Optimal distribution method and system for electric vehicle charging stations

Abstract

The invention discloses an optimal distribution method for electric vehicle charging stations, and the method comprises the steps: constructing a state transition matrix based on the travel time of a driver of a to-be-charged electric vehicle, the charging cost, the number of available charging piles of the charging stations, the comprehensive position of the charging stations, and the attraction of the charging stations, and generating charging demand probability distribution in real time; calculating a reachable radius according to the residual electric quantity and the energy consumption rate of the to-be-charged electric vehicle, screening a candidate charging station set, fusing a driver preference weight, and establishing a multi-target distribution cost evaluation mechanism; constructing an optimal distribution model of the electric vehicle charging stations; an initial population is generated through greedy random adaptive search, a multi-parent cross strategy or a directional exchange strategy is dynamically executed according to the remaining time of a driver, and a corresponding optimal charging station distribution scheme is output. According to the method, the optimal charging station is allocated for the electric vehicle user, and the driving distance cost, the charging currency cost and the destination walking distance cost are reduced to the maximum extent.

Description

Technical Field

[0001] This invention relates to the field of power system technology, and in particular to an optimized allocation method and system for electric vehicle charging stations. Background Technology

[0002] With the rapid development of my country's new energy vehicle market, public attention to vehicle charging is constantly increasing. Solving the charging problem for users is crucial for the popularization of electric vehicles. Users are typically influenced by various factors when choosing a charging station, including daily mileage, electric vehicle network access time, remaining state of charge (SOC), vehicle downtime, charging costs, charging infrastructure configuration, starting charging time, and the density of points of interest. How to allocate the best charging stations to electric vehicle users and minimize driving distance costs, charging monetary costs, and walking distance costs to the destination has become a key concern for consumers. Therefore, a method to optimize the allocation of electric vehicle charging stations is urgently needed. Summary of the Invention

[0003] To address the shortcomings of the prior art, this invention provides an optimized allocation method and system for electric vehicle charging stations. The method can allocate the best charging stations to electric vehicle users and minimize driving distance costs, charging currency costs, and destination walking distance costs.

[0004] This invention provides an optimized allocation method for electric vehicle charging stations, comprising:

[0005] S1: Based on the travel time of the drivers of electric vehicles waiting to be charged, the charging cost, the number of available charging piles at the charging station, the comprehensive location of the charging station and the attractiveness of the charging station, construct a state transition matrix and generate a probability distribution of charging demand in real time.

[0006] S2: Calculate the reachable radius based on the remaining power and energy consumption rate of the electric vehicle to be charged, screen the candidate charging station set, integrate driver preference weights, and establish a multi-objective allocation cost evaluation mechanism;

[0007] S3: Construct an optimal allocation model for electric vehicle charging stations, wherein the optimal allocation model for electric vehicle charging stations includes minimizing the driving distance cost, charging currency cost, and destination walking distance cost as objective functions and electricity feasibility constraints;

[0008] S4: Solve the optimal allocation model for electric vehicle charging stations: Generate an initial population through a greedy random adaptive search, and dynamically execute a multi-parent crossover strategy or a directional exchange strategy based on the driver's remaining time to output the corresponding optimal charging station allocation scheme.

[0009] Furthermore, the specific process of S1 is as follows:

[0010] S11: Based on charging stations Service rating Convenience of transportation Calculate the attractiveness of charging stations The calculation formula is as follows:

[0011]

[0012] in, , All are weighting coefficients; Rate the service of charging station i; To improve the accessibility of charging station i

[0013] S12: Based on the attractiveness of the charging station Charging costs Calculate the achievement rate The calculation formula is as follows:

[0014]

[0015] in, This is the vehicle density coefficient for the area where the charging station is located.

[0016] S13: Calculate the departure rate using the number of available charging piles at charging stations and the travel time of drivers of electric vehicles waiting to be charged. The calculation formula is as follows:

[0017]

[0018] in, Basic service rate; This represents the number of available charging stations. For travel time;

[0019] S14: Construct the state transition matrix Q:

[0020]

[0021] in, This is the system state transition matrix; The time step is denoted by m; m and n are both system states. M represents the real-time capacity status of charging station i; M represents the total number of charging piles in the charging station.

