Electric vehicle charging and battery replacing method based on efficiency visual angle

By improving genetic algorithms and introducing evolutionary reversal and elite strategies, and optimizing the location selection of electric vehicle charging and swapping stations, the problems of scarcity and uneven distribution of charging and swapping facilities are solved, and more efficient charging and swapping experience and facility utilization are achieved.

CN119067473APending Publication Date: 2024-12-03CHANGAN UNIV
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411153526.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-21
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

The scarcity and unbalanced distribution of electric vehicle charging and swapping facilities lead to low charging and swapping efficiency for users, limiting market development.

Method used

Adopt the charging and swapping method of electric vehicles based on the perspective of efficiency, and by improving genetic algorithms and introducing evolutionary reversal and elite strategies, optimizing the site selection model of charging and swapping stations, improving the search capability and efficiency of the algorithm, reducing the time cost of users to find the site, and achieving more convenient , efficient charging and swapping experience.

Benefits of technology

It significantly improves the charging and swapping efficiency, reduces the time cost of users to find a station, ensures the balanced layout of charging and swapping facilities, and improves the efficiency of facilities utilization.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119067473A_ABST
    Figure CN119067473A_ABST
Patent Text Reader

Abstract

The invention provides an electric vehicle charging and swapping method based on an efficiency perspective. The method comprises the specific steps that S1, consideration factors of electric vehicle charging and swapping site selection are determined based on the two perspectives of a charging and swapping mode and charging and swapping infrastructure classification; s2, based on the consideration factors determined in the S1, establishing an electric vehicle charging and battery swap station optimization site selection model; and S3, improving a genetic algorithm, and based on the improved genetic algorithm, selecting a target road network to solve the electric vehicle charging and battery swap station optimization site selection model. According to the method, the overall performance of the algorithm is remarkably enhanced, and a more efficient and reliable tool is provided for solving a complex optimization problem. By optimizing the site selection model of the charging station, the time cost of searching for the charging station by the user is effectively reduced, so that more convenient and efficient charging experience is created.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the field of intelligent transportation, and in particular relates to a method for charging and replacing electric vehicles based on an efficiency perspective. Background Art

[0002] With the rapid development of the new energy vehicle industry, the market penetration rate of electric vehicles (EVs) has increased significantly, which not only reflects the world's determination to transform to low-carbon transportation, but also reflects consumers' growing demand for sustainable travel. However, although electric vehicles have shown significant advantages in environmental performance and operating costs, their charging and swapping efficiency has become one of the key bottlenecks in the development of the industry, especially for those users who rely on public charging facilities. The convenience and time efficiency of electric vehicle charging are two core considerations. The long waiting time for charging and the uneven distribution of charging infrastructure have seriously affected the user experience, thereby limiting the full expansion of the electric vehicle market. This situation highlights the urgency of planning and construction of charging infrastructure, as well as the necessity of optimizing charging technology to shorten the charging cycle.

[0003] Faced with the surge in the number of electric vehicles, the contradiction between supply and demand of charging and swapping infrastructure has become increasingly prominent, becoming the main bottleneck restricting the development of the industry. Although fast charging technology has effectively improved the charging rate, the coverage density of charging stations is still insufficient. Although the battery swap model can achieve rapid energy replenishment of vehicles, the high construction and operation costs, coupled with the lack of cross-brand compatibility, limit its large-scale application, and ultimately make it difficult for users to achieve rapid battery swapping; as the number of electric vehicles continues to grow, how to solve the problem of low charging and swapping efficiency caused by insufficient number and uneven distribution of charging and swapping infrastructure has become an urgent need to promote the sustainable and healthy development of the electric vehicle market. Summary of the invention

[0004] The purpose of the embodiments of the present invention is to provide an electric vehicle charging and swapping method based on efficiency perspective, so as to solve the problem of scarce and uneven distribution of charging and swapping facilities and improve the efficiency of electric vehicle charging and swapping.

