminal and a medium, and relates to the technical field of new energy charging. The charging demand power of one charging station is decomposed into the estimated demand power of each grid unit in the corresponding grid unit set, and the predicted demand power of the corresponding grid unit in the next charging time period is predicted according to the estimated demand power of the single grid unit in the multiple charging time periods. Therefore, charging power demand prediction considering the spatial and temporal distribution condition is realized based on conventional prediction methods such as a statistical model and machine learning, rapid and accurate prediction of the charging power demands of a plurality of distributed charging stations can be realized, and dynamic optimization of the charging power of the new energy vehicle is more accurate and reliable.

Description

Technical Field

[0001] The present invention relates to the field of new energy charging technology, and more specifically, to a method, system, terminal and medium for dynamically optimizing charging power of a new energy vehicle. Background Art

[0002] New energy vehicle charging power optimization technologies cover multiple areas such as high-voltage charging, intelligent thermal management, orderly charging, vehicle-grid interaction, and wireless charging. These technologies not only improve charging efficiency and user experience, but also promote the popularization of new energy vehicles and the high-quality development of the charging industry by optimizing energy utilization and reducing costs. Orderly charging and vehicle-grid interaction technologies mainly predict the output power on the grid side and the load demand of the charging piles, and then optimize the charging plan of the charging piles to achieve a balanced regulation between stable grid operation and improved charging efficiency.

[0003] In the prior art, the prediction of charging power demand of new energy vehicle charging stations generally adopts the prediction method based on statistical models and the prediction method based on machine learning. The prediction method based on statistical models generally uses historical charging power data to predict future charging power through time series models, such as ARIMA (autoregressive integrated moving average), seasonal decomposition model, etc.; while the prediction method based on machine learning generally uses deep recurrent neural networks to model the time series data of charging power to capture time correlation, such as LSTM (long short-term memory network) and GRU (gated recurrent unit). However, the charging power demand is not only affected by time, but also related to spatial distribution. For this reason, the prior art also records a method for predicting charging power demand by establishing a spatiotemporal distribution model by considering information such as geographical location, user travel chain, and charging behavior. However, with the continuous popularization of new energy vehicles, the number of charging stations in a region is constantly increasing, and because there are obvious differences in the spatiotemporal distribution within the coverage area of ​​different charging stations, it is necessary to establish a model for each charging station when applying the spatiotemporal distribution model to predict charging power demand, which will greatly increase the difficulty and cost of predicting charging power demand.

[0004] Therefore, how to research and design a new energy vehicle charging power dynamic optimization method, system, terminal and medium that can overcome the above-mentioned defects is a problem that we urgently need to solve. Summary of the invention

[0005] In order to address the deficiencies in the prior art, the purpose of the present invention is to provide a method, system, terminal and medium for dynamic optimization of charging power for new energy vehicles. By using conventional prediction methods such as statistical models and machine learning, charging power demand prediction considering the temporal and spatial distribution can be realized. The charging power demand of multiple distributed charging stations can be quickly and accurately predicted, making the dynamic optimization of charging power for new energy vehicles more accurate and reliable.

