An electric vehicle charging station site selection optimization method and system

Abstract

The present application relates to electric vehicle charging station planning technical field, specifically to a kind of electric vehicle charging station site selection optimization method and system, method includes: based on city traffic road network structure data, city interest point data and electric vehicle travel and charging demand data, obtain charging demand point set;Based on land use, traffic accessibility and power access condition, obtain candidate charging station set;Build the electric vehicle charging station site selection optimization model considering interruption risk disturbance;Based on the improved non-dominated sorting genetic algorithm, the electric vehicle charging station site selection optimization model is solved, obtains the optimal solution set of electric vehicle charging station phased site selection;Based on the optimal solution set of electric vehicle charging station phased site selection, electric vehicle charging station site selection is carried out.The present application faces interruption risk disturbance and uses phased dynamic evolution type electric vehicle charging station site selection, improves the service ability and reliability of charging network under complex operating environment.

Description

Technical Field

[0001] This invention relates to the field of electric vehicle charging station planning technology, specifically to a method and system for optimizing the site selection of electric vehicle charging stations. Background Technology

[0002] With the rapid development of the new energy vehicle industry and the continuous increase in the number of electric vehicles, the planning and construction of charging infrastructure has become a key support for promoting the widespread application of electric vehicles. The rational layout of charging stations is crucial for improving charging service efficiency, shortening user charging waiting time, and optimizing the overall operational efficiency of the charging network.

[0003] Current research on electric vehicle charging station site selection largely focuses on building site selection optimization models. These models comprehensively consider factors such as construction costs, demand coverage, and service capacity. They set optimization objectives such as minimizing construction costs or maximizing demand coverage, and use multi-objective optimization algorithms to solve for layout schemes. Some studies also incorporate user satisfaction indicators to evaluate service quality from dimensions such as distance to the station, waiting time, and charging costs, thereby enhancing the rationality of planning.

[0004] However, in practical applications, the construction of charging infrastructure exhibits distinct phased characteristics. The number of charging stations needs to gradually increase with the growth in demand for electric vehicles, and during operation, there may be risks of service interruptions caused by equipment failures, power supply fluctuations, and maintenance, affecting the overall service capacity of the charging network. Existing research, when balancing construction costs and demand coverage, has not reasonably incorporated interruption risk factors and the phased construction process into a unified optimization model, thus limiting the reliability and applicability of site selection results. Summary of the Invention

[0005] The purpose of this invention is to provide a method and system for optimizing the site selection of electric vehicle charging stations in order to solve at least one of the above-mentioned technical problems.

[0006] The present invention achieves the above objectives through the following technical solutions: A method for optimizing the location of electric vehicle charging stations includes the following steps: Based on urban traffic network structure data, urban points of interest data, and electric vehicle travel and charging demand data, a set of charging demand points is obtained; based on land use, traffic accessibility, and power access conditions, a set of candidate charging stations is obtained. Based on the set of charging demand points and the set of candidate charging stations, an electric vehicle charging station site selection optimization model considering the risk of interruption is constructed. An improved non-dominated sorting genetic algorithm is used to solve the electric vehicle charging station site selection optimization model to obtain the optimal solution set for the staged site selection of electric vehicle charging stations. Electric vehicle charging station site selection is based on the optimal solution set of phased site selection.

[0007] Furthermore, the process of obtaining the set of charging demand points is as follows: The city’s functional areas are identified by urban point of interest data. These functional areas include: residential areas, commercial areas, industrial areas, public service areas, and leisure areas. Based on the urban point of interest data in various functional areas, and combined with electric vehicle travel and charging demand data, the kernel density estimation method is used to obtain the distribution density characteristics of electric vehicles. Based on urban traffic network structure data, network analysis method is used to calculate the network topology characteristic indicators of each functional area; Using the distribution density characteristics of electric vehicles in each functional area as the core feature vector and the network topology feature index as the spatial weight coefficient, a weighted clustering analysis using a clustering algorithm is employed to obtain the electric vehicle charging demand points.

[0008] Furthermore, the process of obtaining the candidate charging station set is as follows: The constraints are land use compliance and power access capacity; Based on network analysis of urban traffic network structure data, the traffic accessibility index of candidate locations is calculated. The candidate locations are scored and sorted, and the top m locations are selected as candidate charging stations.

[0009] Furthermore, the electric vehicle charging station site selection optimization model includes: , , , in, This indicates the total cost of building a charging station. ; This represents the total construction cost of candidate charging station j; Let j represent the location decision variables for candidate charging station j. ; This represents the set of candidate charging stations; This indicates the number of uncovered demand points. ; This indicates whether requirement point i is covered. ; Represents the set of charging demand points; Indicates user time satisfaction. ; This represents the charging demand at demand point i. Indicates whether demand point i is assigned to candidate charging station j at level r; This represents the probability that the r-th level charging station is in a serviceable state; Indicates the time satisfaction of a single user; R represents the actual response time when demand point i is allocated to candidate charging station j at level r; R represents the system demand coverage. Meanwhile, the electric vehicle charging station site selection optimization model satisfies the following constraints: , , , , in, Represents the reachability parameter. , This represents the distance between demand point i and candidate charging station j. This indicates the maximum service distance that the user can accept.

[0010] Furthermore, the probability that the r-th level charging station is in a serviceable state is calculated using the following formula. : Where q represents the probability of an interruption at the charging station; Calculated using the following formula : in, This represents the satisfaction decay coefficient. This indicates the maximum acceptable response time threshold for the user; The actual response time for demand point i to be allocated to candidate charging station j at level r is calculated using the following formula. : in, This represents the distance between demand point i and candidate charging station j; This indicates the average speed of the vehicle. Let represent the average queuing time of candidate charging station j at level r, calculated using a queuing theory model; This indicates the processing time before charging begins after the vehicle arrives at candidate charging station j.

[0011] Furthermore, an improved non-dominated sorting genetic algorithm is used to solve the electric vehicle charging station site selection optimization model, including: Normalize each objective function: ; Scalar functions are constructed based on the objective functions obtained from normalization: ; in, Represents the target weight vector. ; The Pareto optimal solution set for charging station site selection is obtained by solving the scalarization function.

