Electric vehicle path planning method and system based on large-scale neighborhood search

Abstract

The invention provides an electric vehicle path planning method and system based on large-scale neighborhood search. According to the embodiment of the invention, power station insertion can be carried out at a plurality of insertion positions in reconstruction processing, so that the problem that the electric quantity constraint condition cannot be met when only a single power station is inserted is avoided, and the practicability of electric vehicle path planning is improved. According to the embodiment of the invention, a non-linear electric vehicle battery power consumption calculation mode is also used, so that battery behaviors in a real delivery scene can be well reflected, and electric vehicle route planning is more scientific and easier to implement. Besides, in the process of constructing the initial solution, all the client sites are subjected to priority ranking in advance, and it is ensured that the client sites with strict constraints can be preferentially served, so that the overall insertion efficiency of the client sites is improved, and the calculation time is saved.

Description

Technical Field

[0001] The present application relates to the technical field of vehicle routing problem (VRP), and in particular to a method and system for electric vehicle path planning based on large-scale neighborhood search (LNS). Background Art

[0002] With the introduction of carbon emission policies, more and more logistics companies need to replace fuel vehicles with electric vehicles (EVs) to carry out logistics and distribution tasks. Currently, there is a lack of widely recognized and widely adopted EV distribution planning solutions in the market.

[0003] Existing precise algorithms based on linear programming (LP) model the problem as an LP formula according to the branch-and-price framework and then solve it to obtain the VRP solution. However, these precise algorithms are computationally intensive and, in particular, inefficient when solving large-scale problems.

[0004] Existing genetic algorithms encode all problem instances (customer nodes, charging station nodes, etc.) and model vehicle journeys as code sequences to obtain an initial population. The optimization process involves crossover and mutation operations to change the sequence arrangement. However, genetic algorithms require full chromosome encoding during the initial population construction process, making it impossible to dynamically adjust the EV SoC under varying delivery conditions.

[0005] The existing route-first-cluster-second heuristic method first uses a traditional routing algorithm to form a large tour from the warehouse to all customers and then back to the warehouse. This tour is then optimally divided into a set of sub-vehicle routes, known as clusters, taking battery charging into account. This method relies on a large tour framework that does not consider battery status during the initial routing process. It assumes that customers close to each other are likely to be served within the same vehicle route. It only considers graph information to construct the large tour, ignoring non-graph information or constraints. This can lead to low clustering quality and impair subsequent optimization efficiency.

[0006] The prior art disassembly and reconstruction heuristic method is an extension of the LNS framework that considers both customer sites and power stations. In each iteration, the site selected in the previous round is deleted and inserted in a better location to reduce the total transportation cost. Currently, the prior art disassembly and reconstruction heuristic method does not usually differentiate between customer sites before building the initial solution, which may cause insertion failures and increase the number of search iterations. In addition, the prior art method may fail to repair infeasible paths during the reconstruction operation, resulting in an inability to solve the problem of infeasible paths. Therefore, the above method has the problem of low effectiveness. Summary of the Invention

[0007] At least one embodiment of the present application provides an electric vehicle path planning method and system based on large-scale neighborhood search, thereby improving the practicality of electric vehicle path planning.

[0008] According to a first aspect of the present application, at least one embodiment provides an electric vehicle path planning method based on large-scale neighborhood search, comprising:

[0009] Constructing an initial solution for electric vehicle routing, the initial solution comprising at least one delivery route, each delivery route comprising a station that the electric vehicle passes through in sequence, the stations comprising: a warehouse station, a customer station for loading and unloading goods, and a power station for charging and / or replacing batteries for the vehicle; wherein the warehouse station is the starting station for each delivery route;

[0010] The current solution of the electric vehicle path planning is subjected to multiple rounds of iterative optimization processes to obtain a final solution of the electric vehicle path planning, wherein the iterative optimization process includes: a first type of iterative optimization process that optimizes only the power station; in the first type of iterative optimization process, the current solution is disassembled and reconstructed in the following manner:

[0011] removing at least one power station from the delivery route, calculating the remaining power of the vehicle upon arrival at each station after the power station is removed, and filtering out infeasible routes that do not meet power constraint conditions; wherein the power constraint condition includes that the remaining power of the vehicle upon arrival at each station is positive;

[0012] Repeat at least one round of reconstruction for the infeasible path until the infeasible path satisfies the power constraint, and terminate the current round of iterative process after all infeasible paths satisfy the power constraint. Each round of reconstruction includes the following steps:

[0013] The position between each two adjacent stations in the first partial path is used as an insertion position. The first partial path is the path between the first station and the second station on the infeasible path. The first station is the first negative power station on the infeasible path, and the second station is the first power station or the warehouse station before the first station. The negative power station means that the calculated remaining power of the vehicle when arriving at the station is negative, and the positive power station means that the calculated remaining power of the vehicle when arriving at the station is not less than 0.