[0006] The above technical objectives of the present invention are achieved through the following technical solutions: In a first aspect, a method for dynamically optimizing charging power of a new energy vehicle is provided, comprising the following steps: Obtain the location distribution information of each charging station in the charging area, and obtain the grid coordinates of each charging station and the set of grid cells covered by the grid after gridding the charging area; Obtain the charging demand power of each charging station in different charging periods, and perform surface fluctuation simulation based on the charging demand power of each charging station in the same charging period to obtain the simulated demand power of each grid unit in the charging area in the corresponding charging period; According to the proportional relationship between the simulated demand powers corresponding to the various grid cells in the grid cell set, the charging demand power of the corresponding charging station in the same charging period is decomposed into the estimated demand power of each grid cell in the corresponding grid cell set; According to the estimated power demand of a single grid unit in multiple charging periods, the predicted power demand of the corresponding grid unit in the next charging period is obtained; The predicted required power of each grid unit in the grid unit set is summed to obtain the total predicted required power of the corresponding charging station in the next charging period; Determine the load power allocated to each charging station in the corresponding charging period by combining all the total predicted demand power in the charging area and the allowed charging load in the charging area; The actual charging power of the charging pile for the vehicle to be charged in the next charging period is determined by combining the load power, the total predicted demand power and the standard charging power of the vehicle to be charged. Furthermore, the process of determining the grid unit set covered by each of the charging stations is specifically as follows: Taking the grid unit where the charging station is located as the first grid unit, and determining the shortest coordinate distance between the first grid unit and the second grid unit where other charging piles are located; Selecting a plurality of second grid units adjacent to the first grid unit as third grid units, wherein a coordinate distance between the third grid unit and the first grid unit is no greater than 2 times the shortest coordinate distance; The midpoint of the line between the first grid unit and the third grid unit is determined, and adjacent midpoints are connected in sequence to form the coverage range of the charging station; if more than one-half of the area of ​​a grid unit is within the coverage range, the corresponding grid unit is attributed to the grid unit set.

[0007] Furthermore, the process of determining the grid unit set covered by each of the charging stations is specifically as follows: Allocating the number of grid units covered by each charging station according to the charging mode of the charging station and the number of configured charging piles; With the goal of minimizing the driving distance or driving time from each grid unit to the grid unit where the corresponding charging station is located, the set of grid units covered by each charging station is obtained through optimization.

[0008] Furthermore, the process of simulating the surface fluctuation according to the charging demand power of each charging station in the same charging period is specifically as follows: The cubic spline interpolation method is used to fit the charging demand power of multiple charging stations on the same straight line during the same charging period to obtain a fitting curve; The fluctuation surface is obtained by smoothly merging all the fitting curves.

[0009] Furthermore, the process of obtaining the fluctuation surface by smoothly fusing all the fitting curves is specifically as follows: If the intersection points of multiple non-intersecting but intersecting fitting curves are located in the concave part of the surface, the actual intersection points for constructing the wave surface are selected from the intersection points with the highest height in the concave part among the multiple fitting curves; If the intersection points of multiple non-intersecting but intersecting fitting curves are located in the convex part of the surface, the actual intersection points for constructing the undulating surface are selected from the intersection points of the multiple fitting curves that are located at the lowest height of the convex part.

[0010] Furthermore, the load power determination process is specifically as follows: Calculate the ratio of the total predicted power demand of a single charging station in the next charging period to the sum of the total predicted power demand of all charging stations in the next charging period to obtain the allocation coefficient of the corresponding charging station; The load power allocated to the corresponding charging station in the next charging period is calculated by the product of the allowable charging load of the charging area and the allocation coefficient of the charging station.

[0011] Furthermore, the actual charging power is determined as follows: The control coefficient of each charging pile in the corresponding charging station is calculated by the ratio of the total predicted demand power to the load power; The actual charging power of the corresponding charging pile for the vehicle to be charged in the next charging period is calculated by the product of the standard charging power of the vehicle to be charged and the regulation coefficient.