[0005] In order to solve the above technical problems, the technical solution adopted by the present invention is a method for charging and replacing electric vehicles based on efficiency, comprising the following steps:

[0006] S1. Determine the factors to be considered in selecting the location for charging and swapping of electric vehicles based on the charging and swapping methods and the classification of charging and swapping infrastructure;

[0007] S2, establish an optimal site selection model for electric vehicle charging and swapping stations based on the considerations determined in S1;

[0008] S3. Improve the genetic algorithm and select the target road network based on the improved genetic algorithm to solve the optimal site selection model for electric vehicle charging and swapping stations.

[0009] Furthermore, the consideration factors determined in S1 are the user's station search cost and the coverage rate of charging and swapping stations.

[0010] Furthermore, S2 includes two sets of objective functions, namely, the user station search time cost and the charging and swapping station coverage rate, based on the considerations determined in S1:

[0011] S201, establish the user station search time cost objective function:

[0012]

[0013] Where f is the total time cost of the user to find a station; N is the total number of candidate points; D i is the sum of the shortest paths of all vehicles heading to node i; v is the average road speed of household electric vehicles; p is the user's unit time cost; the decision variable x i It is used to indicate whether a charging and swapping station has been established in area i; the decision variable y ji It is used to indicate the willingness of electric vehicles in area j to go to the charging and swapping stations established in area i; j is the number of vehicles with charging and swapping needs in area j; s ij is the shortest distance between the required area i and area j, min represents the minimum function, and max represents the maximum function;

[0014] S202, establish the charging and swapping station coverage rate objective function:

[0015]

[0016] Where a is the POI coverage rate; A i is the number of POIs covered by the charging and swapping station in area i; A is the number of POIs covered by all charging and swapping stations.

[0017] Furthermore, S2 also includes establishing constraint conditions, specifically:

[0018] S203. Establishing the number constraints of charging and swapping stations:

[0019]

[0020] Among them, M is the planned construction number of electric vehicle charging and swapping stations;

[0021] S204. Distance constraint between charging and swapping stations and demand points:

[0022] d i ≤d max

[0023] d i =min{y js ij}, j∈N

[0024] Among them, d i is the distance between area i and the nearest charging and swapping station; d max is the maximum distance; y j is a decision variable used to indicate whether a charging and swapping station is built in area j; min represents the minimum function, and max represents the maximum function;

[0025] S205, user charging and battery replacement constraints:

[0026] y ji ≤x i

[0027]

[0028] S206. Charging and swapping station capacity constraints:

[0029]

[0030] Among them, c i is the capacity of charging and swapping station i, w j is the number of vehicles that need charging or battery replacement at point j.

[0031] Furthermore, the S2 further includes:

[0032] S207, taking the minimum value of the ratio of the charging and swapping station coverage rate objective function to the charging and swapping station coverage rate objective function as the objective function minQ:

[0033]

[0034] Furthermore, the genetic algorithm is improved in S3 as follows:

[0035] S301. In each generation of the genetic algorithm, the population evolves through selection, crossover, and mutation operations:

[0036] P(t+1)=G(P(t))

[0037] Where P(t) represents the evolutionary operation at step t, and G(P(t)) represents the combination of all evolutionary operations;

[0038] S302, restore the genetic algorithm to the t0th generation:

[0039] P(t)→P(t0)

[0040] P(t0)=M -1 (C -1 (S -1 (P(t))))

[0041] Among them, S -1 Represents adverse selection operation; C -1 Indicates reverse crossover operation; M -1 Represents a reverse mutation operation.

[0042] Furthermore, in S3, in the process of solving the optimal site selection model for electric vehicle charging and swapping stations using an improved genetic algorithm, a certain proportion of individuals with the highest fitness are retained in each generation of crossover, mutation, and replacement operations of the genetic algorithm to enter the next generation.

[0043] Furthermore, when the iterative curve of the genetic algorithm converges, the optimal solution of the optimization site selection model for electric vehicle charging and swapping stations is obtained.