[0014] Performing the insertion process at each insertion position in order from back to front on the infeasible path until the first negative power site on the infeasible path is converted into a positive power site, wherein performing the insertion process at the current insertion position includes:

[0015] If there is a power station that is reachable by the vehicle at the current insertion location, insert a power station that is reachable by the vehicle;

[0016] If there is no power station that is reachable by the vehicle at the current insertion location, no power station is inserted.

[0017] Optionally, if there is a power station that is reachable by the vehicle at the current insertion location, inserting a power station that is reachable by the vehicle specifically includes:

[0018] For each power station that is reachable by the vehicle, calculate the increase in remaining power and the increase in transportation cost when the vehicle arrives at the first negative power station on the infeasible path after the power station is inserted at the current insertion position; based on the increase in remaining power and / or the increase in transportation cost corresponding to each power station, select a power station from the power stations that are reachable by the vehicle and insert it into the current insertion position.

[0019] Optionally, the first type of iterative optimization process is an iterative optimization process of a preset round in the multiple rounds of iterative processes.

[0020] Optionally, the iterative optimization process further includes: a second type of iterative optimization process for optimizing both the power station and the customer site, where the second type of iterative optimization process is an iterative optimization process in the multiple rounds of iterative processes except the first type of iterative optimization process.

[0021] Optionally, during the second type of iterative optimization process, the current solution is disassembled and reconstructed in the following manner:

[0022] removing at least one customer site from the delivery route;

[0023] Repeat the following steps until all customer sites have been inserted into the delivery route:

[0024] Determine whether there is a customer site that has not been inserted into the delivery path. If so, insert the customer site that has not been inserted into the delivery path into the delivery path, and determine whether the delivery path meets the power constraint condition after the customer site is inserted. If the power constraint condition is not met, insert a power station into the delivery path to make the delivery path meet the power constraint condition.

[0025] Optionally, construct an initial solution for electric vehicle path planning, including:

[0026] Calculate a score for the customer site based on the priority of the customer site, a first distance between the customer site and the warehouse site, a second distance between the customer site and the power station closest to the customer site, and a shortest time window for the customer site to receive service; wherein the score is positively correlated with the priority level, the first distance, and the second distance, and negatively correlated with the length of the shortest time window;

[0027] Each client site is inserted into the initial solution in order from largest to smallest score.

[0028] Optionally, calculate the customer site's score using the following formula:

[0029] S=c pri ×pri+c d ×(d d +d s )pri-c tw ×tw min

[0030] Among them, c pri 、c d 、c tw Respectively represent the preset coefficients of priority, distance, and shortest time window; pri, d d d s , tw min They respectively represent the priority, first distance, second distance, and length of the shortest time window of the client site.

[0031] Optionally, during the construction of the initial solution and during multiple rounds of iterative optimization of the initial solution, the power consumption between adjacent stations in the delivery path of the vehicle is calculated according to the following formula:

[0032] Δb=d×(1+pts load )

[0033] Where Δb represents the power consumption between adjacent stations in the delivery route, d represents the driving distance between the adjacent stations, pts load Indicates the vehicle load coefficient, which is positively correlated with the vehicle load, and pts loadGreater than 0 and not greater than 1.

[0034] According to a second aspect of the present application, at least one embodiment provides an electric vehicle path planning system based on large-scale neighborhood search, comprising:

[0035] An initial solution construction module, configured to construct an initial solution for electric vehicle route planning, the initial solution comprising at least one delivery route, each delivery route comprising a station that the electric vehicle passes through in sequence, the stations comprising: a customer station for loading and unloading goods, and a power station for charging and / or replacing batteries for the vehicle;

[0036] A solution optimization module is configured to perform multiple rounds of iterative optimization on the current solution of the electric vehicle path planning to obtain a final solution of the electric vehicle path planning, wherein the iterative optimization process includes: a first type of iterative optimization process that optimizes only the power station; in the first type of iterative optimization process, the current solution is disassembled and reconstructed in the following manner:

[0037] removing at least one power station from the delivery route, calculating the remaining power of the vehicle upon arrival at each station after the power station is removed, and filtering out infeasible routes that do not meet power constraint conditions; wherein the power constraint condition includes that the remaining power of the vehicle upon arrival at each station is positive;

[0038] Repeat at least one round of reconstruction for the infeasible path until the infeasible path satisfies the power constraint, and terminate the current round of iterative process after all infeasible paths satisfy the power constraint. Each round of reconstruction includes the following steps:

[0039] Starting from the first negative power station on the infeasible path, the position between each station and the adjacent previous station is used as an insertion position. A negative power station means that the calculated remaining power of the vehicle when arriving at the station is negative, and a positive power station means that the calculated remaining power of the vehicle when arriving at the station is not less than 0;

[0040] Performing the insertion process at each insertion position in order from back to front on the infeasible path until the first negative power site on the infeasible path is converted into a positive power site, wherein performing the insertion process at the current insertion position includes:

[0041] If there is a power station that is reachable by the vehicle at the current insertion location, insert a power station that is reachable by the vehicle;

[0042] If there is no power station that is reachable by the vehicle at the current insertion location, no power station is inserted.

[0043] According to the third aspect of the present application, at least one embodiment provides an electric vehicle path planning system based on large-scale neighborhood search, comprising a processor, a memory, and a program or instruction stored on the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the method described in any one of the first aspects.

[0044] According to the fourth aspect of the present application, at least one embodiment provides a computer-readable storage medium having a program stored thereon, and when the program is executed by a processor, the steps of any method of the first aspect are implemented.

[0045] According to a fifth aspect of the present application, at least one embodiment provides a computer program product, comprising computer instructions, which, when executed by a processor, implement the steps of the method described in any one of the first aspects.

[0046] Compared with the prior art, the electric vehicle path planning method and system based on large-scale neighborhood search provided by the embodiment of the present application can insert power stations at multiple insertion positions during the reconstruction process, thereby avoiding the problem that the power constraint conditions cannot be met when only a single power station is inserted, and improving the practicality of electric vehicle path planning. The embodiment of the present application also uses a nonlinear electric vehicle battery power consumption calculation method, which can well reflect the battery behavior in the real delivery scenario, making electric vehicle route planning more scientific and easier to implement. In addition, in the process of constructing the initial solution, the embodiment of the present application prioritizes all customer sites in advance to ensure that customer sites with strict constraints can be served first, thereby improving the overall insertion efficiency of customer sites and saving computing time. The electric vehicle path planning method of the embodiment of the present application, the construction of its initial solution depends on the customer site and battery station nodes, so that it can outperform the performance of the genetic algorithm of the prior art under the same computing conditions. In addition, compared with the traditional exact method, the meta-heuristic nature of the embodiment of the present application can achieve higher solution efficiency, especially when solving large-scale instances. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Various other advantages and benefits will become apparent to those skilled in the art upon reading the detailed description of the preferred embodiment below. The accompanying drawings are for illustration purposes only and are not to be considered as limiting the present application. The same reference symbols are used throughout the drawings to represent the same components. In the drawings:

[0048] Figure 1 A schematic diagram of a feasible tram delivery route according to an embodiment of the present application;

[0049] Figure 2-Figure 4 Example diagrams of removal and insertion operations at a customer site;

[0050] Figure 5-Figure 7 An example diagram of the removal and insertion operation of a power station;

[0051] Figure 8 This is a flowchart of an electric vehicle path planning method based on large-scale neighborhood search according to an embodiment of the present application;

[0052] Figure 9-10 This is an example diagram of the insertion position of an embodiment of the present application;

[0053] Figure 11 An example diagram of a power station inserted in an embodiment of the present application;

[0054] Figure 12 This is an example flow chart of the electric vehicle path planning method according to an embodiment of the present application;

[0055] Figure 13 A schematic structural diagram of an electric vehicle path planning system based on large-scale neighborhood search according to an embodiment of the present application;

[0056] Figure 14 This is another structural diagram of an electric vehicle path planning system based on large-scale neighborhood search according to an embodiment of the present application. DETAILED DESCRIPTION

[0057] The following describes exemplary embodiments of the present application in more detail with reference to the accompanying drawings. Although exemplary embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the present application and to fully convey the scope of the present application to those skilled in the art.