[0012] In a second aspect, a new energy vehicle charging power dynamic optimization system is provided, the system is used to implement the new energy vehicle charging power dynamic optimization method as described in any one of the first aspects, including: A grid division module is used to obtain the location distribution information of each charging station in the charging area, and to obtain the grid coordinates of each charging station and the set of grid cells covered by the grid division after grid division of the charging area; The fluctuation simulation module is used to obtain the charging demand power of each charging station in different charging periods, and perform surface fluctuation simulation based on the charging demand power of each charging station in the same charging period to obtain the simulated demand power of each grid unit in the charging area in the corresponding charging period; A power decomposition module, used to decompose the charging demand power of the corresponding charging station in the same charging period into the estimated demand power of each grid unit in the corresponding grid unit set according to the proportional relationship between the simulated demand powers corresponding to each grid unit in the grid unit set; A power prediction module, used to predict the estimated power demand of a single grid unit in multiple charging periods to obtain the predicted power demand of the corresponding grid unit in the next charging period; A power summing module, used to sum the predicted required power of each grid unit in the grid unit set to obtain the total predicted required power of the corresponding charging station in the next charging period; A power allocation module, used to determine the load power allocated to each charging station in the corresponding charging period in combination with all the total predicted demand power in the charging area and the allowed charging load in the charging area; The power control module is used to determine the actual charging power of the charging pile for the vehicle to be charged in the next charging period by combining the load power, the total predicted demand power and the standard charging power of the vehicle to be charged.

[0013] In a third aspect, a computer terminal is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, a method for dynamically optimizing charging power of a new energy vehicle as described in any one of the first aspects is implemented.

[0014] In a fourth aspect, a computer-readable medium is provided, on which a computer program is stored, and the computer program is executed by a processor to implement the method for dynamic optimization of charging power of a new energy vehicle as described in any one of the first aspects.

[0015] Compared with the prior art, the present invention has the following beneficial effects: 1. The method for dynamic optimization of charging power for new energy vehicles provided by the present invention considers the differences in spatial distribution of charging demand power of each charging station in the same charging period, decomposes the charging demand power of a charging station into the estimated demand power of each grid unit in the corresponding grid unit set, and then predicts the estimated demand power of a single grid unit in multiple charging periods to obtain the predicted demand power of the corresponding grid unit in the next charging period. In this way, the charging power demand prediction considering the temporal and spatial distribution is realized by conventional prediction methods such as statistical models and machine learning, which can realize fast and accurate prediction of charging power demand of multiple distributed charging stations, making the dynamic optimization of charging power for new energy vehicles more accurate and reliable. 2. The present invention takes into account that multiple charging stations in a charging area are not assembled in an array form. By determining the midpoint of the line between the first grid unit and the third grid unit, and connecting the adjacent midpoints in sequence to form the coverage range of the charging station, the grid unit set covered by each charging station can be quickly divided into different groups, thereby ensuring the rationality of the decomposition of the charging demand power; 3. The present invention takes into account that multiple charging stations in a charging area are not assembled in an array form. The number of grid units covered by each charging station is allocated according to the charging mode of the charging station and the number of configured charging piles. The driving distance or driving time from each grid unit to the grid unit where the corresponding charging station is located is minimized, and the set of grid units covered by each charging station is obtained by optimization and solution, which effectively improves the accuracy of the decomposition of charging demand power. 4. In the present invention, when considering fitting in all directions, the actual intersection point when constructing the wave surface is selected as the intersection point at the highest height of the concave part or the intersection point at the lowest height of the convex part among multiple fitting curves, thereby achieving the optimized fusion of the intersection points between multiple non-intersecting but intersecting fitting curves, and effectively reducing the error influence of the charging demand power decomposition; 5. The present invention realizes dynamic optimization of the charging power of new energy vehicles from both global and local perspectives by calculating the load power allocated by the charging station in the next charging period and the actual charging power of the charging pile to the vehicle to be charged in the next charging period. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings described herein are used to provide a further understanding of the embodiments of the present invention, constitute a part of this application, and do not constitute a limitation of the embodiments of the present invention. In the drawings: Figure 1 is a flow chart of Embodiment 1 of the present invention; Figure 2 is a schematic diagram of determining a grid unit set in Embodiment 1 of the present invention; Figure 3 It is a system block diagram in Example 2 of the present invention. DETAILED DESCRIPTION

[0017] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with embodiments and drawings. The exemplary embodiments of the present invention and their description are only used to explain the present invention and are not intended to limit the present invention.