[0044] The beneficial effects of the present invention are as follows: the present invention has achieved a breakthrough in the field of genetic algorithms, and its core advantage is that it significantly improves the search ability and efficiency of the algorithm. First, by innovatively introducing the evolutionary reversal operation, the present invention effectively expands the exploration boundary of the space. Unlike traditional random mutation, evolutionary reversal only takes effect when the individual fitness is improved, accurately promotes the local search of the algorithm, and accelerates the discovery speed of high-quality solutions. This operation breaks the local optimal trap by directional reversal of individual genes, increases population diversity, and improves the performance of finding the global optimal solution. Secondly, the application of the elite strategy ensures the retention of high-quality solutions during the evolution process, and avoids the loss of excellent individuals caused by conventional operations such as crossover, mutation or replacement. This strategy accelerates the convergence of the algorithm and prevents premature local convergence by adjusting the proportion of elite individuals, ensuring that the algorithm still has a strong global search capability while maintaining high efficiency. By organically combining evolutionary reversal with the elite strategy, the present invention further consolidates the stability and solution speed of the genetic algorithm. This comprehensive strategy not only improves the overall performance of the algorithm, but also provides a more efficient and reliable tool for solving complex optimization problems. The present invention significantly reduces the time cost of users looking for stations by optimizing the site selection model of charging and swapping stations, creating a more convenient and efficient charging and swapping experience. At the same time, through the fine control of the distribution of charging and swapping stations by this method, the balanced layout of infrastructure can be achieved, and the utilization efficiency of facilities can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0046] Figure 1 It is a schematic diagram of the overall process of this implementation mode;

[0047] Figure 2 This is a network topology diagram constructed in Example 1 of the present invention;

[0048] Figure 3 It is an improved genetic algorithm iteration curve according to Embodiment 1 of the present invention;

[0049] Figure 4 The control group of Example 1 of the present invention is a standard genetic algorithm iteration curve;

[0050] Figure 5 This is a visualization diagram of the site selection results of Example 1 of the present invention. DETAILED DESCRIPTION

[0051] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0052] like Figure 1 This embodiment provides an electric vehicle charging and swapping method based on an efficiency perspective. When establishing an optimized site selection model, the characteristics of different charging and swapping methods and their applicable scenarios are fully considered, so as to formulate a more reasonable layout of charging and swapping facilities.

[0053] The specific steps include:

[0054] S1. By considering four charging and swapping methods (slow charging, fast charging, a combination of fast charging and slow charging, and a combination of charging and swapping) and the types of charging and swapping facilities and existing problems, factors (variables) are provided for the construction of subsequent charging and swapping models. For example, the different technical requirements and cost characteristics of fast charging and slow charging directly affect the site selection and investment planning of charging stations. The high construction cost and compatibility issues of the battery swapping model prompt the optimization model to be more cautious in selecting battery swapping stations in order to balance the charging and swapping efficiency and the user's time cost of finding a station. Through in-depth classification and analysis of the current status of charging and swapping methods and facilities, the method provided in this embodiment can better adapt to actual needs, improve the practicality and effectiveness of the model, and help optimize the site selection of charging and swapping stations and improve charging and swapping efficiency.

[0055] In order to address the problems of uneven distribution of charging and swapping facilities and poor user experience, a comprehensive optimization model is proposed. This model mainly guides site selection decisions through two key objective functions: the user's time cost for finding a station and the POI (Point of Interest in a specific map or geographic information system, the ratio of the number of points of interest that have been collected and recorded to the total number of all possible points of interest, in this embodiment, that is, the coverage rate of charging and swapping stations) coverage. The optimization process of the model relies on advanced algorithm improvement strategies, namely evolutionary reversal and elite strategies, to improve the search ability and efficiency of genetic algorithms. Specifically, the optimization model optimizes the layout and service quality of the charging and swapping network by minimizing the user's time cost for finding a station, improving the accessibility and utilization efficiency of charging and swapping facilities, and maximizing the POI coverage rate.

[0056] Then the complex uncertain factors in practice are simplified, specifically:

[0057] ① Assume that users have a consistent behavior pattern when choosing charging and swapping stations, that is, they tend to choose the nearest charging and swapping station without considering other factors. ② Assume that all vehicles have the same maximum driving distance, and use this distance to constrain the maximum distance between the charging and swapping station and the user's demand point. ③ Assume that a demand point only chooses the nearest charging and swapping station and will not go to other charging and swapping stations. ④ Assume that the time cost of electric vehicle users in the road network remains consistent in different scenarios and takes a unified value.