[0022] S15: Generation of charging demand probability distribution:

[0023]

[0024] in, Let t be the expected probability that charging station i is counted as an overloaded station under the preset congestion conditions; Let be the steady-state probability distribution of charging station i at time t; This is an indicator function.

[0025] Furthermore, the formula for calculating the reachable radius in S2 is:

[0026]

[0027] in, The reachable radius; This is a preset upper limit for the reachable radius; Energy consumption rate of electric vehicles (kWh / km); The remaining battery power (kWh) of the electric vehicle.

[0028] Furthermore, the specific formula for the driver preference weights in S2 is as follows:

[0029]

[0030] in, Driver preference weights; To select the historical number of times the cost-dominant option of type k is chosen; To select the first in the historical charging record for the driver The cumulative number of cost-driven schemes.

[0031] Furthermore, the multi-objective allocation cost evaluation mechanism in S2 is as follows:

[0032]

[0033] in, The overall objective function; All are preference weights; This refers to the cost of the driving distance, i.e., the distance between the vehicle and the charging station; The charging cost for charging station i; Cost of walking distance to the destination.

[0034] Furthermore, the specific constraints on electricity feasibility are as follows: .

[0035] Furthermore, the specific process of S4 is as follows:

[0036] S41: A greedy random adaptive search is used to generate the initial population, that is, for the current electric vehicle v, a restricted candidate list RCL is constructed from the corresponding set of candidate charging stations:

[0037]

[0038] Where RCL is the restricted candidate list; i represents electric vehicles; A collection of candidate charging stations; The corresponding values ​​are the minimum and maximum costs in the candidate charging station set; For greedy random coefficients, ;

[0039] S42: Determine the remaining computation time Is it greater than the upper bound of the calculation time? If yes, proceed to S43; if no, proceed to S44.

[0040] S43: Perform multi-parental crossover operation ( That is, to randomly select three parent chromosomes to exchange characteristic segments and construct the offspring chromosome;

[0041] S44: Directed exchange operation ( If there is insufficient time remaining, it will force a switch to the nearest charging station.

[0042] Furthermore, the specific process of S43 is as follows:

[0043] S431: Randomly select three parent chromosomes ;

[0044] S432: Generate two random cutting points i and j, where 1≤i≤j≤N v N v The length of the chromosome;

[0045] S433: Constructing offspring chromosomes :

[0046]

[0047] in, paternal chromosomes The gene segment numbered from s to e, i.e. the charging station allocation scheme for vehicle indexes from s to e;

[0048] S434: Obtain the newly created offspring chromosome. Then, the offspring chromosomes Decode the offspring chromosomes; the decoded chromosomes represent the charging station allocation scheme.

[0049]

[0050] in, The decoded offspring chromosomes, i.e., the charging station allocation scheme; is the gene value of vehicle v in the offspring chromosome; N is the total number of charging stations in the region.

[0051] Furthermore, S44 specifically becomes:

[0052] S441: Calculate all blocking probability values ​​in the current solution, where the formula for calculating the blocking probability value is:

[0053]

[0054] S442: Determine whether the blocking probability value is greater than the preset blocking probability threshold: if yes, proceed to S443; if no, proceed to S444.

[0055] S443: If the charging station i corresponding to the congestion probability value is determined to be overloaded, that is, if the occupancy rate of charging station i is >80%, then for the electric vehicle v allocated to charging station i, retain the original set of candidate charging stations corresponding to electric vehicle v. Calculate the target charging station for emergency replacement Remove the original candidate charging station set Currently, the charging stations in the middle are overloaded. The nearest charging station in the European direction will be selected for forced allocation. This means unbinding the electric vehicle v from the original overloaded charging station i, and establishing a connection between the electric vehicle v and the emergency replacement target charging station. The binding;

[0056] Where, is the Euclidean distance (in meters) from electric vehicle v to charging station k; k is the traversal index of the candidate charging stations in the candidate charging station set; and v is the index of the vehicle to be reassigned. This represents the blocking probability value, i.e., the real-time load rate of charging station i. The preset blocking probability threshold, i.e. the overload threshold of the charging station, is set to 0.8 in this embodiment; For binary decision variables: This indicates that electric vehicle v is allocated to charging station i. This indicates that electric vehicle v has not been assigned to charging station i.