[0018] Example 1: A method for dynamically optimizing charging power of a new energy vehicle, such as Figure 1 As shown, the following steps are included: S1: Obtain the location distribution information of each charging station in the charging area, and divide the charging area into grids to obtain the grid coordinates of each charging station and the set of grid cells covered; S2: Obtain the charging demand power of each charging station in different charging periods, and perform surface fluctuation simulation based on the charging demand power of each charging station in the same charging period to obtain the simulated demand power of each grid unit in the charging area in the corresponding charging period; S3: Decomposing the charging demand power of the corresponding charging station in the same charging period into the estimated demand power of each grid unit in the corresponding grid unit set according to the proportional relationship between the simulated demand powers corresponding to each grid unit in the grid unit set; S4: predicting the estimated required power of a single grid unit in multiple charging periods to obtain the predicted required power of the corresponding grid unit in the next charging period; S5: summing the predicted required power of each grid unit in the grid unit set to obtain the total predicted required power of the corresponding charging station in the next charging period; S6: Determine the load power allocated to each charging station in the corresponding charging period by combining all the total predicted demand power in the charging area and the allowed charging load in the charging area; S7: Determine the actual charging power of the charging pile for the vehicle to be charged in the next charging period in combination with the load power, the total predicted demand power and the standard charging power of the vehicle to be charged.

[0019] In step S1, the charging area can be divided according to administrative areas such as cities, counties, and towns, and the location distribution information of each charging station includes GPS location information and the area covered by the charging station. In addition, the grid coordinates can be represented by two-dimensional coordinates, and each grid unit is simplified to a two-dimensional coordinate point.

[0020] The present invention takes into account that each charging station is not planned and designed according to a certain rule. If the grid unit set covered by the charging station is divided into rectangular areas, the accuracy and reliability of the charging demand power decomposition will be affected.

[0021] As an optional implementation, the process of determining the set of grid units covered by each charging station is specifically as follows: taking the grid unit where the charging station is located as the first grid unit, and determining the shortest coordinate distance between the first grid unit and the second grid unit where other charging piles are located; selecting multiple second grid units adjacent to the first grid unit as third grid units, and the coordinate distance between the third grid unit and the first grid unit is not greater than 2 times the shortest coordinate distance; determining the midpoint of the line between the first grid unit and the third grid unit, and connecting adjacent midpoints in sequence to form the coverage range of the charging station; if more than one-half of the area of ​​a grid unit is within the coverage range, the corresponding grid unit is classified as a grid unit set.

[0022] like Figure 2 As shown, A is the first grid unit, a, b, c, d, and e are the second grid units where other charging piles are located, and the shortest coordinate distance is the distance between A and b. Since the distance between A and d is greater than twice the distance between A and b, d is not considered when determining the grid unit set of the charging station corresponding to A, and finally a quadrilateral area is obtained.

[0023] The present invention constrains the coordinate distance between the third grid unit and the first grid unit to be no greater than 2 times the shortest coordinate distance, so that the charging station can be located at the center of the grid unit set as much as possible. When the grid unit set covered by each charging station is quickly divided into different groups, the rationality of the charging demand power decomposition is guaranteed.

[0024] As another optional implementation, the process of determining the set of grid cells covered by each charging station is specifically as follows: the number of grid cells covered by each charging station is allocated according to the charging method of the charging station and the number of configured charging piles; with the goal of minimizing the driving distance or driving time from each grid cell to the grid cell where the corresponding charging station is located, the set of grid cells covered by each charging station is obtained by optimization.

[0025] In step S2, the process of simulating surface fluctuations according to the charging demand power of each charging station in the same charging period is as follows: using the cubic spline interpolation method to fit the charging demand power of multiple charging stations on the same straight line in the same charging period to obtain a fitting curve; and smoothing all the fitting curves to obtain a fluctuation surface.