[0058] It should be understood that references throughout this specification to "one embodiment" or "an embodiment" mean that a particular feature, structure, or characteristic associated with the embodiment is included in at least one embodiment of the present application. Therefore, the appearance of "in one embodiment" or "in an embodiment" throughout this specification does not necessarily refer to the same embodiment. Furthermore, these particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. The terms "first," "second," and so on, used in the specification and claims of this application are used to distinguish similar items and are not necessarily used to describe a particular order or sequential sequence. It should be understood that such usage is interchangeable where appropriate, such that the embodiments of the present application described herein can, for example, be implemented in an order other than that illustrated or described herein. Furthermore, the terms "including," "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, product, or apparatus. The term "and / or" used in the specification and claims refers to at least one of the connected items.

[0059] In the various embodiments of the present application, it should be understood that the size of the serial numbers of the following processes does not mean 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 application.

[0060] The following description provides examples and does not limit the scope, applicability, or configuration set forth in the claims. Changes may be made to the function and arrangement of the elements discussed without departing from the spirit and scope of this disclosure. The various examples may appropriately omit, substitute, or add various procedures or components. For example, the described methods may be performed in an order different from that described, and various steps may be added, omitted, or combined. In addition, features described with reference to certain examples may be combined in other examples.

[0061] The final solution to a trolley delivery scheduling problem is a set of delivery routes, where each delivery route is a sequence of customer stations and power stations. After the vehicle arrives at the customer station, it loads and unloads the goods, and replenishes the remaining power by charging and / or swapping batteries at the power station. A feasible trolley delivery route is as follows: Figure 1 As shown, the white circle represents the customer site and the black circle represents the power station. Figure 1 In the example, the percentage of remaining power is used to represent the remaining power of the vehicle when it arrives at a certain station (arrival power) and the remaining power when it departs from the station (departure power). In the embodiment of the present application, the power station can be a charging station and / or a battery swap station.

[0062] The present invention provides an electric vehicle path planning method based on large-scale neighborhood search, which can improve the practicality of the electric vehicle path planning method. In the large-scale neighborhood search algorithm, iterative optimization is performed by destroying and recreating the solution. In the present invention, the solution destruction and reconstruction mainly includes four operations: customer site removal, customer site insertion, power station removal, and power station insertion.

[0063] Figure 2-Figure 4 An example of customer site removal and insertion operations is provided. In this example, a customer site C2 is first deleted from a feasible delivery path and then inserted back to a new location to reduce the total cost (such as the total mileage) and improve the solution quality. Figure 2 is a feasible delivery route. Figure 3 To remove customer site C2 between customer sites C1 and C3. Figure 4 In order to reinsert customer site C2 between customer sites C3 and C4, an improved feasible delivery path is obtained.

[0064] Figure 5-Figure 7 This example provides examples of power station removal and insertion. In this example, a power station S2 is removed from a feasible delivery route, and then another power station S1 is added back to the route. This reduces total cost (e.g., total mileage) and improves solution quality while still ensuring power availability. Figure 5 is a feasible delivery route. Figure 6 To remove the power station S2. Figure 7 To insert the power station S1 into the path.

[0065] Please refer to Figure 8 The electric vehicle path planning method based on large-scale neighborhood search provided in the embodiment of the present application includes the following steps:

[0066] Step 81, construct an initial solution for electric vehicle path planning, the initial solution includes at least one delivery path, each delivery path includes a station that the electric vehicle passes through in sequence, the stations include: warehouse stations, customer stations for loading and unloading goods, and power stations for charging and / or replacing batteries for vehicles; wherein the warehouse station is the starting station of each delivery path.

[0067] Here, the customer site information includes at least one of the following information: location information of the customer site, cargo delivery information of the customer site (for example, cargo information that needs to be loaded from the customer site and / or cargo information that needs to be unloaded to the customer site, and the cargo information may specifically include information such as the weight, volume and delivery requirements of the cargo), and a time window for the customer site to receive services (that is, the customer site hopes to obtain services within this time window).

[0068] In the embodiment of the present application, the fleet path can be planned based on the customer site information and power station information so that the planned path can meet the constraints, thereby obtaining the initial solution for the electric vehicle path planning. The constraints include: power constraint, load constraint, and service time constraint. Among them, the power constraint means that the remaining power of the vehicle before arriving at any station is not less than 0; the load constraint means that the load of the vehicle after loading and unloading goods at each customer station does not exceed the maximum load of the vehicle; the service time constraint means that the time when the customer station is served meets the time window requirement for the customer station to receive service.

