Method, device and equipment for locating and sizing electric vehicle charging station and medium

Abstract

The invention relates to the technical field of charging station addressing, and discloses an electric vehicle charging station addressing and sizing method, device, equipment and medium, and the method comprises the steps: firstly obtaining the GPS data of a target area to generate a geographic data graph, carrying out the grid division for multiple times, and combining the grid reasonability index of the charging station to determine the addressing capacity of the charging station; and finely dividing an actual grid set suitable for the target area. Aiming at each actual grid, analyzing the charging demand and the service capability of the actual grid, determining the range of the number of charging stations, and generating a candidate station combination set according to the range; and then, optimizing the position and capacity configuration of the charging station by using a charging station locating and sizing model, ensuring that the charging station provides efficient service at a reasonable position, balancing the load of the power grid and reducing the charging waiting time, and finally improving the utilization efficiency and the overall service level of the charging station. According to the technical scheme, the site selection of the charging station can be optimized, the charging time of a user is reduced through reasonable configuration and layout, and the utilization rate of the charging station is improved.

Description

Technical Field

[0001] This application relates to the field of charging station site selection technology, and in particular to a method, apparatus, equipment and medium for determining the site location of electric vehicle charging stations. Background Technology

[0002] With the rapid development of the electric vehicle market, the construction of charging infrastructure has become a key issue restricting the industry's development. Despite the increasing number of charging devices, challenges remain in the layout, configuration, and utilization efficiency of charging stations. Traditional research focuses more on construction costs, coverage, and traffic flow, neglecting the details of user experience and charging demand. Factors such as user charging behavior, charging time, distance, and charging pile type directly affect the utilization rate of charging stations and service satisfaction.

[0003] Therefore, optimizing the location of charging stations, rationally configuring their layout to reduce users' charging time, and improving the utilization rate of charging stations are urgent technical problems that need to be solved. Summary of the Invention

[0004] This application provides a method, apparatus, equipment, and medium for site selection and capacity determination of electric vehicle charging stations, which achieves the technical effects of optimizing the site selection of charging stations, rationally configuring the layout to reduce users' charging time, and improving the utilization rate of charging stations.

[0005] To achieve the above objectives, the main technical solutions adopted in this application include: In a first aspect, embodiments of this application provide a method for site selection and capacity determination of electric vehicle charging stations, the method comprising: Obtain GPS data for the target area, and generate a geographic data map of the target area based on the GPS data; Based on the geographic data map, the charging stations in the target area are divided into grids multiple times. For each set of charging station grids obtained from the division, a reasonableness index of the charging station grid set is calculated. Based on the calculated reasonableness index, an actual grid set suitable for the target area is determined. The reasonableness index is determined based on the charging compensation relationship between each charging station grid in the charging station grid set. Traverse each actual grid in the actual grid set, and for any actual grid, identify the total charging demand of the actual grid. Determine the range of the number of charging stations based on the maximum and minimum service capabilities of the charging stations in the actual grid and the total charging demand. Based on the combinations of different numbers of charging stations within the range of the number of charging stations, a set of candidate site combinations corresponding to the actual grid is determined; wherein, each candidate site combination represents the number of candidate sites; For any candidate site combination in the candidate site combination set, a target charging station location and capacity determination scheme is determined based on a pre-set charging station location and capacity determination model; wherein, the charging station location and capacity determination model is constructed based on the charging pile type, the number of different types of charging piles in each charging station, and the coverage of the charging station.

[0006] This embodiment provides a method for site selection and capacity determination of electric vehicle charging stations. It generates a geographic data map based on GPS data of the target area, performs multiple grid divisions, calculates the rationality index of each grid, and evaluates the compensation relationship and load adjustment capacity between charging station grids. Then, based on the rationality index, the most suitable set of grids is selected to ensure effective coverage of charging demand within the area. By analyzing the total charging demand and service capacity of each grid, a reasonable range for the number of charging stations is determined, thereby generating a candidate site combination set. Finally, using a charging station site selection and capacity determination model, the site selection and capacity configuration of charging stations are optimized to ensure that charging stations provide efficient service in optimal locations, reducing resource waste and overload. This method, through such refined grid division and optimized layout, can improve the utilization efficiency of charging stations, reduce user charging waiting time, balance grid load, and thus effectively improve the overall efficiency of charging services and user experience.

[0007] In one implementation, the rationality index of the charging station grid set includes: Retrieve multiple pre-defined statistical time periods; For any statistical period and for any charging station grid in the charging station grid set, a first number of charging stations with charging compensation relationships in the charging station grid is determined within the statistical period, and a charging compensation coefficient of the charging station grid is generated based on each first number obtained in each statistical period. The average value of the charging compensation coefficient of each charging station grid in the charging station grid set is obtained, and the average value is used as the rationality index of the charging station grid set.

[0008] This embodiment acquires multiple preset statistical time periods and, within each time period, determines the number of charging stations with charging compensation relationships within each charging station grid in the charging station grid set. Based on the number of charging stations counted in each time period, a charging compensation coefficient for the charging station grid is generated. Then, the average charging compensation coefficient of all charging station grids is calculated as a rationality index to evaluate the overall layout and operational efficiency of the charging station grid. This method effectively identifies areas with small load fluctuations and strong charging compensation capabilities, thereby optimizing charging station location selection, rationally distributing charging stations, improving charging station utilization, reducing user charging wait times, and enhancing overall charging efficiency.

[0009] In one implementation, determining the range of the number of charging stations based on the maximum and minimum service capabilities of the charging stations within the actual grid and the total charging demand includes: The minimum number of charging stations is determined based on the maximum service capacity of the charging stations within the actual grid and the total charging demand. The maximum number of charging stations is determined based on the minimum service capacity of the charging stations within the actual grid and the total charging demand. The range from the minimum number of charging stations to the maximum number of charging stations is defined as the range of the number of charging stations.

[0010] This embodiment ensures coverage of every charging demand point by determining the minimum number of charging stations, avoiding resource waste. Then, it determines the maximum number of charging stations to prevent over-construction, ensuring that service capacity matches demand. Next, cluster analysis is used to select different numbers of charging stations, effectively optimizing charging station site selection, improving resource utilization, reducing user charging time, avoiding duplicate coverage and blank areas within the actual grid, and improving the efficiency of charging station usage.

[0011] In one implementation, determining the candidate site combination set corresponding to the actual grid based on combinations of different numbers of charging stations within the range of the number of charging stations includes: For each type of charging station within the range of charging station quantities, determine the distance from each charging demand point within the actual grid to the cluster center, and determine the sum of squared errors based on the distances; A relationship diagram is plotted showing the sum of squared errors corresponding to different numbers of charging stations, and the candidate station combination set is determined from the relationship diagram.

[0012] This embodiment calculates the distance from each charging demand point to the cluster center based on the number of charging stations, and evaluates the matching degree between charging demand points and charging stations using the sum of squared errors. A smaller sum of squared errors indicates a shorter distance between the charging demand point and the charging station, resulting in a higher matching degree. This optimizes charging station site selection and improves charging station coverage and utilization. Next, by plotting the relationship between the sum of squared errors and the number of charging stations, an appropriate number of charging stations is selected to avoid resource waste or insufficient coverage. With a reasonable layout, the distance to the charging station for users is shortened, charging waiting time is reduced, and overall charging efficiency and user experience are improved. Simultaneously, it also enables the scientific allocation of regional resources, ensuring a balanced distribution of charging stations across different areas and achieving efficient resource utilization.