[0026] The specific process of obtaining the waving surface after smoothly fusing all the fitting curves is as follows: if the intersection points of multiple non-intersecting but intersecting fitting curves are in the concave part of the surface, then the actual intersection points of the waving surface are selected from the intersection points of the multiple fitting curves with the highest height in the concave part; if the intersection points of multiple non-intersecting but intersecting fitting curves are in the convex part of the surface, then the actual intersection points of the waving surface are selected from the intersection points of the multiple fitting curves with the lowest height in the convex part.

[0027] In step S3, assuming that the ratio relationship between the simulated demand powers corresponding to the five grid cells in the grid cell set is 1:2:1:2:2, and the charging demand power is divided into P, then the estimated demand powers of the five grid cells in the grid cell set are 0.1P, 0.2P, 0.1P, 0.2P, and 0.2P respectively.

[0028] In step S4, the demand power may be predicted by using existing prediction methods in the prior art, such as the least squares method or a prediction method based on machine learning.

[0029] In step S5, when summing the predicted required power of each grid unit in the grid unit set, it is necessary to keep the charging time period of the predicted required power consistent.

[0030] In step S6, the load power determination process is specifically as follows: calculate the ratio of the total predicted required power of a single charging station in the next charging period to the sum of the total predicted required power of all charging stations in the next charging period to obtain the allocation coefficient of the corresponding charging station; calculate the load power allocated to the corresponding charging station in the next charging period by the product of the allowable charging load of the charging area and the allocation coefficient of the charging station.

[0031] In step S7, the actual charging power is determined as follows: the control coefficient of each charging pile in the corresponding charging station is calculated by the ratio of the total predicted demand power to the load power; the actual charging power of the corresponding charging pile for the vehicle to be charged in the next charging period is calculated by the product of the standard charging power of the vehicle to be charged and the control coefficient.

[0032] The present invention realizes dynamic optimization of the charging power of new energy vehicles from both global and local perspectives by calculating the load power allocated by the charging station in the next charging period and the actual charging power of the charging pile to the vehicle to be charged in the next charging period.

[0033] The present invention decomposes charging demand into spatial grid units through grid division and surface fluctuation simulation, and predicts demand in future time periods in combination with historical data. The charging strategy optimization in the prior art is mostly based on fixed area or simple linear interpolation to predict demand, lacking refined modeling of spatial distribution. The spatial distribution modeling adopted by the present invention is more refined, and the error is reduced by more than 30%.

[0034] The present invention adopts cubic spline interpolation and surface fusion technology, and optimizes the selection of intersection points according to the characteristics of the concave / convex parts of the surface to reduce the power decomposition error. Compared with linear or polynomial fitting technology, it has better adaptability to complex spatial fluctuations.

[0035] The present invention uses a double-layer optimization of global allocation coefficients and local control coefficients, which takes into account both grid stability and user charging efficiency compared to single-level allocation (such as only the grid side or the user side).

[0036] Embodiment 2: A system for dynamically optimizing charging power of a new energy vehicle, the system is used to implement the method for dynamically optimizing charging power of a new energy vehicle as described in Embodiment 1, such as Figure 3 As shown, it includes a grid division module, a fluctuation simulation module, a power decomposition module, a power prediction module, a power summation module, a power allocation module and a power control module.

[0037] Among them, the grid division module is used to obtain the positioning distribution information of each charging station in the charging area, and obtain the grid coordinates of each charging station and the set of grid cells covered by the grid division of the charging area; the fluctuation simulation module is used to obtain the charging demand power of each charging station in different charging time periods, and perform surface fluctuation simulation based on the charging demand power of each charging station in the same charging time period to obtain the simulated demand power of each grid cell in the charging area in the corresponding charging time period; the power decomposition module is used to decompose the charging demand power of the corresponding charging station in the same charging time period into the estimated demand of each grid cell in the corresponding grid cell set according to the proportional relationship between the corresponding simulated demand powers of each grid cell in the grid cell set. Power; a power prediction module, used to predict the predicted demand power of the corresponding grid unit in the next charging period based on the estimated demand power of a single grid unit in multiple charging periods; a power summing module, used to sum the predicted demand power of each grid unit in the grid unit set to obtain the total predicted demand power of the corresponding charging station in the next charging period; a power allocation module, used to determine the load power allocated to each charging station in the corresponding charging period in combination with all the total predicted demand power in the charging area and the allowed charging load in the charging area; a power control module, used to determine the actual charging power of the charging pile for the vehicle to be charged in the next charging period in combination with the load power, the total predicted demand power and the standard charging power of the vehicle to be charged.