[0012] An electric vehicle charging station site selection optimization system includes: The acquisition module is used to acquire a set of charging demand points based on urban traffic network structure data, urban point of interest data, and electric vehicle travel and charging demand data; and to acquire a set of candidate charging stations based on land use, traffic accessibility, and power access conditions. The model building module is used to construct an electric vehicle charging station location optimization model that takes into account the interruption risk disturbance based on the set of charging demand points and the set of candidate charging stations. The model solving module is used to solve the electric vehicle charging station site selection optimization model based on the improved non-dominated sorting genetic algorithm, and obtain the optimal solution set for the staged site selection of electric vehicle charging stations; The site selection module is used to select the location of electric vehicle charging stations based on the optimal solution set of the phased site selection of electric vehicle charging stations.

[0013] Furthermore, the electric vehicle charging station site selection optimization model includes: , , , in, This indicates the total cost of building a charging station. ; This represents the total construction cost of candidate charging station j; Let j represent the location decision variables for candidate charging station j. ; This represents the set of candidate charging stations; This indicates the number of uncovered demand points. ; This indicates whether requirement point i is covered. ; Represents the set of charging demand points; Indicates user time satisfaction. ; This represents the charging demand at demand point i. Indicates whether demand point i is assigned to candidate charging station j at level r; This represents the probability that the r-th level charging station is in a serviceable state; Indicates the time satisfaction of a single user; R represents the actual response time when demand point i is allocated to candidate charging station j at level r; R represents the system demand coverage. Meanwhile, the electric vehicle charging station site selection optimization model satisfies the following constraints: , , , , in, Represents the reachability parameter. , This represents the distance between demand point i and candidate charging station j. This indicates the maximum service distance that the user can accept.

[0014] Furthermore, the probability that the r-th level charging station is in a serviceable state is calculated using the following formula. : Where q represents the probability of an interruption at the charging station; Calculated using the following formula : , in, This represents the satisfaction decay coefficient. This indicates the maximum acceptable response time threshold for the user; The actual response time for demand point i to be allocated to candidate charging station j at level r is calculated using the following formula. : in, This represents the distance between demand point i and candidate charging station j; This indicates the average speed of the vehicle. Let represent the average queuing time of candidate charging station j at level r, calculated using a queuing theory model; This indicates the processing time before charging begins after the vehicle arrives at candidate charging station j.

[0015] A computer-readable storage medium storing a computer program that, when executed by a processor, implements the electric vehicle charging station site optimization method as described above.

[0016] The beneficial effects of this invention are as follows: This invention employs a meticulously constructed site selection optimization model encompassing multiple dimensions, including construction cost, demand coverage, and user satisfaction. It incorporates the risk of charging station outages and fully considers the complex and ever-changing uncertainties of the actual operating environment, resulting in charging station site selection outcomes that better align with real-world needs and possess higher reliability and practicality. Furthermore, this invention adopts a phased, dynamic evolutionary construction strategy, enabling rational planning of the charging network construction based on the development status at different stages. This ensures a smooth and orderly gradual expansion of the charging network from its initial stage to maturity, effectively avoiding resource waste and over-investment. In addition, this invention utilizes an improved non-dominated sorting genetic algorithm to solve the model, significantly improving the optimization efficiency of the site selection scheme. It can obtain high-quality site selection schemes in a short time while enhancing the stability of the schemes, providing a solid guarantee for the rational layout and efficient operation of electric vehicle charging stations. Attached Figure Description

[0017] Figure 1 This is a flowchart of an electric vehicle charging station site selection optimization method according to one embodiment of the present invention; Figure 2 Flowchart of a phased site selection optimization method for electric vehicle charging stations according to another embodiment of the present invention; Figure 3 This is a trend curve of the multi-strategy site selection coverage rate as a function of construction scale, representing one embodiment of the present invention. Figure 4 This represents the set of optimal solutions for city A. Figure 5 This is a schematic diagram of the structure of an electric vehicle charging station site selection optimization system according to one embodiment of the present invention. Detailed Implementation

[0018] The invention will now be discussed with reference to exemplary embodiments. It should be understood that the described embodiments are merely intended to enable those skilled in the art to better understand and thus implement the invention, and are not intended to imply any limitation on the scope of the invention.

[0019] As used herein, the term "comprising" and its variations are to be interpreted as open-ended terms meaning "including but not limited to". The term "based on" is to be interpreted as "at least partially based on". The terms "one embodiment" and "an embodiment" are to be interpreted as "at least one embodiment".

[0020] Example 1 Figure 1 This is a flowchart illustrating an electric vehicle charging station site selection optimization method according to one embodiment of the present invention. Figure 1 As shown, according to one embodiment of the present invention, a method for optimizing the location of electric vehicle charging stations includes the following steps: Step S102: Based on urban traffic network structure data, urban points of interest data, and electric vehicle travel and charging demand data, obtain a set of charging demand points; based on land use, traffic accessibility, and power access conditions, obtain a set of candidate charging stations. Step S104: Based on the set of charging demand points and the set of candidate charging stations, construct an electric vehicle charging station location optimization model that considers the disturbance of interruption risk. Step S106: Solve the electric vehicle charging station site selection optimization model based on the improved non-dominated sorting genetic algorithm to obtain the optimal solution set for the phased site selection of electric vehicle charging stations; Step S108: Select the location of electric vehicle charging stations based on the optimal solution set of phased site selection.

[0021] This embodiment proposes a phased, dynamically evolving electric vehicle charging station site selection optimization method oriented towards interruption risk disturbances. This method first obtains a set of charging demand points based on urban traffic network structure data, urban point-of-interest data, and electric vehicle travel and charging demand data through spatial analysis and cluster analysis. Simultaneously, it filters and obtains a set of candidate charging stations based on land use, traffic accessibility, and power grid connection conditions. Based on this, an electric vehicle charging station site selection optimization model considering interruption risk disturbances is constructed. This model comprehensively covers charging station construction costs, demand coverage, user satisfaction, and interruption risk disturbance factors, and introduces a phased construction strategy to achieve dynamic evolutionary layout planning of the charging network. The construction cost model includes land costs, construction costs, operation and maintenance costs, and equipment depreciation costs; the multi-objective optimization model aims to minimize construction costs, minimize the number of uncovered demand points, and maximize user time satisfaction; the phased construction strategy includes single-point construction strategies, quantitative construction strategies, and dynamic adjustment strategies to adapt to the gradual expansion of the charging network from its initial to mature stages. Finally, an improved non-dominated sorting genetic algorithm is used to solve the model, obtain the Pareto optimal solution set for the phased site selection of electric vehicle charging stations, and determine the final charging station layout scheme accordingly.