[0057] S444: Determine that the charging station i corresponding to the blockage probability value is not overloaded, and confirm that the binding relationship between electric vehicle v and charging station i is valid; if invalid, return to S441; if valid, keep the decision variable unchanged, i.e. The allocation is marked as a stable allocation and added to the final solution set. Then, the expected load growth rate of charging station i is calculated, the vehicle arrival time is estimated, and the charging station status data is updated.

[0058] The formula for calculating the expected load growth rate of charging station i is as follows:

[0059]

[0060] in, The expected load growth rate of charging station i; This represents the total number of charging piles at charging station i. This refers to the set of electric vehicles that have been allocated but have not yet arrived within the current time period; Charging stations for electric vehicles that have been allocated but not yet arrived;

[0061] Estimated vehicle arrival time The calculation formula is:

[0062]

[0063] in, Current system time; Vehicle-to-charging-station distance; Average driving speed.

[0064] Secondly, the present invention provides an optimized allocation system for electric vehicle charging stations, the system performing the method described above, including:

[0065] Charging demand probability acquisition module: Based on the travel time of the driver of the electric vehicle to be charged, the charging cost, the number of available charging piles at the charging station, the comprehensive location of the charging station and the attractiveness of the charging station, it constructs a state transition matrix and generates a charging demand probability distribution in real time.

[0066] Multi-objective allocation cost evaluation mechanism construction module: used to calculate the reachable radius based on the remaining power and energy consumption rate of the electric vehicle to be charged, screen the candidate charging station set, integrate driver preference weights, and establish a multi-objective allocation cost evaluation mechanism;

[0067] The charging station allocation model set constraint module is used to construct an optimal allocation model for electric vehicle charging stations. The optimal allocation model for electric vehicle charging stations includes minimizing the driving distance cost, charging currency cost, and destination walking distance cost as objective functions and electricity feasibility constraints.

[0068] Charging station allocation scheme generation module: used to solve the optimal allocation model of electric vehicle charging stations: an initial population is generated through greedy random adaptive search, and a multi-parent crossover strategy or a directional exchange strategy is dynamically executed according to the driver's remaining time to output the corresponding optimal charging station allocation scheme.

[0069] This invention proposes an optimized allocation method for electric vehicle charging stations. This method assigns the best charging stations to electric vehicle drivers to minimize charging costs and destination distances, while ensuring effective utilization of the overall charging station capacity based on renewable energy. This is of great significance for the establishment of electric vehicle charging station infrastructure, maximizing energy efficiency and the number of electric vehicles expected to charge, reducing the total allocation cost for electric vehicle users, and promoting the widespread adoption of electric vehicles. Attached Figure Description

[0070] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0071] Figure 1 This is a flowchart of the optimized allocation method for electric vehicle charging stations provided in an embodiment of the present invention. Detailed Implementation

[0072] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be described in detail below. Obviously, the described embodiments are merely some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other implementation methods obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0073] Example 1

[0074] like Figure 1 As shown, this embodiment provides an optimized allocation method for electric vehicle charging stations, including:

[0075] S1: Based on the travel time of drivers of electric vehicles waiting to be charged, charging costs, the number of available charging piles at charging stations, the overall location of charging stations, and the attractiveness of charging stations, a state transition matrix is ​​constructed to generate a real-time probability distribution of charging demand. The specific process is as follows:

[0076] S11: Based on charging stations Service rating Convenience of transportation Calculate the attractiveness of charging stations The calculation formula is as follows:

[0077]

[0078] in, , All are weighting coefficients; In this specific implementation, the service score for charging station i is obtained by averaging the historical scores. To assess the accessibility of charging station i, this embodiment uses a dynamic weighted calculation based on factors such as road network density (40%), vehicle speed ratio (30%), number of entrances / exits (15%), and distance to traffic facilities (15%). The calculation formula is as follows:

[0079]

[0080] in, The regularization value for road network density is (0~1). Peak average speed (km / h); Free-flow speed (km / h); The number of entrances and exits is scored (≥4 = 1.0, deduct 0.25 for each less than 4). Distance to the nearest bus stop (m); Distance to the nearest subway station (m);

[0081] S12: Based on the attractiveness of the charging station Charging costs Calculate the achievement rate The calculation formula is as follows:

[0082]

[0083] in, This is the vehicle density coefficient for the area where the charging station is located.