[0013] In one implementation, determining the candidate site combination set corresponding to the actual grid based on combinations of different numbers of charging stations within the range of the number of charging stations includes: For each type of charging station quantity within the range of charging station quantities, determine the first average distance from each charging demand point in the actual grid to the adjacent charging demand points in the same cluster. Determine the second average distance from each charging demand point within the actual grid to the charging demand point in the nearest cluster; Based on the ratio between the first average distance and the second average distance, a single profile coefficient is determined for each charging demand point, and an overall profile coefficient matching the number of each type of charging station is determined based on the single profile coefficient. The overall contour coefficients are filtered to obtain the candidate site combination set.

[0014] This embodiment assesses cluster density by calculating the first average distance from each charging demand point to its nearest neighboring charging demand points within the same cluster, ensuring effective charging station coverage of the actual grid and reducing user waiting time. Secondly, calculating the second average distance from each charging demand point to the nearest charging demand point in its cluster helps assess inter-cluster separation, avoiding redundant coverage and improving site utilization. Furthermore, combining this with the calculation of the profile coefficient allows for a comprehensive evaluation of cluster quality, ensuring the rationality of the number and layout of charging stations and avoiding over- or under-construction. Finally, by filtering the overall profile coefficient, the optimal number and layout of charging stations are determined, thereby optimizing charging station configuration, improving charging station utilization, and reducing user charging time.

[0015] In one implementation, the objective function in the charging station site selection and sizing model is constructed as follows: For any combination of candidate sites and the corresponding locations of the candidate sites, determine the target total construction cost corresponding to any combination of candidate sites; Determine the coverage area that matches the location of the candidate sites, and determine the target coverage rate corresponding to any combination of candidate sites based on the coverage area; The target coverage rate is converted into target coverage loss cost using a preset penalty cost coefficient; The objective function is defined by summing the total construction cost of the target and the loss cost of the target coverage.

[0016] This embodiment ensures the economic feasibility of the charging station site selection and capacity allocation scheme by calculating the target total construction cost corresponding to the candidate site combination; by determining the coverage range and target coverage rate of the candidate site locations, it ensures that the charging stations can meet user needs, thereby shortening users' charging time and waiting time; then, by using a penalty cost coefficient, insufficient coverage is quantified into economic loss, prompting the optimization algorithm to improve the coverage rate; finally, by combining the target total construction cost and the target coverage loss cost, an objective function is constructed to find the optimal charging station site selection and capacity allocation scheme, which satisfies user needs while controlling costs.

[0017] In one implementation, determining the target total construction cost corresponding to any candidate site combination includes: For any combination of candidate sites and the corresponding candidate site locations, determine the construction cost, equipment cost, equipment maintenance cost, and power consumption cost matching each candidate site location; Based on the decision variable of whether to build a charging station at the candidate site location, the construction cost, the equipment cost, the equipment maintenance cost, and the electricity consumption cost are weighted and summed to obtain the single total construction cost matching each candidate site location; Based on the total construction cost of all the individual sites, determine the target total construction cost corresponding to any combination of candidate sites.

[0018] This embodiment determines the construction cost, equipment cost, equipment maintenance cost, and electricity consumption cost for each candidate site location. Then, it uses decision variables to determine whether to build a charging station at that candidate site location. By weighted summing of all costs, the total construction cost for each candidate site location is obtained. Finally, based on all individual total construction costs, the final target total construction cost is determined. The optimization goal is not only to select the lowest-cost site but also to consider site utilization and user demand, rationally configuring site layout to ensure that charging stations meet user needs while having high utilization and low operating costs.

[0019] In one implementation, determining the target coverage corresponding to any candidate site combination includes: Determine the coverage area that matches the candidate site location, and filter the target charging demand points within the coverage area; The ratio between the target charging demand points and the total charging demand is determined as the target coverage rate corresponding to any candidate site combination.

[0020] This embodiment determines the coverage area of ​​each candidate site location and filters out the target charging demand points within that coverage area. Then, it calculates the target coverage rate by proving the ratio of the target charging demand points covered by each candidate site location to the total demand points. This target coverage rate reflects the effectiveness of the site selection and helps assess whether the site can effectively meet user needs. A higher target coverage rate indicates that the site selection better serves users, thereby improving the utilization rate of charging stations and reducing users' charging wait times.

[0021] Secondly, embodiments of this application provide a site selection and capacity determination device for electric vehicle charging stations, the device comprising: A geographic data acquisition unit is used to acquire GPS data of a target area and generate a geographic data map of the target area based on the GPS data. The grid set determination unit is used to perform multiple grid divisions of charging stations within the target area based on the geographic data map, and to calculate the rationality index of the charging station grid set for each division, and to determine the actual grid set suitable for the target area based on the calculated rationality index; wherein, the rationality index is determined based on the charging compensation relationship between each charging station grid in the charging station grid set. The charging station quantity determination unit is used to traverse each actual grid in the actual grid set, and for any actual grid, identify the total charging demand of the actual grid, and determine the range of the number of charging stations based on the maximum and minimum service capabilities of the charging stations in the actual grid and the total charging demand. The candidate site determination unit is used to determine the set of candidate site combinations corresponding to the actual grid based on the combinations of different numbers of charging stations within the range of the number of charging stations; wherein, each candidate site combination represents the number of candidate sites; The site selection and capacity determination unit is used to determine the target charging station site selection and capacity determination scheme based on a pre-set charging station site selection and capacity determination model for any candidate site combination in the candidate site combination set; wherein, the charging station site selection and capacity determination model is constructed based on the charging pile type, the number of different types of charging piles in each charging station and the coverage of the charging station.

[0022] Thirdly, embodiments of this application provide a computer device, including: The system includes a memory and a processor, which are interconnected. The memory stores computer instructions, and the processor executes these computer instructions to perform the aforementioned method for selecting and determining the location and capacity of electric vehicle charging stations.

[0023] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer instructions, which are used to cause a computer to execute the above-described electric vehicle charging station site selection and capacity determination method. Attached Figure Description

[0024] To more clearly illustrate the technical solutions in the specific embodiments of this application or the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0025] Figure 1 A flowchart illustrating a method for site selection and capacity determination of an electric vehicle charging station, as provided in this application embodiment; Figure 2 A flowchart illustrating the rationality index of the statistical charging station grid set provided in this application embodiment; Figure 3 A flowchart for determining the range of the number of charging stations provided in this application embodiment; Figure 4 A flowchart of the first step S7 provided in the embodiments of this application; Figure 5 A flowchart of the second step S7 provided in the embodiments of this application; Figure 6 A flowchart illustrating the construction method of the objective function in the charging station site selection and sizing model provided in this application embodiment; Figure 7 A flowchart of step S91 provided in an embodiment of this application; Figure 8 A flowchart of step S93 provided in the embodiments of this application; Figure 9 A block diagram of an electric vehicle charging station site selection and capacity determination device provided in this application embodiment; Figure 10 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0026] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0027] With the rapid rise of the electric vehicle (EV) market, the construction of charging infrastructure has become a key bottleneck restricting the sustainable and healthy development of the EV industry. As the number of EVs surges, the demand for charging equipment also increases significantly. While the growth in the number of charging stations can be seen as a positive development for the industry, the relationship between the quantity and quality of charging stations remains a major issue that urgently needs to be addressed. The layout, configuration, and utilization efficiency of charging facilities directly impact the speed of EV adoption and user experience. Whether the distribution of charging stations is reasonable, the equipment configuration is scientific, and the utilization rate meets standards all affect users' charging convenience and service satisfaction.

[0028] In recent years, a large body of literature has explored the site selection and capacity determination of electric vehicle charging stations. These issues are constrained by various factors, including land costs, construction costs, traffic flow, transportation networks, and charging demand. These factors provide a complex decision-making context for charging station site selection and capacity determination. Traditional research has primarily focused on the construction investment costs of charging stations, typically using mathematical optimization models to select suitable locations and sizes to ensure that charging stations can cover a predetermined area and meet basic traffic flow demands.