[0022] This invention can simultaneously consider construction cost control, demand coverage balance, user service experience and operational reliability during the site selection process of charging stations, effectively improving the service capability and system stability of charging networks in complex operating environments, and realizing the optimized configuration of electric vehicle charging infrastructure.

[0023] According to one embodiment of the present invention, the process of obtaining the charging demand point set in step S102 is as follows: The city’s functional areas are identified by urban point of interest data. These functional areas include: residential areas, commercial areas, industrial areas, public service areas, and leisure areas. Based on the urban point of interest data in various functional areas, and combined with electric vehicle travel and charging demand data, the kernel density estimation method is used to obtain the distribution density characteristics of electric vehicles. Based on urban traffic network structure data, network analysis method is used to calculate the network topology characteristic indicators of each functional area; Using the distribution density characteristics of electric vehicles in each functional area as the core feature vector and the network topology feature index as the spatial weight coefficient, a weighted clustering analysis using a clustering algorithm is employed to obtain the electric vehicle charging demand points.

[0024] The process of obtaining the candidate charging station set is as follows: The constraints are land use compliance and power access capacity; Based on network analysis of urban traffic network structure data, the traffic accessibility index of candidate locations is calculated. The candidate locations are scored and sorted, and the top m locations are selected as candidate charging stations.

[0025] In this embodiment, the acquisition of the charging demand point set and the acquisition of the candidate charging station set are further defined. Urban functional areas, including residential areas, commercial areas, industrial areas, public service areas, and leisure areas, are identified through urban point of interest data. Then, for urban point of interest data within each functional area, combined with electric vehicle travel and charging demand data, a kernel density estimation method is used to obtain the electric vehicle distribution density characteristics. Simultaneously, based on urban traffic network structure data, network analysis is used to calculate the network topology characteristic indicators of each functional area. Finally, using the electric vehicle distribution density characteristics within each functional area as the core feature vector and the network topology characteristic indicators as spatial weight coefficients, a weighted clustering analysis is performed using a clustering algorithm to obtain the electric vehicle charging demand points. With land use compliance and power access capacity as constraints, the traffic accessibility index of candidate locations is calculated using network analysis based on urban traffic network structure data. The candidate locations are then comprehensively scored and ranked, and the top m optimal locations are selected as the candidate charging station set.

[0026] This invention accurately identifies charging demand points by integrating kernel density estimation, network analysis, and weighted clustering methods, and combines multiple constraints and traffic accessibility assessment to screen candidate charging stations, effectively improving the accuracy of charging demand prediction and the feasibility of site selection schemes, and laying a data foundation for subsequent phased dynamic site selection optimization.

[0027] According to one embodiment of the present invention, the electric vehicle charging station site selection optimization model includes: , , , in, This indicates the total cost of building a charging station. ; This represents the total construction cost of candidate charging station j; Let j represent the location decision variables for candidate charging station j. ; This represents the set of candidate charging stations; This indicates the number of uncovered demand points. ; This indicates whether requirement point i is covered. ; Represents the set of charging demand points; Indicates user time satisfaction. ; This represents the charging demand at demand point i. Indicates whether demand point i is assigned to candidate charging station j at level r; This represents the probability that the r-th level charging station is in a serviceable state; Indicates the time satisfaction of a single user; R represents the actual response time when demand point i is allocated to candidate charging station j at level r; R represents the system demand coverage. Meanwhile, the electric vehicle charging station site selection optimization model satisfies the following constraints: , , , , in, Represents the reachability parameter. , This represents the distance between demand point i and candidate charging station j. This indicates the maximum service distance that the user can accept.

[0028] The probability that a charging station at level r is in a serviceable state is calculated using the following formula. : Where q represents the probability of an interruption at the charging station; Calculated using the following formula : in, This represents the satisfaction decay coefficient. This indicates the maximum acceptable response time threshold for the user; The actual response time for demand point i to be allocated to candidate charging station j at level r is calculated using the following formula. : in, This represents the distance between demand point i and candidate charging station j; This indicates the average speed of the vehicle. Let represent the average queuing time of candidate charging station j at level r, calculated using a queuing theory model; This indicates the processing time before charging begins after the vehicle arrives at candidate charging station j.

[0029] In this embodiment, the electric vehicle charging station site selection optimization model aims to minimize the total construction cost of charging stations, minimize the number of uncovered demand points, and maximize user time satisfaction. The total construction cost is determined by the construction cost of each candidate charging station and site selection decision variables. The number of uncovered demand points is determined by the coverage status of each demand point. User time satisfaction is determined by the charging demand at each demand point, hierarchical allocation decision variables, the probability of charging station availability, and the actual response time. The model also satisfies demand point coverage constraints, hierarchical allocation uniqueness constraints, allocation and construction status consistency constraints, and accessibility constraints. The model calculates the probability of charging station availability at each level using the interruption probability, constructs a user time satisfaction function by comprehensively considering the satisfaction decay coefficient and the maximum response time threshold, and calculates the actual response time based on the distance between the demand point and the candidate station, the average vehicle speed, queuing time, and pre-charging processing time. This achieves comprehensive optimization of charging station construction costs, demand coverage levels, user service experience, and interruption risk disturbance factors.

[0030] This invention constructs a multi-objective optimization model with the goals of minimizing construction costs, minimizing the number of uncovered demand points, and maximizing user time satisfaction. It also introduces an interruption risk disturbance mechanism and a hierarchical service allocation strategy to achieve a comprehensive balance between construction economy, demand coverage balance, user service experience, and operational reliability in the charging station site selection scheme. This significantly improves the service capability and system stability of the charging network in complex operating environments.

[0031] According to one embodiment of the present invention, a solution is provided for an electric vehicle charging station site selection optimization model based on an improved non-dominated sorting genetic algorithm, including: Normalize each objective function: ; Scalar functions are constructed based on the objective functions obtained from normalization: ; The Pareto optimal solution set for charging station site selection is obtained by solving the scalarization function.