[0084] S13: Calculate the departure rate using the number of available charging piles at charging stations and the travel time of drivers of electric vehicles waiting to be charged. The calculation formula is as follows:

[0085]

[0086] in, Basic service rate refers to the average service capacity of a single charging station under ideal conditions, that is, the number of vehicles that can be fully served per unit of time (usually 1 hour). ; This represents the number of available charging stations. For travel time.

[0087] S14: Construct the state transition matrix:

[0088]

[0089] in, The state transition matrix represents the system state. The time step is denoted by m; m and n are both system states. M represents the real-time capacity status of charging station i; M represents the total number of charging piles in the charging station.

[0090] S15: Generation of charging demand probability distribution:

[0091]

[0092] in, is the expected probability that charging station i is counted as an overloaded station under the preset blocking condition at time t; is the steady-state probability distribution of charging station i at time t; is the indicator function (triggering the selection probability when there are idle charging piles). The state transition matrix Q is used to describe the internal state evolution of the charging station (the change in the number of vehicles). The indicator function 𝕀( <M): takes 1 when the load rate of the charging station is less than the total number of charging piles M (allowing new vehicles to enter), otherwise takes 0 (blocking entry). Relationship with the user selection probability: The 𝕀 function ensures that the Q matrix only receives new vehicles when the charging station is not full, indirectly affecting subsequent allocation decisions.

[0093] S2: Calculate the reachable radius based on the remaining power and energy consumption rate of the electric vehicle to be charged, screen the set of candidate charging stations, fuse the driver preference weights, and establish a multi-objective allocation cost evaluation mechanism. The specific process is as follows:

[0094] The calculation formula for the reachable radius is:

[0095]

[0096] where, is the reachable radius; is the preset upper limit of the reachable radius; is the energy consumption rate of the electric vehicle (kWh / km); is the remaining power of the electric vehicle (kWh). In specific implementation, with the electric vehicle as the center and the reachable radius as the radius, the charging stations within the reachable radius that meet the screening probability filtering conditions for candidate charging stations are all candidate charging stations, obtaining the set of candidate charging stations, where the screening probability filtering conditions for candidate charging stations are:

[0097] Screening probability filtering conditions for candidate charging stations:

[0098]

[0099] where, is the preset threshold (taking 0.2).

[0100] The driver preference weight is dynamically calibrated through historical selection data, and the specific formula is:

[0101]

[0102] where, is the driver preference weight; is the historical number of times of selecting the k-th type of cost-dominant scheme, is the type of cost-dominant scheme, is the distance cost-dominant type when = 1, When the value is 2, it is a waiting time-dominant type. =3 when electricity price is cost-driven; This indicates that the driver selects the first option in the charging history. The cumulative number of cost-driven schemes.

[0103] Based on the travel distance cost (i.e., the Euclidean distance between the electric vehicle v and the charging station i), the charging currency cost, and the destination walking distance cost, a multi-objective cost allocation evaluation mechanism is established as follows:

[0104]

[0105] in, The overall objective function; All are preference weights; The cost is the distance traveled, i.e., the Euclidean distance between the electric vehicle v and the charging station i; The charging cost for charging station i; Cost of walking distance to the destination.

[0106] The distance traveled is calculated by obtaining the current location coordinates of the electric vehicle v in real time. and the coordinates of charging station i The calculation is performed using the following formula:

[0107]

[0108] Calculate the charging monetary cost using the rate table for charging station i. The calculation formula is as follows:

[0109]

[0110] in, For charging costs; Estimated charging amount (kWh) for electric vehicle v; Service fee (RMB).