[0069] In step 81, the construction of the initial solution specifically includes: selecting an unassigned vehicle in the fleet as the current vehicle, and commencing current path planning: inserting each unserved customer site into the current path corresponding to the current vehicle one by one, until inserting a customer site into the current path fails to satisfy the constraints, at which point the current path corresponding to the current vehicle is obtained; then, the above process is repeated until all vehicles have been assigned and / or all customer sites have been served. For more specific implementation methods of constructing the initial solution, reference may be made to relevant prior art, and this embodiment of the present application will not be further elaborated on.

[0070] In addition, when constructing the initial solution, no delivery routes have been constructed yet, and all customer sites are marked as "unserved." In the first iteration, customer sites are selected one by one and attempted to be inserted into the initial solution one by one to construct the initial vehicle delivery route. The order in which the next customer site to be inserted into the initial solution is selected directly affects the quality of the initial solution and the subsequent solution optimization process. In the embodiment of the present application, when inserting each unserved customer site into the current path corresponding to the current vehicle, a score for the customer site can be calculated based on the customer site's priority, the first distance between the customer site and the warehouse site, the second distance between the customer site and the power station closest to the customer site, and the shortest time window in which the customer site receives service. The score is positively correlated with the priority level, the first distance, and the second distance, and negatively correlated with the length of the shortest time window. Then, each customer site is inserted into the initial solution in descending order of the score until the constraint conditions are no longer satisfied after inserting a customer site into the current path.

[0071] As an example, the embodiment of the present application may calculate the score of the client site according to the following formula:

[0072] S=c pri ×pri+c d ×(d d +d s )pri-ctw ×tw min

[0073] Among them, c pri 、c d 、c tw Respectively represent the preset coefficients of priority, distance, and shortest time window; pri, d d d s , tw min They respectively represent the priority, first distance, second distance, and length of the shortest time window of the client site.

[0074] Generally, if a customer site has a higher priority, is farther away from the warehouse site and power station, and has a shorter serviceable time window, then the service conditions of the customer site are more stringent. In this embodiment of the application, a higher score is given to it so that it is inserted into the solution first, thereby improving the overall insertion efficiency of the customer site and saving calculation time.

[0075] Step 82: Perform multiple rounds of iterative optimization on the current solution of the electric vehicle path planning to obtain a final solution of the electric vehicle path planning. The iterative optimization process includes: a first type of iterative optimization process that optimizes only the power station; in the first type of iterative optimization process, the current solution is disassembled and reconstructed in the following manner:

[0076] removing at least one power station from the delivery route, calculating the remaining power of the vehicle upon arrival at each station after the power station is removed, and filtering out infeasible routes that do not meet power constraint conditions; wherein the power constraint condition includes that the remaining power of the vehicle upon arrival at each station is positive;

[0077] Repeat at least one round of reconstruction for the infeasible path until the infeasible path satisfies the power constraint, and terminate the current round of iterative process after all infeasible paths satisfy the power constraint. Each round of reconstruction includes the following steps:

[0078] The position between each two adjacent stations in the first partial path is used as an insertion position. The first partial path is the path between the first station and the second station on the infeasible path. The first station is the first negative power station on the infeasible path, and the second station is the first power station or the warehouse station before the first station. The negative power station means that the calculated remaining power of the vehicle when arriving at the station is negative, and the positive power station means that the calculated remaining power of the vehicle when arriving at the station is not less than 0.

[0079] Performing the insertion process at each insertion position in order from back to front on the infeasible path until the first negative power site on the infeasible path is converted into a positive power site, wherein performing the insertion process at the current insertion position includes:

[0080] If there is a power station that is reachable by the vehicle at the current insertion location, insert a power station that is reachable by the vehicle;

[0081] If there is no power station that is reachable by the vehicle at the current insertion location, no power station is inserted.

[0082] Here, the embodiment of the present application can perform multiple rounds of iterative optimization process, for example, perform 3000 rounds of iterative optimization process. The specific number of rounds can be set based on experience or computing resources and other factors.