[0032] In this embodiment, an improved non-dominated sorting genetic algorithm is used to solve the electric vehicle charging station site selection optimization model. First, the objective functions are normalized to eliminate dimensional differences. Then, a scalarization function is constructed based on the normalized objective functions. By setting the objective weight vector, the multi-objective optimization problem is transformed into a single-objective optimization problem for comprehensive evaluation. Finally, the scalarization function is solved to obtain the Pareto optimal solution set for charging station site selection, thereby determining the optimal charging station layout scheme that takes into account construction costs, demand coverage, and user satisfaction.

[0033] This invention transforms a multi-objective optimization problem into a solvable single-objective problem through normalization and scalarization function construction. Combined with an improved non-dominated sorting genetic algorithm, it effectively obtains the Pareto optimal solution set, realizing efficient optimization and scientific decision-making for charging station site selection in multi-objective trade-offs.

[0034] Example 2 Figure 2 This is a flowchart illustrating a phased site selection optimization method for electric vehicle charging stations, representing another embodiment of the present invention. Figure 2 As shown, according to one embodiment of the present invention, considering the risk of interruption and disturbance factors, a phased dynamic evolution of electric vehicle charging station construction is carried out in city A. The phased site selection optimization method for electric vehicle charging stations of the present invention includes the following steps: Step S201: Obtain the electric vehicle charging demand points and candidate charging stations, and calculate the distance between them; specifically, Step 1: Obtain the set N of charging demand points; Based on urban traffic network structure data, urban points of interest data, and electric vehicle travel and charging demand data for city A, a set N of charging demand points is determined through spatial analysis and cluster analysis; where N = { N1, N2, ..., N...} i ,...,N n}, N i Let i represent the charging demand point, and n represent the number of demand points. First, functional areas of city A are identified using Point of Interest (POI) data. These areas include residential areas, commercial areas, industrial areas, public service areas, and leisure areas. For each functional area, POI data is combined with electric vehicle travel and charging demand data to obtain electric vehicle distribution density characteristics using kernel density estimation. Simultaneously, based on urban traffic network structure data, network analysis is used to calculate network topology characteristic indicators for each functional area, including key intersection identification (based on shortest path frequency) and average road network density.

[0035] Then, using the electric vehicle distribution density characteristics within each functional area as the core feature vector and network topology feature indicators as spatial weight coefficients, a weighted clustering analysis was performed using the K-means++ clustering algorithm. During the clustering process, the spatial coordinates of electric vehicle travel and charging demand data were used as input, and the cluster center positions were adjusted based on the weights of the network topology feature indicators. The cluster centers obtained from the clustering were then used as the electric vehicle charging demand points.

[0036] Based on the above cluster analysis, we obtain the set N of charging demand points, and the number of charging demand points in city A is n = 82.

[0037] Step 2: Obtain the candidate charging station set Q; Based on the land use, transportation accessibility, and power grid connection conditions of city A, an evaluation index system for candidate charging stations is constructed to screen and determine the candidate charging station set Q; where Q = { Q1, Q2, ..., Q...} j ,..., Q m}, where Q j Let j represent candidate charging station and m represent the number of candidate charging stations.

[0038] Specifically, a three-tiered evaluation index system is established: the first tier consists of binding indicators, including land use compliance (whether it is located on land types permitted for charging facility construction) and power grid access capacity (whether the remaining available capacity of the surrounding power grid meets the fast-charging demand); the second tier consists of optimization indicators, using network analysis based on urban traffic network structure data to calculate the traffic accessibility index of candidate locations; the third tier is a comprehensive decision-making layer, employing the AHP-TOPSIS multi-criteria decision-making method to score and rank candidate locations. The top m ranked locations are selected as candidate charging stations; in this embodiment, m = 30.

[0039] Step 3: Calculate the distance d between the charging demand point and the candidate charging station. ij ; Based on the urban traffic network structure data of city A, Dijkstra's shortest path algorithm is used to calculate the shortest path distance between charging demand point i and candidate charging station j, denoted as d. ij . d ij This will serve as the basis for subsequent charging station site selection optimization.

[0040] Step S202: Construct a charging station construction cost model; After obtaining the demand point set N and the candidate charging station set Q, a charging station construction cost model is constructed to quantify the full life cycle construction cost of each candidate charging station, providing a cost objective function basis for subsequent multi-objective optimization.

[0041] Step 1: Determine the land cost of candidate charging stations ; in, This represents the land cost of candidate charging station j; The area occupied by candidate charging station j (in square meters) is determined by the number of charging piles and the internal layout specifications. The unit land price (in ten thousand yuan / square meter) represents the location of candidate charging station j, which is determined based on the land grade classification and benchmark land price data of city A. Step 2: Determine the construction cost of each candidate charging station. ; in, This represents the construction cost of candidate charging station j; The number of charging piles configured in candidate charging station j is a decision variable determined by subsequent optimization. This represents the construction cost of a single charging pile at candidate charging station j. The cost of charging station infrastructure construction is determined based on the site's construction conditions, thus comprehensively reflecting the investment in charging station construction. This represents the infrastructure construction cost of candidate charging station j, which is determined based on the site construction conditions to comprehensively reflect the investment in charging station construction; Step 3: Determine the operation and maintenance costs of candidate charging stations. ; in, This represents the operation and maintenance cost of candidate charging station j; This represents the ratio of operation and maintenance costs; This represents the construction cost of candidate charging station j; Step 4: Determine the equipment depreciation cost of candidate charging stations. ; in, This represents the equipment depreciation cost of candidate charging station j; Indicates the equipment value loss coefficient; The coefficient of variation of loss is represented by t; t represents the time parameter. This represents the construction cost of candidate charging station j; Step 5: Determine the total construction cost of each candidate charging station. ; in, This represents the total construction cost of candidate charging station j. The construction cost of a single charging pile in city A. = 100,000 yuan, infrastructure construction costs = 800,000 yuan, operating and maintenance cost ratio coefficient = 0.15, Equipment Value Loss Coefficient =0.1.

[0042] Step 6: Construct a charging station construction cost model ; in, This indicates the total cost of building a charging station; This represents the total construction cost of candidate charging station j; Let j represent the location decision variables for candidate charging station j. When candidate charging station j is selected for construction, = 1, otherwise = 0; Q represents the set of candidate charging stations.

[0043] Step S203: Construct a demand coverage model; in, Indicates the number of uncovered demand points; This indicates whether requirement point i is covered. When demand point i is covered by at least one existing charging station, =1, otherwise = 0.