[0111] Specifically, the cost of walking distance to the destination The calculation uses the method of straight-line distance × detour coefficient:

[0112]

[0113] in, Here are the latitude and longitude coordinates of charging station i; The coordinates of the user's destination are latitude and longitude; k represents the detour factor.

[0114] S3: Construct an optimal allocation model for electric vehicle charging stations. The optimal allocation model for electric vehicle charging stations includes minimizing the travel distance cost (i.e., the travel cost of the Euclidean distance between the current location of the electric vehicle and charging station i), the charging currency cost, and the destination walking distance cost as objective functions, and introduces power feasibility constraints.

[0115] The objective function is:

[0116]

[0117] To ensure that the vehicle's remaining battery power supports its journey to the charging station, a battery feasibility constraint is introduced, specifically:

[0118]

[0119] S4: A hybrid heuristic algorithm is used to solve the optimal allocation model for electric vehicle charging stations: an initial population is generated through a greedy random adaptive search, and a multi-parent crossover strategy or a targeted exchange strategy is dynamically executed based on the drivers' remaining time to output the optimal allocation scheme; the specific process is as follows:

[0120] S41: A greedy random adaptive search is used to generate the initial population, that is, for the current electric vehicle v, a restricted candidate list RCL is constructed from the corresponding set of candidate charging stations:

[0121]

[0122] Where RCL is the restricted candidate list; i represents electric vehicles; A collection of candidate charging stations; This corresponds to the minimum and maximum costs in the candidate charging station set (i.e., the charging monetary cost corresponding to each candidate charging station in the candidate charging station set). For greedy random coefficients, ;

[0123] S42: Determine the remaining computation time Is it greater than the upper bound of the calculation time? If yes, proceed to S43; if no, proceed to S44. In practice, the remaining computation time refers to the remaining time for the entire optimization problem, obtained by subtracting the current cumulative computation time from the set upper bound of the computation time. When time is sufficient ( > Global optimization (multi-parental crossover) is performed when time is insufficient. ≤ When an emergency strategy (directed exchange) is triggered.

[0124] S43: Perform multi-parental crossover operation ( That is, randomly selecting three paternal chromosome exchange feature segments, specifically:

[0125] S431: Randomly select three parent chromosomes Among them, the parent chromosome represents the complete charging station allocation scheme; chromosome: a complete solution vector that encodes the charging station selection scheme for all vehicles to be allocated; gene position: the corresponding vehicle index (e.g., position 1 = vehicle 1); gene value: the charging station ID allocated to this vehicle (e.g., gene value = 3 → allocated to charging station 3).

[0126] S432: Generate two random cutting points i, j (1≤i≤j≤N) v N v (This refers to the length of the chromosome, i.e., the total number of electric vehicles);

[0127] S433: Constructing offspring chromosomes Specifically:

[0128]

[0129] in, paternal chromosomes The gene segment numbered from s to e, that is, the gene segment on the chromosome from index s to e, represents a subset of the charging station allocation schemes for vehicles indexed from s to e, such as... paternal chromosomes The gene segment from index 1 to index i;

[0130] S434: Obtain the newly created offspring chromosome. Then, the offspring chromosomes Decode the offspring chromosomes; the decoded chromosomes represent the charging station allocation scheme.

[0131]

[0132] in, The decoded offspring chromosomes, i.e., the charging station allocation scheme; is the gene value of vehicle v in the offspring chromosome; N is the total number of charging stations in the region.

[0133] S44: Directed exchange operation ( When the remaining time is insufficient, it will forcibly switch to the nearest charging station, as detailed below:

[0134] S441: Calculate all blocking probability values ​​in the current solution; where, the current solution refers to the blocking probability value of the currently evaluated candidate allocation scheme (i.e., the vehicle-charging station mapping relationship after chromosome decoding). The formula for calculating the blocking probability value is as follows:

[0135]

[0136] S442: Determine whether the blocking probability value is greater than the preset blocking probability threshold: if yes, proceed to S443; if no, proceed to S444.