[0029] However, most current research focuses on macro-level factors such as the cost, coverage, and traffic flow of charging infrastructure, neglecting the user experience and specific needs of charging stations. In reality, user charging behavior and satisfaction with charging services play a crucial role in the actual operation of charging stations. Considering users' charging needs at different times and in different locations can not only effectively improve the user charging experience but also optimize the operational efficiency of charging stations.

[0030] Charging behavior research has gained increasing attention in recent years, particularly regarding how to incorporate users' actual needs and charging habits into charging station site selection and capacity assessment models. When choosing a charging station, factors such as charging time, distance, charging pile type (e.g., slow, fast, and super-fast charging), and service quality all significantly impact the station's utilization rate. If a charging station cannot provide sufficient fast charging facilities, users may abandon the station due to long waiting times, leading to low utilization and potential user churn. Furthermore, the geographical location of the charging station is also a key factor influencing user charging demand. If a station is located far from major traffic flow or inaccessible, it may result in lower user frequency, affecting the overall utilization efficiency of the facility.

[0031] Therefore, optimizing the location of charging stations, rationally configuring their layout to reduce users' charging time, and improving the utilization rate of charging stations are urgent technical problems that need to be solved.

[0032] To address the aforementioned technical problems, according to an embodiment of this application, an embodiment of a method for site selection and capacity determination of electric vehicle charging stations is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0033] This embodiment provides a method for site selection and capacity determination of electric vehicle charging stations. Figure 1 A flowchart of a method for site selection and capacity determination of an electric vehicle charging station provided in this application embodiment is shown below. Figure 1 As shown, the process includes the following steps: Step S1: Obtain GPS data for the target area and generate a geographic data map of the target area based on the GPS data.

[0034] Specifically, the target area can be a city, urban area, or specific region. To address the site selection and capacity determination issue, it is first necessary to define the coverage area of ​​the charging facilities and determine the area where GPS data needs to be collected. GPS data sources can include GPS trajectory data from vehicles such as taxis, buses, and private cars. This trajectory data provides a wealth of traffic flow, road conditions, and driving behavior data. It should be noted that the data collection process here is based on user permission to ensure data privacy protection. This data can be uploaded and collected through in-vehicle GPS devices and mobile applications (such as taxi or ride-sharing platforms). The GPS data is then used to analyze traffic flow within the target area, including peak hours, traffic hotspots, and traffic bottlenecks. Charging demand in different areas is analyzed, especially in areas frequently visited by electric vehicle users, such as commercial areas, residential areas, and public transportation hubs. Geographic Information System (GIS) tools such as ArcGIS are used to overlay GPS data with existing street maps, traffic networks, and urban infrastructure data. Through spatial analysis, areas with dense traffic flow and high user charging demand are identified. These areas are typically the optimal locations for electric vehicle charging stations.

[0035] Step S3: Based on the geographic data map, the charging stations in the target area are divided into grids multiple times. For each set of charging station grids obtained from the division, the rationality index of the charging station grid set is calculated. Based on the calculated rationality index, the actual grid set suitable for the target area is determined. The rationality index is determined based on the charging compensation relationship between each charging station grid in the charging station grid set.

[0036] Specifically, based on geographic data maps, Geographic Information System (GIS) tools are used to divide the grid multiple times using different grid sizes, such as 1km×1km and 2km×2km. Multiple preset statistical time periods are obtained, and within each time period, the number of charging stations with charging compensation relationships within each charging station grid set is determined. Based on the number of charging stations counted in each time period, a charging compensation coefficient for each charging station grid is generated. Then, the average charging compensation coefficient of all charging station grids is calculated as a rationality index to evaluate the overall layout and operational efficiency of the charging station grid. The rationality indices of the charging station grid sets obtained from each grid division are compared. The charging station grid set with the highest rationality index is selected as the final actual grid set adopted.

[0037] Step S5: Traverse each actual grid in the actual grid set, and for any actual grid, identify the total charging demand of the actual grid. Based on the maximum and minimum service capabilities of the charging stations in the actual grid and the total charging demand, determine the range of the number of charging stations.

[0038] Specifically, the number of electric vehicles (EVs) is one of the most fundamental indicators for measuring charging demand. With the increasing prevalence of EVs, charging demand also increases. When selecting and allocating charging station locations, each actual grid is analyzed individually to obtain the total charging demand, i.e., the total charging demand of all vehicles in each actual network. Based on historical data of vehicle charging behavior from the geographical data map, the number of times vehicles charge and the amount of electricity charged within each grid can be statistically analyzed. Where n is the number of vehicles in the actual grid.

[0039] For example, the total charging demand of a certain actual grid during a specific time period is 10,000 vehicles.

[0040] Step S7: Based on the combinations of different numbers of charging stations within the range of the number of charging stations, determine the set of candidate site combinations corresponding to the actual grid; wherein, each candidate site combination represents the number of candidate sites.

[0041] Specifically, based on the total charging demand, within a defined range of minimum and maximum charging station numbers, different numbers of charging stations are selected for cluster analysis. Each combination represents a possible charging station layout scheme, where the number of clusters represents the number of candidate stations. Charging demand points are divided using clustering algorithms (such as K-means) to generate multiple candidate station combinations. These combinations not only cover different numbers of stations but also reflect the distribution of charging stations under different layout schemes in the actual grid, providing diverse options for subsequent optimization analysis.

[0042] Step S9: For any candidate site combination in the candidate site combination set, determine the target charging station location and capacity scheme based on the pre-set charging station location and capacity model; wherein, the charging station location and capacity model is constructed based on the charging pile type, the number of different types of charging piles in each charging station and the coverage of the charging station.

[0043] Specifically, the constraints in the charging station site selection and capacity determination model include charging station load, travel time, charging pile type selection, and the number of multiple types of charging piles; among them, the charging station load constraints include: Basic load constraints: Among them, P i,t Let be the load of the i-th confirmed construction site at time t; This represents the maximum load that the i-th confirmed site can withstand.

[0044] Load balance constraints: Where m is the number of sites that have been determined to be constructed; P g,t Let t be the total power that the power grid can provide at time t. In the load constraint model, in addition to considering the load capacity of a single charging station, it is also necessary to consider the load of each station and the power supply capacity of the external power grid or the load balance between other stations. Travel time constraints: Among them, T w,i (t) represents the travel time of electric vehicle w to the designated station i; dis(S w -S i ) represents the distance from the current location of electric vehicle w to the designated station i; μ(t) is the congestion coefficient at time t, reflecting the actual traffic situation; T max The maximum permissible time for electric vehicle w to travel to the designated construction site i; Average driving speed; v represents the number of electric vehicles located on road segment L at time t; w (t) represents the real-time driving speed; dis(L) w (t)-L w (t-1)) represents the geographical distance of electric vehicle w at time t and time t-1; The sampling period.

[0045] Constraints for selecting charging station type: in, Select the charging method of charging station i for electric vehicle w at time t; m is the number of stations that have been determined to be built.

[0046] The constraints on the number of various types of charging piles include: Constraints on the number of slow charging stations: in, Let be the number of slow charging stations required by the electric vehicle at charging station i at time t. The number of slow charging piles built at charging station i.

[0047] Fast charging station quantity constraints: in, Let t be the number of fast charging stations required for the electric vehicle at charging station i at time t. The number of fast charging piles built at charging station i.

[0048] Constraints on the number of super-fast charging stations: in, Let be the number of super-fast charging stations required for the electric vehicle at charging station i at time t. The number of super-fast charging piles built at charging station i.

[0049] By constructing a charging station site selection and capacity determination model, which comprehensively considers two objective functions—total construction cost and coverage rate—and introduces constraints such as charging station load, driving time, charging pile type selection, and the number of multiple types of charging piles, the optimal configuration of charging station layout can be achieved. This model not only ensures the economic efficiency of charging stations but also improves service coverage and user experience, providing a scientific basis for the site selection and capacity determination of electric vehicle charging stations.