[0044] Introducing reachability parameters , in, This represents the distance between demand point i and candidate charging station j. This indicates the maximum acceptable service distance for the user. In this embodiment, = 5km.

[0045] Satisfy the requirement point coverage constraint, that is: Only if at least one distance constraint is satisfied ( And the selected candidate charging stations ( Only when (=1) can demand point i be considered covered. =1).

[0046] System requirements coverage It can be represented as: Where n represents the number of charging points; N represents the set of charging points. This indicates whether requirement point i is covered.

[0047] Step S204: Introduce interruption risk disturbance factors and charging station non-service penalty costs to construct the total system cost function; Let q be the probability of a charging station experiencing an outage. When multiple charging stations provide services to the demand points according to priority, the probability that the r-th level charging station is in a serviceable state is: in, This represents the probability that the r-th level charging station is in a serviceable state; This indicates the probability of a charging station outage; r represents the service level number. After considering the disturbance caused by charging station outages, and in order to comprehensively reflect the construction costs of charging stations, the costs of user non-service penalties, and vehicle operating costs, this invention further constructs a total system cost function. System total cost function It is not used as an independent optimization objective, but as a secondary screening index for the Pareto optimal solution set, used to comprehensively evaluate the overall operating cost of candidate solutions under the condition of interruption risk disturbance.

[0048] in, Q represents the total system cost; Q represents the set of candidate charging stations. This represents the total construction cost of candidate charging station j; Let N represent the location decision variables for candidate charging station j; N represents the set of charging demand points; and R represents the system demand coverage rate. This represents the penalty cost coefficient when charging demand is not met. As an adjustable parameter, its value can be set according to the service level requirements during the planning period. This represents the charging demand at demand point i. This indicates whether demand point i is assigned to candidate charging station j at level r. ; This represents the probability that the r-th level charging station is in a serviceable state; This represents the cost coefficient per unit distance traveled. This represents the vehicle arrival rate at demand point i. This represents the distance between demand point i and candidate charging station j; Vehicle arrival rate at demand point i It is calculated using the following formula: in, Indicate demand points Vehicle arrival rate, This indicates the overall vehicle arrival rate of the system; Indicates demand point i The charging demand, This represents the total charging demand at all points of demand. This represents the charging demand at candidate charging station k. The above formula represents the overall vehicle arrival rate of the system. The demand is allocated according to the proportion of each demand point to the total charging demand, thus obtaining the demand points. Vehicle arrival rate and satisfy .

[0049] The following constraints must be met: Step S205: Construct a multi-strategy location selection model; under dynamic strategy adjustment, based on priority indicators... Establish rules for selecting new charging stations in each phase, and determine the charging stations to be built in each phase under the constraint of the number of stations to be built in each phase.

[0050] The planning period is defined as having T construction phases, and the construction decision variables added in phase t1 are defined. , Indicates whether candidate charging station j is in the first position. New construction phases; define cumulative construction state variables. , Indicates up to the Whether candidate charging station j has been built by the end of the phase, then... No. Number of newly built charging stations in the phase for: The total number of buildings to be constructed during the planning period, K, is: To the At the end of the phase, the coverage status of demand point i is denoted as Its satisfaction To reflect the contribution of newly added candidate sites to the coverage of remaining demand, candidate charging station j is defined as the one at the 1st rank. Phase priority indicators for in, This represents the charging demand at demand point i. The larger the value, the more unmet needs that candidate charging station j can cover at the current stage, and therefore the higher its priority for new construction.

[0051] In the phased construction process of charging stations, this study designed three site selection strategies for comparative analysis regarding the candidate site selection mechanism: (1) Single-point construction strategy, where one charging station is fixed to be built in each phase, i.e. =1; (2) Quantitative construction strategy, fixed construction at each stage One charging station, namely ; (3) In the dynamic adjustment strategy, the first is a preset constant; Number of newly built charging stations in the phase Priority indicators are dynamically determined based on the remaining uncovered needs from the previous phase. The process of selecting new sites during the actual participation phase is defined as follows: New construction decision variables for each stage , ,in, Indicates candidate charging stations In the New construction in phases, This indicates that no new construction will be carried out.

[0052] Then the first The selection of new sites for each phase must meet the following rules: st , .

[0053] The above constraint means that: in the first In this phase, selection will be made from candidate charging stations that have not yet been built. One new construction site will be added, and priority indicators will be selected first. Larger candidate charging stations.

[0054] To evaluate the coverage effectiveness of each strategy, a simulation experiment was conducted using City A as the application scenario to compare and analyze the changing patterns of demand coverage under different construction scales. Figure 3 This is a trend curve of multi-strategy site selection coverage as a function of construction scale, representing one embodiment of the present invention. Figure 3As shown in the experimental results, the dynamic adjustment strategy exhibits a significant coverage efficiency advantage under the same construction scale because it prioritizes coverage of areas with high unmet demand. As the number of sites increases from 0 to 6, the coverage rates of all three strategies show a monotonically increasing trend, and the dynamic adjustment strategy consistently outperforms both the single-site construction strategy and the quantitative construction strategy. This result verifies that under limited construction budget constraints, the dynamic adjustment strategy can effectively improve the spatial coverage efficiency and demand response capability of the charging network.

[0055] For city A, the number of construction phases during the planning period is taken as T=3, and the total number of planned charging stations is taken as K=15.

[0056] Step S206: Construct a user time satisfaction model.

[0057] To quantify the impact of vehicle waiting time on the user charging experience, the actual response time of demand point i being assigned to candidate charging station j at level r is defined. for in, This represents the actual response time when demand point i is assigned to candidate charging station j at level r; This represents the distance between demand point i and candidate charging station j; This indicates the average speed of the vehicle. Let represent the average queuing time of candidate charging station j at level r, calculated using a queuing theory model; This indicates the processing time before charging begins after the vehicle arrives at candidate charging station j.

[0058] To describe the queuing service process of candidate charging stations, the effective arrival rate of candidate charging station j at level r is defined. for: in, This represents the vehicle arrival rate at demand point i. Indicates whether demand point i is assigned to candidate charging station j at level r; Assume the average service rate of a single charging pile is Then the system service strength is in, This indicates the service strength of candidate charging station j at level r; This indicates the number of charging piles configured in candidate charging station j.