[0137] S443: If the charging station i corresponding to the congestion probability value is determined to be overloaded, that is, if the occupancy rate of charging station i is >80%, then for the electric vehicle v allocated to charging station i, retain the original set of candidate charging stations corresponding to electric vehicle v. Calculate the target charging station for emergency replacement Remove the original candidate charging station set Currently, the charging stations are overloaded. The nearest charging station in the European direction will be selected for forced allocation. This means unbinding electric vehicle v from the original overload charging station i and establishing a connection between electric vehicle v and the emergency replacement target charging station. The binding. Among them, emergency replacement of target charging stations. The calculation formula is:

[0138]

[0139] in, Let v be the Euclidean distance (in meters) from electric vehicle v to charging station k; k is the traversal index of the candidate charging stations in the candidate charging station set; v is the index of the vehicle to be reassigned. This represents the blocking probability value, i.e., the real-time load rate of charging station i. The preset blocking probability threshold, i.e. the overload threshold of the charging station, is set to 0.8 in this embodiment; For binary decision variables: This indicates that electric vehicle v is assigned to charging station i. This indicates that electric vehicle v has not been assigned to charging station i.

[0140] S444: Determine that the charging station i corresponding to the blockage probability value is not overloaded, and confirm that the binding relationship between electric vehicle v and charging station i is valid; if invalid, return to S441; if valid, keep the decision variable unchanged, i.e. The allocation is marked as a stable allocation and added to the final solution set. Then, the expected load growth rate of charging station i is calculated to realize real-time load rate monitoring and early warning, estimate vehicle arrival time, and update charging station status data.

[0141] The formula for calculating the expected load growth rate of charging station i is as follows:

[0142]

[0143] in, The expected load growth rate of charging station i; This represents the total number of charging piles at charging station i. This refers to the set of electric vehicles that have been allocated but have not yet arrived within the current time period; Charging stations for electric vehicles that have been allocated but not yet arrived;

[0144] Among them, the estimated vehicle arrival time The calculation formula is:

[0145]

[0146] in, Current system time; Vehicle-to-charging-station distance; Average driving speed.

[0147] Example 2

[0148] This embodiment provides an optimized allocation system for electric vehicle charging stations. The system executes the method described above, including:

[0149] Charging demand probability acquisition module: Based on the travel time of the driver of the electric vehicle to be charged, the charging cost, the number of available charging piles at the charging station, the comprehensive location of the charging station and the attractiveness of the charging station, it constructs a state transition matrix and generates a charging demand probability distribution in real time.

[0150] Multi-objective allocation cost evaluation mechanism construction module: used to calculate the reachable radius based on the remaining power and energy consumption rate of the electric vehicle to be charged, screen the candidate charging station set, integrate driver preference weights, and establish a multi-objective allocation cost evaluation mechanism;

[0151] The charging station allocation model set constraint module is used to construct an optimal allocation model for electric vehicle charging stations. The optimal allocation model for electric vehicle charging stations includes minimizing the driving distance cost, charging currency cost, and destination walking distance cost as objective functions and electricity feasibility constraints.

[0152] Charging station allocation scheme generation module: used to solve the optimal allocation model of electric vehicle charging stations: an initial population is generated through greedy random adaptive search, and a multi-parent crossover strategy or a directional exchange strategy is dynamically executed according to the driver's remaining time to output the corresponding optimal charging station allocation scheme.

[0153] Example 3

[0154] This embodiment provides a readable storage medium storing a computer program that, when invoked by a processor, performs the steps of the method described above.

[0155] Example 4

[0156] This embodiment provides an electronic terminal, including a processor and a memory, wherein the memory stores a computer program, and the processor calls the computer program to perform the steps of the method described above.

[0157] It should be understood that, in the embodiments of the present invention, the processor may be a Central Processing Unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor. The memory may include read-only memory and random access memory, and provides instructions and data to the processor. A portion of the memory may also include non-volatile random access memory. For example, the memory may also store device type information.

[0158] The readable storage medium is a computer-readable storage medium, which can be an internal storage unit of the controller described in any of the foregoing embodiments, such as the controller's hard drive or memory. The readable storage medium can also be an external storage device of the controller, such as a plug-in hard drive, Smart Media Card (SMC), Secure Digital (SD) card, or Flash Card equipped on the controller. Further, the readable storage medium can include both the controller's internal storage unit and external storage devices. The readable storage medium is used to store the computer program and other programs and data required by the controller. The readable storage medium can also be used to temporarily store data that has been output or will be output.