[0050] For any candidate site cluster combination in the candidate site cluster combination set, the charging station location and capacity determination model is solved to obtain the target charging station location and capacity determination scheme corresponding to the minimum objective function.

[0051] Specifically, the objective function is minimized while satisfying the constraints. The CPLEX solver in MATLAB is used to solve the charging station site selection and capacity grading model. For example, it can be a comprehensive cost difference analysis under different charging pile configurations, such as only slow charging piles, only slow and fast charging piles, or slow, fast and super-fast charging piles. The output is the target charging station site selection and capacity grading scheme corresponding to the minimum objective function, which ensures that the layout of charging stations achieves a balance between economy and service coverage under the premise of meeting cost, load and user experience constraints.

[0052] This embodiment provides a method for site selection and capacity determination of electric vehicle charging stations. It generates a geographic data map based on GPS data of the target area, performs multiple grid divisions, calculates the rationality index of each grid, and evaluates the compensation relationship and load adjustment capacity between charging station grids. Then, based on the rationality index, the most suitable set of grids is selected to ensure effective coverage of charging demand within the area. By analyzing the total charging demand and service capacity of each grid, a reasonable range for the number of charging stations is determined, thereby generating a candidate site combination set. Finally, using a charging station site selection and capacity determination model, the site selection and capacity configuration of charging stations are optimized to ensure that charging stations provide efficient service in optimal locations, reducing resource waste and overload. This method, through such refined grid division and optimized layout, can improve the utilization efficiency of charging stations, reduce user charging waiting time, balance grid load, and thus effectively improve the overall efficiency of charging services and user experience.

[0053] Figure 2 A flowchart illustrating the rationality index of the statistical charging station grid set provided in this application embodiment, the flowchart may include the following steps: Step S31: Obtain multiple pre-set statistical time periods.

[0054] Specifically, to analyze a charging station grid, statistical time periods need to be pre-defined. These time periods can be scheduled regularly, such as every hour, every two hours, or every half day. The choice of statistical time periods depends on the analysis requirements, and typically selects time intervals that have a significant impact on fluctuations in charging demand. Statistical time periods form the basis for analyzing charging station usage, determining the load status of charging stations within these time intervals and whether off-peak charging can be achieved.

[0055] Step S33: For any statistical time period and for any charging station grid in the charging station grid set, determine the first number of charging stations with charging compensation relationship in the charging station grid within the statistical time period, and generate the charging compensation coefficient of the charging station grid based on the first number obtained in each statistical time period.

[0056] Specifically, for each charging station grid in the charging station grid set, within each statistical period, a first number of charging station grids with charging compensation relationships are determined. Then, these data are used to calculate the charging compensation coefficient for each charging station grid. A charging compensation relationship refers to the relationship between two charging stations if their power supply loads are staggered (i.e., one at a peak and the other at a trough) within the same statistical period. The charging compensation coefficient is calculated as follows: Among them, R i The charging compensation coefficient for the i-th charging station grid; T is the total number of statistical periods; Ni (t) represents the number of charging stations with charging compensation relationships in the i-th charging station grid within the statistical time period t, i.e., the first number; Max(N) i (t) represents the maximum number of charging stations with charging compensation relationships in the i-th charging station grid across all statistical periods.

[0057] In other words, the compensation coefficient for each charging station grid takes into account the ratio of the number of charging stations with a compensation relationship to the maximum number within different statistical periods. The purpose of this is to compare the load changes of the charging station grid at different times. The more volatile the charging station grid, the lower its compensation coefficient, indicating poorer rationality; conversely, the more stable the charging station grid, the higher its compensation coefficient, indicating better rationality.

[0058] Step S35: Calculate the average value of the charging compensation coefficient of each charging station grid in the charging station grid set, and use the average value as the rationality index of the charging station grid set.

[0059] Specifically, the average charging compensation coefficient of all charging station grids is calculated, and this is used as a rationality index for the entire charging station grid set. The specific calculation method is as follows: Where R is the rationality index of the entire charging station grid set; K is the total number of charging station grids contained in the charging station grid set.

[0060] The overall rationality index is obtained by calculating the average charging compensation coefficient of each charging station grid. A higher rationality index indicates that the load fluctuation of each charging station grid in the entire charging station grid set is smaller and that it has a better charging compensation capability; conversely, a lower rationality index indicates that the load fluctuation of each charging station grid in the charging station grid set is larger and that the charging compensation capability is poor.

[0061] This embodiment acquires multiple preset statistical time periods and, within each time period, determines the number of charging stations with charging compensation relationships within each charging station grid in the charging station grid set. Based on the number of charging stations counted in each time period, a charging compensation coefficient for the charging station grid is generated. Then, the average charging compensation coefficient of all charging station grids is calculated as a rationality index to evaluate the overall layout and operational efficiency of the charging station grid. This method effectively identifies areas with small load fluctuations and strong charging compensation capabilities, thereby optimizing charging station location selection, rationally distributing charging stations, improving charging station utilization, reducing user charging wait times, and enhancing overall charging efficiency.

[0062] Figure 3 The flowchart for determining the range of the number of charging stations provided in this application embodiment may include the following steps: Step S51: Determine the minimum number of charging stations based on the maximum service capacity of the actual charging stations within the grid and the total charging demand.

[0063] Specifically, by calculating the minimum number of charging stations N min This allows us to determine the minimum number of charging stations required to meet total charging demand. It avoids having too many charging stations in areas with low demand while ensuring sufficient service capacity in each area to meet user needs. Currently, the service capacity of charging stations can be set at 1350 vehicles per day for large, 600 vehicles per day for medium, and 300 vehicles per day for small charging stations. Therefore, the maximum service capacity of a charging station is 1350 vehicles, and the minimum service capacity is 300 vehicles per day. The minimum number of charging stations, N. min =[10000 / 300]=33.

[0064] Step S53: Determine the maximum number of charging stations based on the minimum service capacity of the actual charging stations within the grid and the total charging demand.

[0065] Specifically, by determining the maximum number of charging stations N max This avoids building too many charging stations in areas with low demand. The maximum number of charging stations limits the number of stations to prevent redundant coverage of existing stations and ensure that resources are not wasted due to excessive number of stations within the service area. Maximum number of charging stations N max =[10000 / 1350]=7.

[0066] Step S55: Determine the range from the minimum number of charging stations to the maximum number of charging stations as the range of the number of charging stations.

[0067] Specifically, by selecting different numbers of charging stations for cluster analysis between the minimum and maximum number of charging stations, the number of charging stations can be flexibly adjusted to adapt to varying demand changes. For example, in areas with high demand, more charging stations can be selected to improve service capacity, while in areas with low demand, the number of charging stations can be appropriately reduced to avoid over-construction. By using clustering algorithms (such as K-means), the clustering effect under different K values ​​can be analyzed based on the selected number of charging stations K, finding the relationship between charging demand and helping to determine which areas within the actual grid need more charging station construction and which areas can reduce or reallocate resources. By evaluating the quality of clustering (such as the silhouette coefficient or elbow rule), the quality of the clustering results can be ensured, thus providing a more scientific basis for charging station site selection. Finally, a set of candidate site combinations is obtained based on the clustering results.

[0068] This embodiment ensures coverage of every charging demand point by determining the minimum number of charging stations, avoiding resource waste. Then, it determines the maximum number of charging stations to prevent over-construction, ensuring that service capacity matches demand. Next, cluster analysis is used to select different numbers of charging stations, effectively optimizing charging station site selection, improving resource utilization, reducing user charging time, avoiding duplicate coverage and blank areas within the actual grid, and improving the efficiency of charging station usage.

[0069] Figure 4 A flowchart of the first step S7 provided in the embodiments of this application is provided. The process may include the following steps: Step S711: For each type of charging station in the range of charging station quantities, determine the distance from each charging demand point in the actual grid to the cluster center, and determine the sum of squared errors based on the distance.