[0059] The corresponding system idle probability is: in, This represents the system idle probability that candidate charging station j is located at the r-th level; =1,2,..., ;( )! represents factorial; This indicates the number of charging piles configured in candidate charging station j; This indicates the service strength of candidate charging station j at level r; This represents the average queuing time of candidate charging station j at level r. for: Constructing a user time satisfaction function in, This represents the satisfaction decay coefficient. This indicates the maximum acceptable response time threshold for the user.

[0060] when When the function value is close to 1, it indicates high user satisfaction; when... When the response time increases, the function value gradually decreases, thus reflecting the adverse impact of increased waiting time on user experience.

[0061] In this embodiment, v = 30km / h can be taken as the average operating speed on urban roads, and the settings can be adjusted according to the configuration of the charging station equipment. and The value of .

[0062] Figure 4 This shows the curves of the user time satisfaction function under different parameter conditions. For example... Figure 4 As shown in the curve, user satisfaction remains high when vehicle response time is short; however, user satisfaction declines significantly as waiting time increases. This satisfaction function quantitatively describes the impact of waiting time on user experience and incorporates user perception factors into the charging station site selection optimization model. Compared to traditional site selection models that only consider cost and coverage, the method of this invention can take user experience into account during the optimization process, thereby improving the overall service quality of the charging network.

[0063] Step S207: Construct a multi-objective site selection model, and under the constraints of the phased construction strategy determined in step S205, solve the multi-objective site selection model based on an improved non-dominated sorting genetic algorithm to obtain the Pareto optimal solution set for the phased site selection of electric vehicle charging stations; then combine this with the system total cost function constructed in step S204. A second selection process is performed on the Pareto optimal solution set. The final phased site selection plan for electric vehicle charging stations will be determined.

[0064] Multi-objective location selection models include: Objective 1: Minimize the total cost of building charging stations. Objective 2: Minimize the number of uncovered requirements. Objective 3: Maximize overall user time satisfaction : The following constraints must be met: in, This indicates the total cost of building a charging station; This represents the total construction cost of candidate charging station j; Let j represent the location decision variables for candidate charging station j. When candidate charging station j is selected for construction, = 1, otherwise = 0; Q represents the set of candidate charging stations; R is the system demand coverage rate; Indicates the number of uncovered demand points; This indicates whether requirement point i is covered. When demand point i is covered by at least one existing charging station, =1, otherwise = 0; This represents the charging demand at demand point i. This indicates whether demand point i is assigned to candidate charging station j at level r. ; This represents the probability that the r-th level charging station is in a serviceable state; A function representing user time satisfaction; Represents the reachability parameter. , This represents the distance between demand point i and candidate charging station j. This indicates the maximum service distance that the user can accept; A unified solution for the multi-objective location selection model is provided, and the specific process includes: Step 1: Normalize each objective function; in, Indicates the first The optimal value achievable by each objective function within the feasible region that satisfies the constraints is used as the benchmark value for the normalization process of the corresponding objective function. Step 2: Construct a scalarization function and conduct a comprehensive evaluation; in, For the target weight vector, And satisfy .

[0065] Step 3: Under the constraints of the phased construction strategy determined in step S205, for different target weight vectors... An improved non-dominated sorting genetic algorithm is used to scalarize the function. The solution is obtained by solving the problem and obtaining candidate solutions under the corresponding weight conditions. Then, the candidate solutions obtained under different weight vectors are subjected to non-dominated screening to form the Pareto optimal solution set for charging station site selection. Finally, the total system cost function is combined with the solution. The Pareto optimal solution set is then further filtered to determine the final phased layout scheme for electric vehicle charging stations.

[0066] The algorithm parameters are: population size 100, maximum number of iterations 200, crossover probability 0.9, mutation probability 0.1, thus obtaining the optimized layout scheme of electric vehicle charging stations.

[0067] Figure 5 This represents the set of optimal solutions for city A. For example... Figure 5 As shown, the optimal layout scheme of the charging station can be obtained by solving the established multi-objective optimization model.

[0068] By applying the electric vehicle charging station site selection optimization method of the present invention to city A, the final electric vehicle charging station site selection results are obtained. This can reduce the construction cost of charging infrastructure while meeting the charging demand coverage, and improve the service capacity and operational reliability of the charging network, making the layout of electric vehicle charging infrastructure more reasonable.

[0069] In this implementation, firstly, urban traffic network structure data, urban points of interest data, electric vehicle travel and charging demand data for city A, as well as land use, traffic accessibility, and power access conditions data required for candidate site selection are collected. Spatial analysis and cluster analysis are used to determine the set of demand points, and a candidate charging station set is obtained through screening. Based on this, a charging station construction cost model is established, incorporating land costs, construction costs, operation and maintenance costs, and equipment depreciation costs. A multi-objective site selection model is constructed, aiming to minimize construction costs, minimize the number of uncovered demand points, and maximize user time satisfaction. This model incorporates charging station outage risk disturbance factors and comprehensively reflects construction costs, non-service penalty costs, and vehicle travel costs through a system total cost function. Furthermore, single-point construction strategies, quantitative construction strategies, and dynamic adjustment strategies are set according to the charging network construction stages, and phased dynamic layout planning of charging stations is achieved based on stage priority indicators. Simultaneously, a user time satisfaction model is established, quantifying the impact of response time on user experience based on queuing theory. Finally, an improved non-dominated sorting genetic algorithm is used to solve the above multi-objective optimization model. Through non-dominated sorting, crowding calculation, and reference point selection mechanisms, the population is iteratively updated to obtain the Pareto optimal solution set for charging station site selection. This is then combined with the system total cost function constructed in step S204. A secondary selection process is performed on the Pareto optimal solution set, prioritizing the selection of... The smaller option was chosen as the final charging station layout plan.

[0070] Compared with traditional static site selection methods, the method of this invention can more realistically reflect the actual operating environment of the charging network, reduce infrastructure construction costs while meeting charging demand coverage, and improve the service capacity and operational reliability of the charging network, making the layout of electric vehicle charging infrastructure more reasonable.