[0159] Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned readable storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0160] It is understood that the same or similar parts in the above embodiments can be referred to each other, and the contents not described in detail in some embodiments can be referred to the same or similar contents in other embodiments.

[0161] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. An optimized allocation method and system for electric vehicle charging stations, characterized in that, include: S1: Based on the travel time of the drivers of electric vehicles waiting to be charged, the charging cost, the number of available charging piles at the charging station, the comprehensive location of the charging station and the attractiveness of the charging station, construct a state transition matrix and generate a probability distribution of charging demand in real time. S2: Calculate the reachable radius based on the remaining power and energy consumption rate of the electric vehicle to be charged, screen the candidate charging station set, integrate driver preference weights, and establish a multi-objective allocation cost evaluation mechanism; S3: Construct an optimal allocation model for electric vehicle charging stations, wherein the optimal allocation model for electric vehicle charging stations includes minimizing the driving distance cost, charging currency cost and destination walking distance cost as objective functions and electricity feasibility constraints; S4: Solve the optimal allocation model for electric vehicle charging stations: Generate an initial population through a greedy random adaptive search, and dynamically execute a multi-parent crossover strategy or a directional exchange strategy based on the driver's remaining time to output the corresponding optimal charging station allocation scheme.

2. The method according to claim 1, characterized in that, The specific process of S1 is as follows: S11: Based on charging stations Service rating Convenience of transportation Calculate the attractiveness of charging stations The calculation formula is as follows: ； in, , All are weighting coefficients; Rate the service of charging station i; To improve the accessibility of charging station i; S12: Based on the attractiveness of the charging station Charging costs Calculate the achievement rate The calculation formula is as follows: ； in, This is the vehicle density coefficient for the area where the charging station is located. S13: Calculate the departure rate using the number of available charging piles at charging stations and the travel time of drivers of electric vehicles waiting to be charged. The calculation formula is as follows: ； in, Basic service rate; This represents the number of available charging stations. For travel time; S14: Construct the state transition matrix: ； in, Let be the system state transition matrix; The time step is denoted by m; m and n are both system states. M represents the real-time capacity status of charging station i; M represents the total number of charging piles in the charging station. S15: Generation of charging demand probability distribution: ； in, Let t be the expected probability that charging station i is counted as an overloaded station under the preset congestion conditions; Let be the steady-state probability distribution of charging station i at time t; This is an indicator function.

3. The method according to claim 1, characterized in that, The formula for calculating the reachable radius in S2 is as follows: ； in, The reachable radius; This is a preset upper limit for the reachable radius; The energy consumption rate of electric vehicles; This refers to the remaining battery power of the electric vehicle.

4. The method according to claim 1, characterized in that, The specific formula for the driver preference weights in S2 is as follows: ； in, Driver preference weights; To select the historical number of times the cost-dominant option of type k is chosen; Select the first charging record for the driver. The cumulative number of times the cost-dominant scheme was implemented.

5. The method according to claim 1, characterized in that, The multi-objective allocation cost evaluation mechanism in S2 is as follows: ； in, The overall objective function; All are preference weights; This refers to the cost of the driving distance, i.e., the distance between the vehicle and the charging station; The charging cost for charging station i; Cost of walking distance to the destination.

6. The method according to claim 5, characterized in that, The specific power availability constraints considered in the optimal allocation model for electric vehicle charging stations in S3 are as follows: .

7. The method according to claim 1, characterized in that, The specific process of S4 is as follows: S41: A greedy random adaptive search is used to generate the initial population, that is, for the current electric vehicle v, a restricted candidate list RCL is constructed from the corresponding set of candidate charging stations: ； Where RCL is the restricted candidate list; i represents electric vehicles; A collection of candidate charging stations; The corresponding values ​​are the minimum and maximum costs in the candidate charging station set; The coefficients are greedy random coefficients; S42: Determine the remaining computation time Is it greater than the upper bound of the calculation time? If yes, proceed to S43; if no, proceed to S44. S43: Perform multi-parental crossover operation ( That is, randomly select three parent chromosomes to exchange feature segments, construct offspring chromosomes, and decode the offspring chromosomes to obtain the charging station allocation scheme; S44: Directed exchange operation ( If there is insufficient time remaining, it will force a switch to the nearest charging station.