[0058] S2. Based on the two objective functions of station search time cost and POI coverage rate, an optimal site selection model for electric vehicle charging and swapping stations is established;

[0059] (1) Objective function construction

[0060] S21: User search time cost

[0061]

[0062] Where f is the total time cost of the user to find a station; N is the total number of candidate points; D i is the sum of the shortest paths of all vehicles traveling to node i; v is the average road speed of household electric vehicles; p is the user's unit time cost; x i is a decision variable. When the value is 1, it means that there is a charging and swapping station in area i. When the value is 0, it means that there is no charging and swapping station in area i. ji represents the decision variable, with values ​​of 0 and 1, which means whether the electric vehicle at point j goes to the charging and swapping station i for charging and swapping, that is, the willingness of the electric vehicle at point j to go to the charging and swapping station established in area i. Only when the charging and swapping facilities are established in area i, will vehicles come to this area for charging; w j is the number of vehicles with charging and swapping needs in area j; sij is the shortest distance between demand area i and area j.

[0063] S22: POI coverage

[0064]

[0065] Where a is the POI coverage rate. In this embodiment, the POI coverage rate is the coverage rate of the charging and swapping stations. i is the number of POIs covered by the charging and swapping station in area i; A is the number of POIs covered by all charging and swapping stations.

[0066] (2) Construction of Constraints

[0067] S23: Constraints on the number of charging and swapping stations

[0068]

[0069] Among them, M is the planned number of electric vehicle charging and swapping stations to be built.

[0070] S24: Distance constraint between charging and swapping stations and demand points

[0071] d i ≤d max

[0072] d i =min{y j s ij}, j∈N

[0073] Where, d i is the distance between area i and the nearest charging and swapping station; d max is the maximum distance; y j is a decision variable. It takes the value of 1 when there is a charging and swapping station in area j, and takes the value of ∞ when there is no charging and swapping station.

[0074] S25: User charging and battery swapping constraints

[0075] In order to ensure that electric vehicle users can only charge and swap at sites with charging and swapping stations in the road network, the constraints are as follows:

[0076] y ji ≤x i

[0077] In order to ensure that each demand point has and only has one charging and swapping station to provide charging and swapping services, the constraints are as follows:

[0078]

[0079] S26: Charging and swapping station capacity setting

[0080]

[0081] Among them, c i is the capacity of charging and swapping station i, w j is the number of vehicles that need charging or battery replacement at point j.

[0082] S27: Using a method based on mutual relationship, the established charging and swapping station site selection model is transformed from a dual-objective to a single-objective solution. The minimum ratio of the user's station search time cost and the POI coverage rate is used as the objective function Q. Specifically:

[0083]

[0084] S3. Based on evolutionary reversal and "elite strategy", the improved genetic algorithm is used to solve the optimal site selection model for electric vehicle charging and swapping stations.

[0085] In order to improve the local search capability of the genetic algorithm, multiple consecutive evolution reversal operations are introduced after selection, crossover, and mutation. The evolution reversal operation includes the "evolution" operation and the reversal operation. In each generation, the population evolves through selection, crossover, and mutation operations, which can be expressed by the following formula:

[0086] P(t+1)=G(P(t))

[0087] Among them, P(t) represents the evolutionary operation of the tth step, including selection, crossover, mutation and other operations; G(P(t)) represents the combination of all evolutionary operations.

[0088] The goal of the evolutionary reversal operation is to restore the population state to a previous generation. Assuming that the system is restored to the t0th generation, the reversal operation can be expressed as:

[0089] P(t)→P(t0)

[0090] Reverse each evolutionary operation, including selection, crossover, and mutation. Then S -1 , C -1 and M -1 They represent reverse selection operation, reverse crossover operation and reverse mutation operation respectively, and the formula of comprehensive reverse operation is as follows:

[0091] P(t0)=M -1 (C -1 (S -1 (P(t))))

[0092] The "evolution" here refers to the unidirectional nature of the reversal operator, that is, only after the reversal, the fitness value of the individual is improved, it will be accepted, otherwise the reversal operation will be considered invalid. The core idea of ​​the reversal operation is to introduce mutations by reversing certain gene bits of the individual to explore a wider solution space. Unlike traditional random mutations, the evolutionary reversal operation is only effective when the fitness of the individual is improved after the reversal, which helps to accelerate the local search process of the algorithm and thus more effectively find better solutions. The reversal operation introduces a certain probability to randomly select some individuals and reverse their genes. If the encoding method is binary encoding, the reversal operation is to change 0 in the binary code to 1 and 1 to 0, thereby generating new individuals. The reversal operation helps to jump out of the local optimal solution, increase the diversity of the population, and promote the global search ability of the algorithm.