[0083] The multi-round iterative optimization process specifically includes a first type of iterative optimization process and a second type of iterative optimization process. Among them, in the first type of iterative optimization process, only the power station in the current solution is optimized; in the second type of iterative optimization process, both the power station and the customer site are optimized. Specifically, the first type of iterative optimization process is an iterative optimization process of a preset round in the multi-round iterative process, and the second type of iterative optimization process is an iterative optimization process other than the first type of iterative optimization process in the multi-round iterative process. For example, it is pre-specified that the first type of iterative optimization process is executed once in every 50 rounds of iterative processes. In this way, the first type of iterative optimization process can be executed when the round of the current iterative process is an integer multiple of 50, otherwise, the second type of iterative optimization process is executed.

[0084] During each iteration, the current solution is usually subjected to a demolition process (ruin) and a reconstruction process (recreate).

[0085] The current solution of the electric vehicle path planning is optimized, and the initial value of the current solution is the initial solution of the electric vehicle path planning obtained in step 81. In subsequent iterations, the current solution is the solution obtained in the previous iteration.

[0086] As can be seen from the above steps, in the first type of iterative optimization process, the embodiment of the present application first performs a disassembly process. Specifically, the current solution may include one or more delivery routes, each of which corresponds to a station that an electric vehicle passes through in sequence. The stations passed by an electric vehicle generally include at least one customer station and n power stations, where n is greater than or equal to 0. At the power station, the vehicle can replenish energy through charging and / or battery replacement to increase the cruising range.

[0087] In each round of the first type of iteration, a disassembly process is first performed, and then at least one round of reconstruction is performed for each infeasible path, until all infeasible paths meet the power constraint condition, and then the iteration process ends. Specifically, it includes:

[0088] Step A: In the disassembly process, delete some power stations in all or part of the distribution paths in the current solution. After deleting the power stations, a distribution path may become an infeasible path. Here, an infeasible path means that the remaining power of the vehicle is negative when it arrives at at least one station in the distribution path. Although the remaining power of the battery will not be negative during actual transportation, for the sake of convenience of calculation, when calculating the remaining power of the vehicle arriving at a certain station, the embodiment of the present application directly subtracts the power required to travel to the station from the current power of the battery to obtain the remaining power of the vehicle arriving at a certain station. At this time, if the remaining power is negative, it means that the current power of the vehicle cannot travel to the station, and the distribution path is an infeasible path. At this time, the embodiment of the present application will record the negative power to evaluate the amount of power that the vehicle needs to replenish. In addition, based on whether the remaining power of the vehicle when it arrives at the station is negative, the station is divided into a negative power station and a positive power station.

[0089] Step B: During the current round of reconstruction for an infeasible path, the position between each two adjacent stations in the first portion of the path between the first and second stations is used as an insertion position. The first station is the first station with a negative charge on the infeasible path, and the second station is the first power station or the warehouse station before the first station. If there is a power station before the first station, the second station is the first power station before the first station; if there is no power station before the first station, the second station is the warehouse station, i.e., the starting station of the delivery path.

[0090] by Figure 9 and Figure 10 For example, the triangle represents the warehouse site, the white circle represents the customer site (indicated by the letter C in the figure), and the black circle represents the power station (indicated by the letter S in the figure). Figure 9 The infeasible path in the example starts from the warehouse, passes through C1, C2, C3, C4, C5, and then returns to the warehouse. Assuming that after leaving a power station, the remaining power of the vehicle at each station is represented by the percentage in the figure, it can be seen that Figure 9C4 in the figure is the first negative power station (-29% remaining power) on the infeasible path, i.e., C4 is the first station. Starting from C4, the search continues on the infeasible path to find the first power station, but no power stations are found. Therefore, the path between the warehouse station and C4 is used as the first partial path. The position between two adjacent nodes on the first partial path is an insertion position. Numbering them in order from back to front on the infeasible path, four insertion positions are obtained: the first insertion position between C3 and C4, the second insertion position between C2 and C3, the third insertion position between C1 and C2, and the fourth insertion position between the warehouse station and C1.

[0091] akin, Figure 10 In the figure, C4 is the first site. Starting from C4, the first power station is searched forward on the infeasible path. The first power station found is S2. Therefore, S2 is the second site. The path between S2 and C4 is taken as the first partial path. The position between two adjacent nodes on the first partial path is an insertion position. According to the order from back to front on the infeasible path, three insertion positions can be obtained, namely: the first insertion position between C3 and C4, the second insertion position between C2 and C3, and the third insertion position between S2 and C2.