[0070] Specifically, charging demand points are divided into several clusters, with each cluster corresponding to a charging station. The cluster center represents the location of a charging station. Calculating the distance from each charging demand point to the cluster center measures the relationship between the charging demand point and its nearest charging station. The cluster center is the "average location" of all charging demand points in that cluster, i.e., the mean of the coordinates of all charging demand points. For each number of charging stations (i.e., different cluster sizes K), the distance from each charging demand point within the actual grid to the cluster center is determined, and the sum of squared errors (SSE) is calculated. This step aims to evaluate the compactness of the clusters, i.e., the sum of distances between sample points within a cluster and the cluster center. The smaller the SSE, the better the clustering effect, the closer the points within the cluster are to the cluster center, and the more suitable the location of the charging station. The calculation method is as follows: Where K is the number of clusters, which is the number of charging stations; C z Let x be the set of the (z)th cluster (charging stations), containing all charging demand points within that cluster; x is the number of points belonging to cluster C. z A specific charging demand point; μ z Let z be the cluster center (charging station location) of the z-th cluster. This represents the Euclidean distance from the charging demand point to the cluster center.

[0071] Step S713: Plot the sum of squared errors corresponding to different numbers of charging stations into a relationship diagram, and determine the candidate station combination set from the relationship diagram.

[0072] Specifically, for different numbers of charging stations K (e.g., K=7, 8, 9, ..., 33), the corresponding sum of squared errors (SSE) is calculated. A graph is plotted with the number of charging stations K on the horizontal axis and the sum of squared errors (SSE) on the vertical axis. Observing the graph, the point where SSE decreases significantly is identified as the "elbow point." The elbow point is where the rate of SSE decrease slows down significantly. When the value of K is small, increasing the number of charging stations will significantly reduce SSE because more charging stations will more precisely match the demand points. However, as the value of K increases, the rate of SSE decrease slows down and eventually stabilizes. The K value corresponding to the elbow point is usually the optimal number of charging stations because it reduces SSE while avoiding redundancy caused by too many charging stations. For example, cluster analysis is performed from K=7 to K=33, calculating the SSE corresponding to each K value. In the graph, the SSE values ​​from K=7 to K=33 usually decrease rapidly, but as the value of K increases, the rate of SSE decrease gradually slows down. Find the elbow point, for example, between K=18 and K=23, where the decrease of SSE becomes gradual. This means that K=18 to K=23 is a suitable range for the number of charging stations, i.e., the candidate site combination set is K=18,19,20,…,23.

[0073] This embodiment calculates the distance from each charging demand point to the cluster center based on the number of charging stations, and evaluates the matching degree between charging demand points and charging stations using the sum of squared errors. A smaller sum of squared errors indicates a shorter distance between the charging demand point and the charging station, resulting in a higher matching degree. This optimizes charging station site selection and improves charging station coverage and utilization. Next, by plotting the relationship between the sum of squared errors and the number of charging stations, an appropriate number of charging stations is selected to avoid resource waste or insufficient coverage. With a reasonable layout, the distance to the charging station for users is shortened, charging waiting time is reduced, and overall charging efficiency and user experience are improved. Simultaneously, it also enables the scientific allocation of regional resources, ensuring a balanced distribution of charging stations across different areas and achieving efficient resource utilization.

[0074] Figure 5 A flowchart of the second step S7 provided in the embodiments of this application is provided. The process may include the following steps: Step S731: For each type of charging station in the range of charging station quantities, determine the first average distance from each charging demand point in the actual grid to the adjacent charging demand points in the same cluster.

[0075] Specifically, to assess the cluster density of each charging demand point, the aggregation of charging demand points within the cluster can be determined by calculating the first average distance a(x) from each charging demand point to other adjacent charging demand points within the same cluster. If the charging demand points within a cluster are close together, it indicates strong aggregation and high internal consistency. High cluster density means that the charging stations within this cluster can provide efficient service, reduce user charging wait times, and improve the utilization rate of the charging stations.

[0076] Step S733: Determine the second average distance from each charging demand point in the actual grid to the charging demand point in the nearest cluster.

[0077] Specifically, to assess the separation between each charging demand point and other clusters, the second average distance b(x) from each charging demand point to the nearest charging demand point within its cluster is calculated. This measures the distance between clusters and allows for the analysis of the independence of different clusters. A larger average distance between clusters indicates better separation, meaning higher "distinctiveness" between charging demand points. This allows charging stations to avoid covering demand points in other clusters, reducing resource overlap. Strong separation helps improve accuracy and efficiency, ensuring that the coverage areas of each charging station do not overlap excessively, thereby improving resource utilization.

[0078] Step S735: Determine the individual profile coefficient for each charging demand point based on the ratio between the first average distance and the second average distance, and determine the overall profile coefficient matching the number of each type of charging station based on the individual profile coefficient.

[0079] Specifically, the profile coefficient takes into account both the compactness within clusters and the separation between clusters.

[0080] Where S(x) is a single profile coefficient of charging demand point x, a(x) is the first average distance from charging demand point x to adjacent charging demand points in the same cluster, and b(x) is the second average distance from charging demand point x to the charging demand point in the nearest cluster.

[0081] When a(x) is small and b(x) is large, the value of S(x) is relatively large, indicating that the charging demand point x is closely related to its cluster and has good separation from other clusters, indicating high clustering quality.

[0082] Step S737: Filter the overall contour coefficients to obtain a set of candidate site combinations.

[0083] Specifically, after calculating the individual profile coefficient for each charging demand point, the next step is to calculate the average profile coefficient of all charging demand points to obtain the overall profile coefficient. This overall profile coefficient reflects the quality of the entire cluster and helps determine the clustering effect under the current number of charging stations (K). The overall profile coefficient will change when different numbers of charging stations K are selected. By filtering for K values ​​with higher overall profile coefficients, a better number and layout scheme of charging stations is selected to ensure that the location of charging stations is both reasonable and efficient. For example, cluster analysis is performed from K=7 to K=33, and the overall profile coefficient corresponding to each K value is calculated. After filtering, it is determined that the range between K=18 and K=23 is a suitable range for the number of charging stations, that is, the candidate site combination set is K=18,19,20,…,23.

[0084] This embodiment assesses cluster density by calculating the first average distance from each charging demand point to its nearest neighboring charging demand points within the same cluster, ensuring effective charging station coverage of the actual grid and reducing user waiting time. Secondly, calculating the second average distance from each charging demand point to the nearest charging demand point in its cluster helps assess inter-cluster separation, avoiding redundant coverage and improving site utilization. Furthermore, combining this with the calculation of the profile coefficient allows for a comprehensive evaluation of cluster quality, ensuring the rationality of the number and layout of charging stations and avoiding over- or under-construction. Finally, by filtering the overall profile coefficient, the optimal number and layout of charging stations are determined, thereby optimizing charging station configuration, improving charging station utilization, and reducing user charging time.

[0085] Figure 6 A flowchart illustrating the construction method of the objective function in the charging station site selection and capacity determination model provided in this application embodiment is provided. The process may include the following steps: Step S91: For any candidate site combination and its corresponding candidate site location, determine the target total construction cost corresponding to any candidate site combination.

[0086] Specifically, a comprehensive assessment of the construction costs, equipment costs, equipment maintenance costs, and electricity consumption costs for each candidate site is required. This involves collecting data on the construction costs (including land development and infrastructure construction costs), equipment purchase and installation costs, equipment maintenance costs, and electricity consumption costs during operation for each candidate site. By introducing weighting coefficients (such as γ, δ, and ε) to adjust the relative importance of different cost items, actual needs can be reflected more flexibly. Finally, this is combined with the decision variable x. j(Indicates whether to build a charging station at candidate site location j). The costs of all candidate site locations are weighted and summed to obtain the target total construction cost for any combination of candidate sites. This cost calculation not only provides basic data for subsequent optimization analysis, but also helps decision-makers conduct economic evaluations among multiple candidate schemes, thereby selecting the charging station layout scheme that meets charging demand while achieving the highest cost-effectiveness.