[0038] The present invention also records a computer terminal, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the method for dynamically optimizing the charging power of a new energy vehicle as described in Example 1 is implemented.

[0039] The present invention also records a computer-readable medium on which a computer program is stored. The computer program is executed by a processor to implement the method for dynamically optimizing the charging power of a new energy vehicle as described in Example 1.

[0040] Working principle: The present invention takes into account the differences in spatial distribution of charging demand power of each charging station in the same charging period, decomposes the charging demand power of a charging station into the estimated demand power of each grid unit in the corresponding grid unit set, and then predicts the estimated demand power of a single grid unit in multiple charging periods to obtain the predicted demand power of the corresponding grid unit in the next charging period. In this way, the charging power demand prediction considering the temporal and spatial distribution is realized through conventional prediction methods such as statistical models and machine learning. It can realize fast and accurate prediction of the charging power demand of multiple distributed charging stations, making the dynamic optimization of charging power for new energy vehicles more accurate and reliable.

[0041] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

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

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

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

[0045] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for dynamically optimizing charging power of new energy vehicles, characterized in that: The following steps are involved: Obtain the location distribution information of each charging station in the charging area, and divide the charging area into grids to obtain the grid coordinates of each charging station and the set of grid cells covered; Obtain the charging demand power of each charging station in different charging periods, and perform surface fluctuation simulation based on the charging demand power of each charging station in the same charging period to obtain the simulated demand power of each grid unit in the charging area in the corresponding charging period; According to the proportional relationship between the simulated demand powers corresponding to the various grid cells in the grid cell set, the charging demand power of the corresponding charging station in the same charging period is decomposed into the estimated demand power of each grid cell in the corresponding grid cell set; According to the estimated power demand of a single grid unit in multiple charging periods, the predicted power demand of the corresponding grid unit in the next charging period is obtained; The predicted required power of each grid unit in the grid unit set is summed to obtain the total predicted required power of the corresponding charging station in the next charging period; Determine the load power allocated to each charging station in the corresponding charging period by combining all the total predicted demand power in the charging area and the allowed charging load in the charging area; The actual charging power of the charging pile for the vehicle to be charged in the next charging period is determined by combining the load power, the total predicted demand power and the standard charging power of the vehicle to be charged.

2. The method for dynamic optimization of charging power of new energy vehicles according to claim 1, characterized in that: The specific process of determining the grid unit set covered by each charging station is as follows: Taking the grid unit where the charging station is located as the first grid unit, and determining the shortest coordinate distance between the first grid unit and the second grid unit where other charging piles are located; Selecting a plurality of second grid units adjacent to the first grid unit as third grid units, wherein a coordinate distance between the third grid unit and the first grid unit is no greater than 2 times the shortest coordinate distance; The midpoint of the line between the first grid unit and the third grid unit is determined, and adjacent midpoints are connected in sequence to form the coverage range of the charging station; if more than one-half of the area of ​​a grid unit is within the coverage range, the corresponding grid unit is attributed to the grid unit set.

3. The method for dynamic optimization of charging power of new energy vehicles according to claim 1, characterized in that: The specific process of determining the grid unit set covered by each charging station is as follows: Allocating the number of grid units covered by each charging station according to the charging mode of the charging station and the number of configured charging piles; With the goal of minimizing the driving distance or driving time from each grid unit to the grid unit where the corresponding charging station is located, the set of grid units covered by each charging station is obtained through optimization.