[0092] Then, according to the order from back to front on the infeasible path, the insertion process is performed at each insertion position in turn until the first negative power station on the infeasible path is converted into a positive power station, wherein the insertion process at the current insertion position includes: (1) if there is a power station that is accessible to the vehicle at the current insertion position, insert a power station that is accessible to the vehicle; (2) if there is no power station that is accessible to the vehicle at the current insertion position, do not insert any power station. Then, it is determined whether the infeasible path meets the power constraint condition, that is, whether all stations on the infeasible path are positive power stations: if so, the reconstruction process of the current infeasible path is terminated and the reconstruction process of the next infeasible path is continued; if not, the insertion process is continued at the next insertion position, and so on, until the current infeasible path meets the power constraint condition.

[0093] Continue with Figure 9 For example, the embodiment of the present application attempts to insert a power station at the first insertion position, the second insertion position, the third insertion position, and the fourth insertion position. If a power station is inserted at the first insertion position, the first negative power station on the current infeasible path ( Figure 9If the current infeasible path is converted to a positive power site (C4), the current round of reconstruction processing is terminated, and it is determined whether the current infeasible path meets the power constraint condition, that is, all sites on the infeasible path are positive power sites: if so, at least one round of reconstruction processing is performed on the next infeasible path until all infeasible paths meet the power constraint condition; if not, the next round of reconstruction processing is continued for the current infeasible path. Please refer to step B above for the process of each round of reconstruction processing.

[0094] In the above-mentioned power station insertion process, in the embodiment of the present application, if a power station that is accessible to the vehicle exists at the current insertion location, the vehicle inserts into a power station that is accessible to the vehicle. Specifically, to determine whether there is a power station that is accessible to the vehicle at the current insertion location, the reachability of each power station can be determined based on whether the remaining power of the vehicle when it arrives at the station before the current insertion location is not less than the power required for the vehicle to travel from that station to the power station.

[0095] In the case where there are multiple power stations that are reachable by the vehicle at the current insertion position, the increase in the remaining power and the increase in the transportation cost when the vehicle arrives at the first negative power station on the infeasible path after the power station is inserted at the current insertion position can be calculated for each power station that the vehicle can reach; according to the increase in the remaining power and / or the increase in the transportation cost corresponding to each power station, a power station is selected from the power stations that the vehicle can reach and inserted into the current insertion position. The increase in the transportation cost can be calculated by comparing the increase in the driving distance and / or the increase in the driving time before and after the insertion of the power station. When considering multiple factors (such as the increase in the remaining power, the increase in the driving distance, and the increase in the driving time) to select the inserted power station, corresponding weights can be set for different factors, and then the factors can be comprehensively considered in combination with their respective weights. This embodiment of the present application does not specifically limit this. Of course, the embodiment of the present application can also select the power station with the largest increase in remaining power for insertion based only on the increase in the remaining power corresponding to each power station to simplify the insertion process.

[0096] Below is Figure 11 For example, Figure 9 The following examples all assume that the vehicle can fully charge its battery at each power station.

[0097] Assume that C4 is the first negative charge station on the infeasible path, and the vehicle's remaining charge at C4 is -29%. This example inserts at the first insertion location between C3 and C4, and calculates the remaining charge of the vehicle reaching C4 after inserting at the first insertion location. The results are assumed to be as follows:

[0098] a) The remaining power of the vehicle starting from C3 is enough to travel to the power station S1, and after being plugged into the power station S1, the remaining power of the vehicle arriving at the customer station C4 is -9%.

[0099] b) The remaining power of the vehicle starting from C3 is not enough to travel to the power station S2, so it is not considered to be inserted into S2.

[0100] c) The remaining power of the vehicle starting from C3 is not enough to travel to the power station S3, so it is not considered to be inserted into S3.

[0101] d) The remaining power of the vehicle starting from C3 is enough to travel to the power station S4, and after being plugged into the power station S4, the remaining power of the vehicle arriving at the customer station C4 is -20%.

[0102] Since the accessible power stations are S1 and S4, only S1 or S4 are considered. Assuming only the increase in the vehicle's remaining charge at C4 is considered, since the vehicle's remaining charge after S1 (-9%) is greater than the remaining charge after S4 (-20%), S1 is inserted at the first insertion position.