[0087] Step S93: Determine the coverage area that matches the candidate site location, and determine the target coverage rate corresponding to any combination of candidate sites based on the coverage area.

[0088] Specifically, the coverage area of ​​each candidate site is determined based on a preset service radius (e.g., 2.5 kilometers). This is typically achieved through buffer analysis in a Geographic Information System (GIS) tool, generating the coverage area for each candidate site. Subsequently, target charging demand points located within these coverage areas are selected. Based on this data, the target coverage rate is calculated, which is the ratio of the target charging demand points covered by all candidate site locations to the total charging demand within the target area. This ratio directly reflects the degree to which the current combination of candidate sites meets the charging demand of the entire area and is an important indicator for evaluating the quality of a charging station layout scheme. By maximizing the target coverage rate, it can be ensured that the layout of charging stations can efficiently serve as many electric vehicle users as possible, thereby optimizing the site selection and resource allocation of charging stations.

[0089] Step S95: Convert the target coverage rate into the target coverage loss cost using a preset penalty cost coefficient.

[0090] Specifically, the target coverage rate represents the proportion of the target charging demand points covered by each candidate site combination to the total charging demand. If the target coverage rate is lower than the expected value, it means that the coverage effect of the candidate site combination is not ideal, and users' charging needs cannot be fully met. To quantify this coverage insufficiency into a calculable cost, a penalty cost coefficient p is introduced, and it is transformed into the target coverage loss cost through the following formula: Target coverage loss cost = p × (1 - T) n The target coverage loss cost reflects the economic losses caused by the failure to effectively meet charging demand. This loss not only directly affects the utilization rate of charging stations, but may also lead to a decline in user experience, thereby bringing more operational pressure.

[0091] Step S97: The sum of the target construction cost and the target coverage loss cost is determined as the objective function.

[0092] Specifically, the objective function is the core of site selection optimization, integrating the total construction cost and the target coverage loss cost. min F = CO + p × (1 - T) nWhere CO represents the target total construction cost, which typically includes expenses for site construction, equipment procurement, installation, and commissioning. p×(1-T) n The objective function aims to minimize the total cost by covering the cost of insufficient coverage. In the optimization process, the goal of the objective function is to find the optimal charging station location and capacity scheme. This scheme should ensure that the construction cost of the charging stations and the penalty cost due to insufficient coverage are balanced. In other words, the optimization process aims to select a charging station layout that effectively meets user needs while reasonably controlling costs.

[0093] This embodiment ensures the economic feasibility of the charging station site selection and capacity allocation scheme by calculating the target total construction cost corresponding to the candidate site combination; by determining the coverage range and target coverage rate of the candidate site locations, it ensures that the charging stations can meet user needs, thereby shortening users' charging time and waiting time; then, by using a penalty cost coefficient, insufficient coverage is quantified into economic loss, prompting the optimization algorithm to improve the coverage rate; finally, by combining the target total construction cost and the target coverage loss cost, an objective function is constructed to find the optimal charging station site selection and capacity allocation scheme, which satisfies user needs while controlling costs.

[0094] Figure 7 The flowchart for step S91 provided in the embodiments of this application may include the following steps: Step S911: For any candidate site combination and its corresponding candidate site location, determine the construction cost, equipment cost, equipment maintenance cost, and power consumption cost matching each candidate site location.

[0095] Specifically, multiple cost factors are determined for each candidate site location within any candidate site combination. Construction cost. This includes land acquisition costs, infrastructure construction costs, etc. The level of construction cost is typically determined by the land's geographical location, land price, and the standards of infrastructure construction (such as grid connection, road construction, etc.). Different candidate sites may differ in these factors, thus affecting construction costs. Equipment costs. This refers to the purchase and installation costs of the charging equipment itself, including charging piles and power distribution equipment. Market prices and installation costs may vary depending on factors such as brand, technology, quantity, and installation environment. Equipment maintenance costs... This includes equipment maintenance, repair, and personnel management costs, which are closely related to the equipment's workload and maintenance schedule. Some equipment may require more maintenance and inspection, resulting in higher maintenance costs. Electricity consumption cost E j This refers to the costs associated with the electricity consumption during the operation of a charging station. Electricity costs depend on the station's electricity demand, local electricity prices, and the frequency of charging station usage.

[0096] Step S913: Based on the decision variable of whether to build a charging station at a candidate site location, the construction cost, equipment cost, equipment maintenance cost, and electricity consumption cost are weighted and summed to obtain the single total construction cost matching each candidate site location.

[0097] Specifically, the decision variable x is based on whether to select a charging station location for each candidate site. j The total construction cost CO for each candidate site is calculated by weighting and summing the various costs. Among them, x j γ is the decision variable, indicating whether to build a charging station at the candidate site location (1 indicates construction, 0 indicates no construction). γ, δ, and ε are weighting coefficients used to adjust the degree of influence of each cost factor on the total cost. Different weighting coefficients reflect the importance of different cost factors. For example, some projects may focus more on equipment costs than construction costs, or maintenance costs may be particularly important in certain regions.

[0098] Step S915: Determine the target total construction cost corresponding to any candidate site combination based on the total construction cost of all individual sites.

[0099] Specifically, the target total construction cost of the entire candidate site portfolio is obtained by weighted summing of the individual construction costs of all candidate sites: Where n represents any combination of candidate sites, i.e., the number of candidate sites, and CO represents the total cost of all candidate sites. Through this objective function, the entire optimization problem becomes a minimization problem, with the goal of selecting the optimal combination of site construction to minimize the total cost.

[0100] This embodiment determines the construction cost, equipment cost, equipment maintenance cost, and electricity consumption cost for each candidate site location. Then, it uses decision variables to determine whether to build a charging station at that candidate site location. By weighted summing of all costs, the total construction cost for each candidate site location is obtained. Finally, based on all individual total construction costs, the final target total construction cost is determined. The optimization goal is not only to select the lowest-cost site but also to consider site utilization and user demand, rationally configuring site layout to ensure that charging stations meet user needs while having high utilization and low operating costs.

[0101] Figure 8 The flowchart for step S93 provided in the embodiments of this application may include the following steps: Step S931: Determine the coverage area that matches the candidate site location, and filter the target charging demand points within the coverage area.

[0102] Specifically, based on actual needs or design standards, the coverage area R can be set to a fixed value, such as 2.5 kilometers. This value represents the maximum radius that can be covered from the candidate site location. The specific coverage area selection depends on various factors, such as: the driving range of electric vehicles is limited, so the coverage radius of the site needs to take into account the typical range of electric vehicles. In densely populated areas, the coverage area may need to be smaller to more effectively distribute charging stations; while in sparsely populated areas, the coverage area may be larger to ensure there are enough charging stations.

[0103] Next, using the defined coverage area R, target charging demand points within that coverage area are selected. Specifically, given any candidate site location... Charging demand points within the coverage area R of the candidate site location will be considered "target charging demand points". , Set D contains all charging demand points that meet the conditions.

[0104] Among them, x i Coordinates of the charging demand point; Let j be the location of the candidate site.

[0105] Step S933: The ratio between the target charging demand points and the total charging demand is determined as the target coverage rate corresponding to any candidate site combination.

[0106] Specifically, the target charging demand points obtained through screening The target coverage T corresponding to any combination of candidate sites can be calculated. n Target coverage rate represents the proportion of the target charging demand points covered by any combination of candidate sites out of the total charging demand points. The calculation formula is as follows: Where n is the number of any candidate site combination, i.e., the number of candidate sites; C is the total charging demand.