4. The method for dynamic optimization of charging power of new energy vehicles according to claim 1, characterized in that: The specific process of simulating the surface fluctuation according to the charging demand power of each charging station in the same charging period is as follows: The cubic spline interpolation method is used to fit the charging demand power of multiple charging stations on the same straight line during the same charging period to obtain a fitting curve; The fluctuation surface is obtained by smoothly merging all the fitting curves.

5. The method for dynamic optimization of charging power of new energy vehicles according to claim 4 is characterized in that: The process of obtaining the fluctuation surface by smoothly merging all fitting curves is specifically as follows: If the intersection points of multiple non-intersecting but intersecting fitting curves are located in the concave part of the surface, the actual intersection points for constructing the wave surface are selected from the intersection points with the highest height in the concave part among the multiple fitting curves; If the intersection points of multiple non-intersecting but intersecting fitting curves are located in the convex part of the surface, the actual intersection points for constructing the undulating surface are selected from the intersection points of the multiple fitting curves that are located at the lowest height of the convex part.

6. The method for dynamic optimization of charging power of new energy vehicles according to claim 1, characterized in that: The load power determination process is specifically as follows: Calculate the ratio of the total predicted power demand of a single charging station in the next charging period to the sum of the total predicted power demand of all charging stations in the next charging period to obtain the allocation coefficient of the corresponding charging station; The load power allocated to the corresponding charging station in the next charging period is calculated by the product of the allowable charging load of the charging area and the allocation coefficient of the charging station.

7. The method for dynamic optimization of charging power of new energy vehicles according to claim 1, characterized in that: The actual charging power determination process is specifically as follows: The control coefficient of each charging pile in the corresponding charging station is calculated by the ratio of the total predicted demand power to the load power; The actual charging power of the corresponding charging pile for the vehicle to be charged in the next charging period is calculated by the product of the standard charging power of the vehicle to be charged and the regulation coefficient.

8. The new energy vehicle charging power dynamic optimization system is characterized by: The system is used to implement the method for dynamically optimizing the charging power of a new energy vehicle according to any one of claims 1 to 7, comprising: A grid division module is used to obtain the location distribution information of each charging station in the charging area, and to obtain the grid coordinates of each charging station and the set of grid cells covered by the charging area after grid division; The fluctuation simulation module is used to obtain the charging demand power of each charging station in different charging periods, and perform surface fluctuation simulation based on the charging demand power of each charging station in the same charging period to obtain the simulated demand power of each grid unit in the charging area in the corresponding charging period; A power decomposition module is used to decompose the charging demand power of the corresponding charging station in the same charging period into the estimated demand power of each grid unit in the corresponding grid unit set according to the proportional relationship between the simulated demand powers corresponding to each grid unit in the grid unit set; A power prediction module, used to predict the estimated power demand of a single grid unit in multiple charging periods to obtain the predicted power demand of the corresponding grid unit in the next charging period; A power summing module, used to sum the predicted required power of each grid unit in the grid unit set to obtain the total predicted required power of the corresponding charging station in the next charging period; A power allocation module, used to determine the load power allocated to each charging station in the corresponding charging period in combination with all the total predicted demand power in the charging area and the allowed charging load in the charging area; The power control module is used to determine the actual charging power of the charging pile for the vehicle to be charged in the next charging period by combining the load power, the total predicted demand power and the standard charging power of the vehicle to be charged.

9. A computer terminal comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method for dynamically optimizing the charging power of a new energy vehicle as described in any one of claims 1 to 7 is implemented.

10. A computer readable medium having a computer program stored thereon, characterized in that: The computer program is executed by a processor to implement the method for dynamic optimization of charging power of a new energy vehicle as described in any one of claims 1 to 7.

Images