[0093] In order to prevent the excellent solutions generated in the evolution process from being destroyed by steps such as crossover, mutation and replacement, an elite strategy is introduced to ensure the preservation of excellent individuals. The specific steps are as follows:

[0094] ① Select the best individuals: In the evolution process of each generation, this implementation method will select the individuals with the highest fitness, which are called "elites".

[0095] ② Retain the elites: During the steps of crossover, mutation and replacement, ensure that these "elites" will not be destroyed, that is, they will be retained and enter the next generation.

[0096] ③ Elite ratio: Set an "elite ratio". In each generation, a certain proportion of individuals with the highest fitness will be retained.

[0097] This can accelerate the convergence speed of the algorithm and enable the algorithm to find the optimal solution faster. The elite strategy can also control the overall convergence speed of the algorithm by introducing the ratio of the number of elites. The more elites there are, the faster the convergence. However, too many elites may cause local convergence of the algorithm, thereby obtaining a local optimal solution.

[0098] Combining evolutionary reversal and elite strategy can further improve the performance of genetic algorithm. Evolutionary reversal operation increases the diversity of population and helps to escape from local optimal solution. Elite strategy retains the excellent individuals of the parent generation and improves the convergence speed of the algorithm. Through the comprehensive application of these two improvement methods, the stability and solution speed of genetic algorithm are improved.

[0099] In some specific embodiments, the input variables of the site selection model of the present invention include four charging and swapping modes (such as slow charging, fast charging, etc.) and related constraints (such as the number of charging and swapping stations, location distance, etc.), and the genetic algorithm is used to iteratively optimize these input variables. The genetic algorithm simulates the evolutionary process in nature, selects, crosses and mutates the input variables of the model, and gradually evolves to find the optimal solution. This process enables the algorithm to find the best solution among multiple possible configurations of the number and location of charging and swapping stations, which is specifically manifested in the specific location of the charging and swapping stations and the demand points they cover. In addition, this embodiment will also ensure the configuration when the objective function (such as the ratio of the user's travel time cost to the coverage rate of points of interest (POI)) reaches the minimum value. In this way, the service efficiency of the charging and swapping stations and the convenience of the users can be effectively balanced.

[0100] Example 1

[0101] The 25-traffic-node network diagram commonly used in the optimization site selection problem is used as an example to solve the problem. Figure 2 The hypothetical network shown is used in the location optimization study. The network consists of 25 nodes. The numbers next to the nodes represent the demand, and the numbers on each edge are the travel time between two adjacent points. All nodes are considered as candidate locations for the starting point, end point, and joint station. Figure 1 The method shown is used to analyze the site selection results. Figure 3 It is the iteration curve of the improved genetic algorithm in the embodiment of the present invention. As the number of iterations increases, the objective function Q, i.e., the ratio of the user travel time cost to the POI coverage rate, decreases. The iteration curve converges when the number of iterations reaches 26, indicating that the global optimal solution of the example has been found. Figure 4 It is the control group of the embodiment of the present invention, which is a standard genetic algorithm iteration curve. Figure 5 is a visualization diagram of the site selection solution result of the embodiment of the present invention, which is drawn from the adjacency matrix converted from the road network in the example. Figure 5 The larger points are charging and swapping stations, and the smaller points are demand points where charging and swapping stations are not built. Each larger point is responsible for the demand points of the same color as its own. From the results of the two figures, we can see that Figure 4 The iterative curve using the standard genetic algorithm is shown. As the number of iterations increases, the value of the objective function gradually decreases, but the convergence speed is relatively slow. Figure 5 This is the site selection scheme after the genetic algorithm is improved in the present invention. Its iteration curve shows that the improved algorithm can find the global optimal solution more quickly. In particular, after the introduction of evolutionary reversal and elite strategies, the algorithm convergence speed is significantly accelerated, indicating that the improved algorithm is more effective in optimizing the site selection of charging and swapping stations.