[0107] This embodiment determines the coverage area of ​​each candidate site location and filters out the target charging demand points within that coverage area. Then, it calculates the target coverage rate by proving the ratio of the target charging demand points covered by each candidate site location to the total demand points. This target coverage rate reflects the effectiveness of the site selection and helps assess whether the site can effectively meet user needs. A higher target coverage rate indicates that the site selection better serves users, thereby improving the utilization rate of charging stations and reducing users' charging wait times.

[0108] The specific implementation of this invention is described below using a specific application scenario. This embodiment uses real geographical information of a certain region as background and collects actual travel trajectory data of taxis in a certain city. A site selection analysis of charging stations is conducted for nearly 10,000 electric vehicle (EV) charging demand points in the region. Analysis based on SSE values ​​and the elbow method reveals that the profile coefficient is concentrated between 0.54 and 0.565, with a small difference, making it difficult to determine the optimal K value. As the K value increases, the rate of decrease in SSE tends to level off when the K value exceeds 17. Therefore, the service capacity of the charging stations is calculated, with the daily service capacity of large, medium, and small charging stations being 1350, 600, and 300 vehicles, respectively. Through analysis, it is considered that a more reasonable candidate site combination set with a K value between 18 and 23 is appropriate.

[0109] In ArcGIS 10.8, the total construction cost and coverage rate were calculated sequentially for K values ​​ranging from 18 to 23, based on a coverage area R of 2.5 km. Subsequently, taxi data, geographic information data, and candidate charging station data were imported into the ArcGIS platform for spatial analysis and visualization, providing basic data support for subsequent charging station site selection and layout.

[0110] Next, combining user demand points for each candidate site combination, Monte Carlo simulation was used to predict the user load demand of charging stations at different times. To comprehensively consider multiple constraints such as charging station construction cost, coverage, load demand, and user charging experience, this embodiment constructed a mixed-integer linear programming model and introduced multiple types of charging equipment (such as slow charging, fast charging, and super-fast charging). Specifically, the model uses the total construction cost and coverage rate of charging stations as objective functions, with constraints including charging station load, travel time, charging pile type selection, and the number of various types of charging piles. Finally, the CPLEX solver in MATLAB was used to optimize the charging station location and capacity model, determining the optimal capacity configuration scheme for each charging station. The result was 21 charging stations with a total construction cost of 1209.7 (K$) yuan and a coverage rate of 93.28%.

[0111] Accordingly, please refer to Figure 9 A block diagram of an electric vehicle charging station site selection and capacity determination device provided in this application embodiment, the device comprising: The geographic data acquisition unit 101 is used to acquire GPS data of the target area and generate a geographic data map of the target area based on the GPS data. The grid set determination unit 103 is used to perform multiple grid divisions of charging stations in the target area based on the geographic data map. For each grid division, the reasonableness index of the charging station grid set is calculated, and the actual grid set suitable for the target area is determined based on the calculated reasonableness index. The reasonableness index is determined based on the charging compensation relationship between each charging station grid in the charging station grid set. The charging station quantity determination unit 105 is used to traverse each actual grid in the actual grid set, and for any actual grid, identify the total charging demand of the actual grid, and determine the range of the number of charging stations based on the maximum and minimum service capabilities of the charging stations in the actual grid and the total charging demand. The candidate site determination unit 107 is used to determine the set of candidate site combinations corresponding to the actual grid based on the combination of different numbers of charging stations within the range of the number of charging stations; wherein, each candidate site combination represents the number of candidate sites. The site selection and capacity determination unit 109 is used to determine the target charging station site selection and capacity determination scheme based on a pre-set charging station site selection and capacity determination model for any candidate site combination in the candidate site combination set; wherein, the charging station site selection and capacity determination model is constructed according to the charging pile type, the number of different types of charging piles in each charging station and the coverage of the charging station.

[0112] In some alternative implementations, the mesh set determination unit 103 includes: Retrieve multiple pre-defined statistical time periods; For any statistical period and for any charging station grid in the charging station grid set, determine the first number of charging stations with charging compensation relationship in the charging station grid within the statistical period, and generate the charging compensation coefficient of the charging station grid based on the first number obtained in each statistical period. Calculate the average charging compensation coefficient of each charging station grid in the charging station grid set, and use the average value as the rationality index of the charging station grid set.

[0113] In some optional implementations, the charging station quantity determination unit 105 includes: The minimum number of charging stations is determined based on the maximum service capacity of the actual charging stations within the grid and the total charging demand. The maximum number of charging stations is determined based on the minimum service capacity of the actual charging stations within the grid and the total charging demand. The range from the minimum number of charging stations to the maximum number of charging stations is defined as the range of the number of charging stations.

[0114] In some optional implementations, the candidate site determination unit 107 includes: For each type of charging station within the range of charging station quantities, determine the distance from each charging demand point within the actual grid to the cluster center, and determine the sum of squared errors based on the distance; A relationship diagram is plotted based on the sum of squared errors corresponding to different numbers of charging stations, and a set of candidate station combinations is determined from the relationship diagram.

[0115] In some optional implementations, the candidate site determination unit 107 includes: For each type of charging station quantity within the range of charging station quantities, determine the first average distance from each charging demand point in the actual grid to the adjacent charging demand points in the same cluster. Determine the second average distance from each charging demand point within the actual grid to the nearest charging demand point in the cluster; Based on the ratio between the first average distance and the second average distance, a single profile coefficient is determined for each charging demand point, and an overall profile coefficient matching the number of each type of charging station is determined based on the single profile coefficient. The overall contour coefficients are filtered to obtain a set of candidate site combinations.

[0116] In some optional implementations, the objective function in the charging station site selection and sizing model is constructed as follows: For any combination of candidate sites and the corresponding locations of the candidate sites, determine the target total construction cost for any combination of candidate sites; Determine the coverage area that matches the candidate site locations, and determine the target coverage rate for any combination of candidate sites based on the coverage area; The target coverage rate is converted into the target coverage loss cost using a preset penalty cost coefficient; The objective function is defined by summing the total cost of target construction and the cost of target coverage loss.

[0117] In some alternative implementations, determining the target total construction cost corresponding to any candidate site combination includes: For any combination of candidate sites and the corresponding candidate site locations, determine the construction cost, equipment cost, equipment maintenance cost, and power consumption cost matching each candidate site location; Based on the decision variable of whether to build a charging station at a candidate site location, the construction cost, equipment cost, equipment maintenance cost, and electricity consumption cost are weighted and summed to obtain the single total construction cost matching each candidate site location. Based on the total construction cost of all individual sites, determine the target total construction cost for any combination of candidate sites.

[0118] In some optional implementations, determining the target coverage corresponding to any combination of candidate sites includes: Determine the coverage area that matches the candidate site location, and filter the target charging demand points within the coverage area; The ratio between the target charging demand points and the total charging demand is determined as the target coverage rate for any candidate site combination.

[0119] Further functional descriptions of the above modules and units are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0120] In this embodiment, the electric vehicle charging station site selection and capacity determination device is presented in the form of a functional unit. Here, a unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0121] Please see Figure 10 , Figure 10 This application provides a schematic diagram of the structure of a computer device, as shown in the embodiment of the present application. Figure 10 As shown, the computer device includes one or more processors 10, memory 20, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components communicate with each other via different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on external input / output devices (such as display devices coupled to the interfaces). In some alternative implementations, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 10 Take a processor 10 as an example.

[0122] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GDA), or any combination thereof.

[0123] The memory 20 stores instructions executable by at least one processor 10 to cause the at least one processor 10 to perform the method shown in the above embodiments.

[0124] The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the computer device. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0125] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0126] The computer device also includes a communication interface 30 for communicating with other devices or communication networks.