[0071] Example 3 Figure 5 This is a schematic diagram of an electric vehicle charging station site selection optimization system according to one embodiment of the present invention. Figure 5 As shown, according to one embodiment of the present invention, an electric vehicle charging station site selection optimization system includes: The acquisition module 10 is used to acquire a set of charging demand points based on urban traffic network structure data, urban point of interest data, and electric vehicle travel and charging demand data; and to acquire a set of candidate charging stations based on land use, traffic accessibility, and power access conditions. Model building module 20 is used to build an electric vehicle charging station site selection optimization model that takes into account the interruption risk disturbance based on the set of charging demand points and the set of candidate charging stations. The model solving module 30 is used to solve the electric vehicle charging station site selection optimization model based on the improved non-dominated sorting genetic algorithm, and obtain the optimal solution set for the staged site selection of electric vehicle charging stations. The location selection module 40 is used to select the location of electric vehicle charging stations based on the optimal solution set of phased location selection for electric vehicle charging stations.

[0072] This embodiment proposes an electric vehicle charging station site selection optimization system, comprising four functional units: an acquisition module 10, a model building module 20, a model solving module 30, and a site selection module 40. These modules work together to optimize the entire charging station site selection process. The acquisition module 10 is responsible for collecting and processing basic data. By integrating urban traffic network structure data, urban point-of-interest data, and electric vehicle travel and charging demand data, it uses spatial analysis and cluster analysis methods to identify the set of charging demand points. Simultaneously, it selects and determines a set of candidate charging stations based on land use compliance, traffic accessibility index, and power access capacity constraints, providing a data foundation for subsequent optimization modeling. The model building module 20, based on the acquired demand point set and candidate station set, establishes a charging station construction cost model that includes land costs, construction costs, operation and maintenance costs, and equipment depreciation costs. Furthermore, it constructs a multi-objective site selection optimization model with the objectives of minimizing construction costs, minimizing the number of uncovered demand points, and maximizing user time satisfaction. This model incorporates the risk of charging station outages. The system employs a perturbation mechanism that comprehensively reflects construction costs, non-service penalty costs, and vehicle operating costs. It also establishes a phased dynamic construction strategy and a user time satisfaction model to achieve coordinated optimization of demand coverage, service reliability, and user experience. The model solution module 30 uses an improved non-dominated sorting genetic algorithm to solve the multi-objective model. Through normalization, scalarization function construction, non-dominated sorting, congestion calculation, and reference point selection mechanisms, it iteratively updates the population to obtain the Pareto optimal solution set for phased site selection of charging stations, achieving efficient optimization under multi-objective trade-offs. The site selection module 40, based on the obtained optimal solution set and combined with the construction quantity and priority indicators of each stage during the planning period, determines the final layout scheme and phased construction plan for charging stations, guiding the actual implementation of charging infrastructure. Through the organic connection and functional synergy of the four modules, the system achieves a closed-loop process from data collection, demand identification, model construction, optimization solution to site selection decision-making. It can balance the economy, coverage, and reliability of the charging network in complex urban environments, providing systematic technical support for the scientific planning and dynamic evolution of electric vehicle charging infrastructure.

[0073] According to one embodiment of the present invention, the electric vehicle charging station site selection optimization model includes: , , , in, This indicates the total cost of building a charging station. ; This represents the total construction cost of candidate charging station j; Let j represent the location decision variables for candidate charging station j. ; This represents the set of candidate charging stations; This indicates the number of uncovered demand points. ; This indicates whether requirement point i is covered. ; Represents the set of charging demand points; Indicates overall user time satisfaction. ; This represents the charging demand at demand point i. Indicates whether demand point i is assigned to candidate charging station j at level r; This represents the probability that the r-th level charging station is in a serviceable state; Indicates user time satisfaction; R represents the actual response time when demand point i is allocated to candidate charging station j at level r; R represents the system demand coverage. Meanwhile, the electric vehicle charging station site selection optimization model satisfies the following constraints: , , , , in, Represents the reachability parameter. , This represents the distance between demand point i and candidate charging station j. This indicates the maximum service distance that the user can accept.

[0074] The probability that a charging station at level r is in a serviceable state is calculated using the following formula. : Where q represents the probability of an interruption at the charging station; Calculated using the following formula : , in, This represents the satisfaction decay coefficient. This indicates the maximum acceptable response time threshold for the user; The actual response time for demand point i to be allocated to candidate charging station j at level r is calculated using the following formula. : in, This represents the distance between demand point i and candidate charging station j; This indicates the average speed of the vehicle. Let represent the average queuing time of candidate charging station j at level r, calculated using a queuing theory model; This indicates the processing time before charging begins after the vehicle arrives at candidate charging station j.

[0075] In this embodiment, the electric vehicle charging station site selection optimization model aims to minimize the total construction cost of charging stations, minimize the number of uncovered demand points, and maximize user time satisfaction. The total construction cost is determined by the construction cost of each candidate charging station and site selection decision variables. The number of uncovered demand points is determined by the coverage status of each demand point. User time satisfaction is determined by the charging demand at each demand point, hierarchical allocation decision variables, the probability of charging station availability, and the actual response time. The model also satisfies constraints on demand point coverage, hierarchical allocation uniqueness, consistency between allocation and construction status, and accessibility. The model calculates the probability of serviceability of charging stations at each level using the probability of interruption, constructs a user time satisfaction function by comprehensively considering the satisfaction decay coefficient and the maximum response time threshold, and calculates the actual response time based on the distance between the demand point and the candidate station, the average vehicle speed, queuing time, and pre-charging processing time. Through the coupled design of the above objective function and constraints, comprehensive optimization of charging station construction cost, demand coverage level, user service experience, and interruption risk disturbance factors is achieved.

[0076] This invention constructs a multi-objective optimization model that integrates an interruption risk mechanism, thereby achieving synergistic optimization of charging station site selection schemes in terms of construction economy, coverage balance, service experience, and operational reliability. This significantly improves the adaptability and overall efficiency of the charging network in complex environments.

[0077] According to one embodiment of the present invention, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, it implements any electric vehicle charging station site selection optimization method of the present invention.

[0078] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the system and medium described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0079] The above description is merely a preferred embodiment of the present invention and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention is not limited to the specific combination of the above-described technical features, but also includes other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the inventive concept. For example, technical solutions formed by substituting the above-described features with (but not limited to) technical features with similar functions disclosed in this invention.