[0102] Each embodiment in this specification is described in a related manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0103] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention are included in the protection scope of the present invention.

Claims

1. A method for charging and replacing electric vehicles based on efficiency, characterized in that: The following steps are involved: S1. Determine the factors to be considered in selecting the location for charging and swapping of electric vehicles based on the charging and swapping methods and the classification of charging and swapping infrastructure; S2, establish an optimal site selection model for electric vehicle charging and swapping stations based on the considerations determined in S1; S3. Improve the genetic algorithm and select the target road network based on the improved genetic algorithm to solve the optimal site selection model for electric vehicle charging and swapping stations.

2. The method for charging and replacing electric vehicles based on efficiency according to claim 1, characterized in that: The considerations determined in S1 are the user's station search cost and the coverage rate of charging and swapping stations.

3. A method for charging and replacing electric vehicles based on efficiency according to any one of claims 1 and 2, characterized in that: S2 includes two sets of objective functions, namely, the user station search time cost and the charging and swapping station coverage rate, based on the considerations determined in S1: S201, establish the user station search time cost objective function: Where f is the total time cost of the user to find a station; N is the total number of candidate points; D i is the sum of the shortest paths of all vehicles traveling to node i; v is the average road speed of household electric vehicles; p is the user's unit time cost; the decision variable x i It is used to indicate whether a charging and swapping station has been established in area i; the decision variable y ji It is used to indicate the willingness of electric vehicles in area j to go to the charging and swapping stations established in area i; j is the number of vehicles with charging and battery swapping needs in area j; s ij is the shortest distance between the required area i and area j, min represents the minimum function, and max represents the maximum function; S202, establish the charging and swapping station coverage rate objective function: Where a is the POI coverage rate; A i is the number of POIs covered by the charging and swapping station in area i; A is the number of POIs covered by all charging and swapping stations.

4. The method for charging and replacing electric vehicles based on efficiency perspective according to claim 3, characterized in that: The S2 also includes establishing constraint conditions, specifically: S203. Establishing the number constraints of charging and swapping stations: Among them, M is the planned construction number of electric vehicle charging and swapping stations; S204. Distance constraint between charging and swapping stations and demand points: d i ≤d max d i =min{y j s ij },j∈N Among them, d i is the distance between area i and the nearest charging and swapping station; d max is the maximum distance; y j is a decision variable used to indicate whether a charging and swapping station is built in area j; S205, user charging and battery replacement constraints: and ji ≤x i S206. Charging and swapping station capacity constraints: Among them, c i is the capacity of charging and swapping station i, w j is the number of vehicles that need charging or battery replacement at point j.

5. A method for charging and replacing electric vehicles based on efficiency perspective according to any one of claims 3 or 4, characterized in that: The S2 further includes: S207, taking the minimum value of the ratio of the charging and swapping station coverage rate objective function to the charging and swapping station coverage rate objective function as the objective function minQ:

6. The method for charging and replacing electric vehicles based on efficiency perspective according to claim 1, characterized in that: The improvements to the genetic algorithm in S3 are as follows: S301. In each generation of the genetic algorithm, the population evolves through selection, crossover, and mutation operations: P(t+1)=G(P(t)) Where P(t) represents the evolutionary operation at step t, and G(P(t)) represents the combination of all evolutionary operations; S302, restore the genetic algorithm to the t0th generation: P(t)→P(t0) P(t0)=M -1 (C -1 (S -1 (P(t)))) Among them, S -1 Represents adverse selection operation; C -1 Indicates reverse crossover operation; M -1 Represents a reverse mutation operation.

7. The method for charging and replacing electric vehicles based on efficiency perspective according to claim 1, characterized in that: In S3, in the process of solving the optimal site selection model of electric vehicle charging and swapping stations using an improved genetic algorithm, a certain proportion of individuals with the highest fitness are retained in each generation of crossover, mutation and replacement operations of the genetic algorithm to enter the next generation.

8. The method for charging and replacing electric vehicles based on efficiency according to claim 1, characterized in that: When the iterative curve of the genetic algorithm converges, the optimal solution of the electric vehicle charging and swapping station optimization site selection model is obtained.