[0127] This application also provides a computer-readable storage medium. The methods described in this application can be implemented in hardware or firmware, or implemented as recordable on a storage medium, or implemented as computer code downloaded over a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and subsequently stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the methods shown in the above embodiments are implemented.

[0128] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this disclosure in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0129] For example, upon receiving a user's active request, a prompt message is sent to the user to explicitly inform them that the requested operation will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the software or hardware, such as the electronic device, application, server, or storage medium performing the operations of this disclosed technical solution, based on the prompt message.

[0130] As an optional but non-limiting implementation, in response to a user's active request, sending a prompt message to the user can be done via a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0131] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of this disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of this disclosure.

[0132] It is understood that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and related provisions.

[0133] It is understood that in the specific implementation of this application, data such as user information, location information, and navigation data are involved. When the above embodiments of this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0134] The apparatus and units described in the above embodiments can be implemented by a computer chip or physical entity, or by a product with a certain function. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or any combination of these devices.

[0135] For ease of description, the above devices are described separately by function as various units. Of course, in implementing this application, the functions of each unit can be implemented in one or more software and / or hardware.

[0136] Those skilled in the art will understand that embodiments of this application can be provided as methods, apparatus, or units. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0137] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatuses, and devices according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the process. 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.

[0138] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work 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 The function specified in one or more boxes.

[0139] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0140] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0141] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the apparatus embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0142] The foregoing is merely an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

[0143] Although embodiments of this application have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of this application, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for site selection and capacity determination of electric vehicle charging stations, characterized in that, The method includes: Obtain GPS data for the target area, and generate a geographic data map of the target area based on the GPS data; Based on the geographic data map, the charging stations in the target area are divided into grids multiple times. For each set of charging station grids obtained from the division, a reasonableness index of the charging station grid set is calculated. Based on the calculated reasonableness index, an actual grid set suitable for the target area is determined. The reasonableness index is determined based on the charging compensation relationship between each charging station grid in the charging station grid set. Traverse each actual grid in the actual grid set, and for any actual grid, identify the total charging demand of the actual grid. Determine the range of the number of charging stations based on the maximum and minimum service capabilities of the charging stations in the actual grid and the total charging demand. Based on the combinations of different numbers of charging stations within the range of the number of charging stations, a set of candidate site combinations corresponding to the actual grid is determined; wherein, each candidate site combination represents the number of candidate sites; For any candidate site combination in the candidate site combination set, a target charging station location and capacity determination scheme is determined based on a pre-set charging station location and capacity determination model; wherein, the charging station location and capacity determination model is constructed based on the charging pile type, the number of different types of charging piles in each charging station, and the coverage of the charging station.

2. The method according to claim 1, characterized in that, The rationality indicators for the statistical analysis of the charging station grid set include: Retrieve multiple pre-defined statistical time periods; For any statistical period and for any charging station grid in the charging station grid set, a first number of charging stations with charging compensation relationships in the charging station grid is determined within the statistical period, and a charging compensation coefficient of the charging station grid is generated based on each first number obtained in each statistical period. The average value of the charging compensation coefficient of each charging station grid in the charging station grid set is obtained, and the average value is used as the rationality index of the charging station grid set.

3. The method according to claim 1, characterized in that, The step of determining the range of the number of charging stations based on the maximum and minimum service capabilities of the charging stations within the actual grid and the total charging demand includes: The minimum number of charging stations is determined based on the maximum service capacity of the charging stations within the actual grid and the total charging demand. The maximum number of charging stations is determined based on the minimum service capacity of the charging stations within the actual grid and the total charging demand. The range from the minimum number of charging stations to the maximum number of charging stations is defined as the range of the number of charging stations.

4. The method according to claim 1, characterized in that, The process of determining the candidate site combination set corresponding to the actual grid based on combinations of different numbers of charging stations within the range of the number of charging stations includes: For each type of charging station within the range of charging station quantities, determine the distance from each charging demand point within the actual grid to the cluster center, and determine the sum of squared errors based on the distances; A relationship diagram is plotted showing the sum of squared errors corresponding to different numbers of charging stations, and the candidate station combination set is determined from the relationship diagram.

5. The method according to claim 1, characterized in that, The process of determining the candidate site combination set corresponding to the actual grid based on combinations of different numbers of charging stations within the range of the number of charging stations includes: For each type of charging station quantity within the range of charging station quantities, determine the first average distance from each charging demand point in the actual grid to the adjacent charging demand points in the same cluster. Determine the second average distance from each charging demand point within the actual grid to the charging demand point in the nearest cluster; Based on the ratio between the first average distance and the second average distance, a single profile coefficient is determined for each charging demand point, and an overall profile coefficient matching the number of each type of charging station is determined based on the single profile coefficient. The overall contour coefficients are filtered to obtain the candidate site combination set.

6. The method according to claim 1, characterized in that, The objective function in the charging station site selection and sizing model is constructed as follows: For any combination of candidate sites and the corresponding locations of the candidate sites, determine the target total construction cost corresponding to any combination of candidate sites; Determine the coverage area that matches the location of the candidate sites, and determine the target coverage rate corresponding to any combination of candidate sites based on the coverage area; The target coverage rate is converted into target coverage loss cost using a preset penalty cost coefficient; The objective function is defined by summing the total construction cost of the target and the loss cost of the target coverage.

7. The method according to claim 6, characterized in that, Determining the target total construction cost corresponding to any candidate site combination includes: For any combination of candidate sites and the corresponding candidate site locations, determine the construction cost, equipment cost, equipment maintenance cost, and power consumption cost matching each candidate site location; Based on the decision variable of whether to build a charging station at the candidate site location, the construction cost, the equipment cost, the equipment maintenance cost, and the electricity consumption cost are weighted and summed to obtain the single total construction cost matching each candidate site location; Based on the total construction cost of all the individual sites, determine the target total construction cost corresponding to any combination of candidate sites.

8. The method according to claim 6, characterized in that, Determining the target coverage rate corresponding to any candidate site combination includes: Determine the coverage area that matches the candidate site location, and filter the target charging demand points within the coverage area; The ratio between the target charging demand points and the total charging demand is determined as the target coverage rate corresponding to any candidate site combination.

9. A site selection and capacity determination device for electric vehicle charging stations, characterized in that, The device includes: A geographic data acquisition unit is used to acquire GPS data of a target area and generate a geographic data map of the target area based on the GPS data. The grid set determination unit is used to perform multiple grid divisions of charging stations within the target area based on the geographic data map, and to calculate the rationality index of the charging station grid set for each division, and to determine the actual grid set suitable for the target area based on the calculated rationality index; wherein, the rationality index is determined based on the charging compensation relationship between each charging station grid in the charging station grid set. The charging station quantity determination unit is used to traverse each actual grid in the actual grid set, and for any actual grid, identify the total charging demand of the actual grid, and determine the range of the number of charging stations based on the maximum and minimum service capabilities of the charging stations in the actual grid and the total charging demand. The candidate site determination unit is used to determine the set of candidate site combinations corresponding to the actual grid based on the combinations of different numbers of charging stations within the range of the number of charging stations; wherein, each candidate site combination represents the number of candidate sites; The site selection and capacity determination unit is used to determine the target charging station site selection and capacity determination scheme based on a pre-set charging station site selection and capacity determination model for any candidate site combination in the candidate site combination set; wherein, the charging station site selection and capacity determination model is constructed based on the charging pile type, the number of different types of charging piles in each charging station and the coverage of the charging station.

10. A computer device, characterized in that, include: The system includes a memory and a processor, which are interconnected. The memory stores computer instructions, and the processor executes the computer instructions to perform the electric vehicle charging station site selection and capacity determination method according to any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to execute the electric vehicle charging station site selection and capacity determination method according to any one of claims 1 to 8.

Images