8. The method according to claim 7, characterized in that, The specific process of S43 is as follows: S431: Randomly select three parent chromosomes ; S432: Generate two random cutting points i and j, where 1≤i≤j≤N v N v The length of the chromosome; S433: Constructing offspring chromosomes : ； in, paternal chromosomes The gene segment numbered from s to e, i.e. the charging station allocation scheme for vehicle indexes from s to e; S434: Obtain the newly created offspring chromosome. Then, the offspring chromosomes Decode the offspring chromosomes; the decoded chromosomes represent the charging station allocation scheme. ； in, The decoded offspring chromosomes, i.e., the charging station allocation scheme; is the gene value of vehicle v in the offspring chromosome; N is the total number of charging stations in the region.

9. The method according to claim 7, characterized in that, Specifically, S44 becomes: S441: Calculate all blocking probability values ​​in the current solution, where the formula for calculating the blocking probability value is: ； S442: Determine whether the blocking probability value is greater than the preset blocking probability threshold: if yes, proceed to S443; if no, proceed to S444. S443: If the charging station i corresponding to the congestion probability value is determined to be overloaded, that is, if the occupancy rate of charging station i is >80%, then for the electric vehicle v allocated to charging station i, retain the original set of candidate charging stations corresponding to electric vehicle v. Calculate the target charging station for emergency replacement Remove the original candidate charging station set Currently, the charging stations in the middle are overloaded. The nearest charging station in the European direction will be selected for forced allocation. This means unbinding the electric vehicle v from the original overloaded charging station i, and establishing a connection between the electric vehicle v and the emergency replacement target charging station. The binding; S444: Determine that the charging station i corresponding to the blockage probability value is not overloaded, and confirm that the binding relationship between electric vehicle v and charging station i is valid; if invalid, return to S441; if valid, keep the decision variable unchanged, i.e. The allocation is marked as a stable allocation and added to the final solution set. Then, the expected load growth rate of charging station i is calculated, the vehicle arrival time is estimated, and the charging station status data is updated. The formula for calculating the expected load growth rate of charging station i is as follows: ； in, The expected load growth rate of charging station i; The total number of charging piles at charging station i; This refers to the set of electric vehicles that have been allocated but have not yet arrived within the current time period; Charging stations for electric vehicles that have been allocated but not yet arrived; Estimated vehicle arrival time The calculation formula is: ； in, Current system time; Travel distance cost, i.e., the distance between the vehicle and the charging station; Average driving speed.

10. An optimized allocation system for electric vehicle charging stations, the system executing the method according to any one of claims 1-9, characterized in that, include: Charging demand probability acquisition module: Based on the travel time of the driver of the electric vehicle to be charged, the charging cost, the number of available charging piles at the charging station, the comprehensive location of the charging station and the attractiveness of the charging station, it constructs a state transition matrix and generates a charging demand probability distribution in real time. Multi-objective allocation cost evaluation mechanism construction module: used to calculate the reachable radius based on the remaining power and energy consumption rate of the electric vehicle to be charged, screen the candidate charging station set, integrate driver preference weights, and establish a multi-objective allocation cost evaluation mechanism; The charging station allocation model set constraint module is used to construct an optimal allocation model for electric vehicle charging stations. The optimal allocation model for electric vehicle charging stations includes minimizing the driving distance cost, charging currency cost, and destination walking distance cost as objective functions and electricity feasibility constraints. Charging station allocation scheme generation module: used to solve the optimal allocation model of electric vehicle charging stations: an initial population is generated through greedy random adaptive search, and a multi-parent crossover strategy or a directional exchange strategy is dynamically executed according to the driver's remaining time to output the corresponding optimal charging station allocation scheme.

Images