[0080] It should be understood that the sequence number of each step in the invention and embodiments of the present invention does not absolutely imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

Claims

1. A method for optimizing the site selection of electric vehicle charging stations, characterized in that, Includes the following steps: Based on urban traffic network structure data, urban points of interest data, and electric vehicle travel and charging demand data, a set of charging demand points is obtained; based on land use, traffic accessibility, and power access conditions, a set of candidate charging stations is obtained. Based on the set of charging demand points and the set of candidate charging stations, an electric vehicle charging station site selection optimization model considering the risk of interruption is constructed. An improved non-dominated sorting genetic algorithm is used to solve the electric vehicle charging station site selection optimization model to obtain the optimal solution set for the staged site selection of electric vehicle charging stations. Electric vehicle charging station site selection is based on the optimal solution set of phased site selection.

2. The method for optimizing the location of electric vehicle charging stations according to claim 1, characterized in that, The process of obtaining the set of charging demand points is as follows: The city’s functional areas are identified by urban point of interest data. These functional areas include: residential areas, commercial areas, industrial areas, public service areas, and leisure areas. Based on the urban point of interest data in various functional areas, and combined with electric vehicle travel and charging demand data, the kernel density estimation method is used to obtain the distribution density characteristics of electric vehicles. Based on urban traffic network structure data, network analysis method is used to calculate the network topology characteristic indicators of each functional area; Using the distribution density characteristics of electric vehicles in each functional area as the core feature vector and the network topology feature index as the spatial weight coefficient, a weighted clustering analysis using a clustering algorithm is employed to obtain the electric vehicle charging demand points.

3. The method for optimizing the location of electric vehicle charging stations according to claim 1, characterized in that, The process of obtaining the candidate charging station set is as follows: The constraints are land use compliance and power access capacity; Based on network analysis of urban traffic network structure data, the traffic accessibility index of candidate locations is calculated. The candidate locations are scored and sorted, and the top m locations are selected as candidate charging stations.

4. The method for optimizing the location of electric vehicle charging stations according to claim 1, characterized in that, The electric vehicle charging station site selection optimization model includes: ， ， ， in, This indicates the total cost of building a charging station. ; This represents the total construction cost of candidate charging station j; Let j represent the location decision variables for candidate charging station j. ; This represents the set of candidate charging stations; This indicates the number of uncovered demand points. ; This indicates whether requirement point i is covered. ; Represents the set of charging demand points; Indicates user time satisfaction. ; This represents the charging demand at demand point i. Indicates whether demand point i is assigned to candidate charging station j at level r; This represents the probability that the r-th level charging station is in a serviceable state; Indicates the time satisfaction of a single user; R represents the actual response time when demand point i is allocated to candidate charging station j at level r; R represents the system demand coverage. Meanwhile, the electric vehicle charging station site selection optimization model satisfies the following constraints: ， ， ， ， in, Represents the reachability parameter. , This represents the distance between demand point i and candidate charging station j. This indicates the maximum service distance that the user can accept.

5. The method for optimizing the location of electric vehicle charging stations according to claim 4, characterized in that: The probability that a charging station at level r is in a serviceable state is calculated using the following formula. : Where q represents the probability of an interruption at the charging station; Calculated using the following formula : in, This represents the satisfaction decay coefficient. This indicates the maximum acceptable response time threshold for the user; The actual response time for demand point i to be allocated to candidate charging station j at level r is calculated using the following formula. : in, This represents the distance between demand point i and candidate charging station j; This indicates the average speed of the vehicle. Let represent the average queuing time of candidate charging station j at level r, calculated using a queuing theory model; This indicates the processing time before charging begins after the vehicle arrives at candidate charging station j.

6. The method for optimizing the site selection of electric vehicle charging stations according to claim 1, characterized in that, An improved non-dominated sorting genetic algorithm is used to solve the site selection optimization model for electric vehicle charging stations, including: Normalize each objective function: ； Scalar functions are constructed based on the objective functions obtained from normalization: ； in, Represents the target weight vector. ; The Pareto optimal solution set for charging station site selection is obtained by solving the scalarization function.

7. A site selection optimization system for electric vehicle charging stations, characterized in that, include: The acquisition module is used to acquire a set of charging demand points based on urban traffic network structure data, urban point of interest data, and electric vehicle travel and charging demand data. Based on land use, transportation accessibility, and power access conditions, a set of candidate charging stations is obtained; The model building module is used to construct an electric vehicle charging station location optimization model that takes into account the interruption risk disturbance based on the set of charging demand points and the set of candidate charging stations. The model solving module is used to solve the electric vehicle charging station site selection optimization model based on the improved non-dominated sorting genetic algorithm, and obtain the optimal solution set for the staged site selection of electric vehicle charging stations; The site selection module is used to select the location of electric vehicle charging stations based on the optimal solution set of the phased site selection of electric vehicle charging stations.

8. The electric vehicle charging station site selection optimization system according to claim 7, characterized in that, The electric vehicle charging station site selection optimization model includes: ， ， ， in, This indicates the total cost of building a charging station. ; This represents the total construction cost of candidate charging station j; Let j represent the location decision variables for candidate charging station j. ; This represents the set of candidate charging stations; This indicates the number of uncovered demand points. ; This indicates whether requirement point i is covered. ; Represents the set of charging demand points; Indicates user time satisfaction. ; This represents the charging demand at demand point i. Indicates whether demand point i is assigned to candidate charging station j at level r; This represents the probability that the r-th level charging station is in a serviceable state; Indicates the time satisfaction of a single user; R represents the actual response time when demand point i is allocated to candidate charging station j at level r; R represents the system demand coverage. Meanwhile, the electric vehicle charging station site selection optimization model satisfies the following constraints: ， ， ， ， in, Represents the reachability parameter. , This represents the distance between demand point i and candidate charging station j. This indicates the maximum service distance that the user can accept.

9. The electric vehicle charging station site selection optimization system according to claim 7, characterized in that: The probability that a charging station at level r is in a serviceable state is calculated using the following formula. : Where q represents the probability of an interruption at the charging station; Calculated using the following formula : ， in, This represents the satisfaction decay coefficient. This indicates the maximum acceptable response time threshold for the user; The actual response time for demand point i to be allocated to candidate charging station j at level r is calculated using the following formula. : in, This represents the distance between demand point i and candidate charging station j; This indicates the average speed of the vehicle. Let represent the average queuing time of candidate charging station j at level r, calculated using a queuing theory model; This indicates the processing time before charging begins after the vehicle arrives at candidate charging station j.

10. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, which, when executed by a processor, implements the electric vehicle charging station site selection optimization method as described in any one of claims 1-6.

Images