[0103] In addition, since the remaining power at the first station C4 is still negative after insertion S1, the power station insertion is continued at the second insertion position, and the insertion method is the same as the above process until the remaining power at the first station C4 is positive. After the remaining power at the first station C4 is positive, it can be further determined whether there are other stations on the infeasible path with negative remaining power when the vehicle arrives. If so, the above process is continued to determine the first station with negative power, and then insertion is performed at each insertion position until the remaining power of all stations on the infeasible path is greater than or equal to 0.

[0104] Through the above steps, the embodiment of the present application can insert power stations at multiple insertion positions during the reconstruction process, which can avoid the problem that the power constraint conditions cannot be met when only a single power station is inserted, and improve the practicality of electric vehicle path planning.

[0105] The iterative optimization process of the embodiment of the present application also includes a second type of iterative optimization process for optimizing power stations and customer sites. In the second type of iterative optimization process, the current solution of the electric vehicle path planning can be disassembled and reconstructed in the following manner:

[0106] Step a, removing at least one customer site in the delivery route;

[0107] Step b, repeat the following steps until all customer sites have been inserted into the delivery path: determine whether there is a customer site that has not been inserted into the delivery path; if so, insert the customer site that has not been inserted into the delivery path into the delivery path, and determine whether the delivery path meets the power constraint condition after the customer site is inserted; if the power constraint condition is not met, insert a power station into the delivery path to make the delivery path meet the power constraint condition.

[0108] Figure 12 An example diagram of a process of the electric vehicle path planning method according to an embodiment of the present application is given, which includes constructing an initial solution and a solution optimization process, and the solution optimization process includes first and second types of iterative optimization processes.

[0109] In addition, during the actual driving process of electric vehicles, the amount of electricity consumed is related to multiple factors such as the driving distance and the vehicle load, rather than just a linear multiple of the driving distance. The embodiment of the present application accepts any power consumption calculation method in the form of parameters. For example, during the construction of the initial solution and the process of performing multiple rounds of iterative optimization on the initial solution, the embodiment of the present application can calculate the power consumption between adjacent stations in the delivery path according to the following formula:

[0110] Δb=d×(1+pts load )

[0111] Where Δb represents the power consumption between adjacent stations in the delivery route, d represents the driving distance between the adjacent stations, pts load Indicates the vehicle load coefficient, which is positively correlated with the vehicle load, and pts load Greater than 0 and not greater than 1.

[0112] In the above manner, the embodiment of the present application calculates the battery power consumption through a scalable electric vehicle nonlinear estimation algorithm, which can better reflect the battery status in the actual delivery scenario and make the route planning of electric vehicles more scientific and easier to implement.

[0113] Please refer to Figure 13 The embodiment of the present application provides a structure of an electric vehicle path planning system based on large-scale neighborhood search, including:

[0114] An initial solution construction module 131 is configured to construct an initial solution for electric vehicle route planning, wherein the initial solution includes at least one delivery route, each delivery route including a station that the electric vehicle passes through in sequence, including: a customer station for loading and unloading goods, and a power station for charging and / or replacing batteries for the vehicle;

[0115] The solution optimization module 132 is configured to perform multiple rounds of iterative optimization on the current solution of the electric vehicle path planning to obtain a final solution of the electric vehicle path planning. The iterative optimization process includes: a first type of iterative optimization process that optimizes only the power station; in the first type of iterative optimization process, the current solution is disassembled and reconstructed in the following manner:

[0116] removing at least one power station from the delivery route, calculating the remaining power of the vehicle upon arrival at each station after the power station is removed, and filtering out infeasible routes that do not meet power constraint conditions; wherein the power constraint condition includes that the remaining power of the vehicle upon arrival at each station is positive;

[0117] Repeat at least one round of reconstruction for the infeasible path until the infeasible path satisfies the power constraint, and terminate the current round of iterative process after all infeasible paths satisfy the power constraint. Each round of reconstruction includes the following steps:

[0118] Starting from the first negative power station on the infeasible path, the position between each station and the adjacent previous station is used as an insertion position. A negative power station means that the calculated remaining power of the vehicle when arriving at the station is negative, and a positive power station means that the calculated remaining power of the vehicle when arriving at the station is not less than 0;

[0119] Performing the insertion process at each insertion position in order from back to front on the infeasible path until the first negative power site on the infeasible path is converted into a positive power site, wherein performing the insertion process at the current insertion position includes:

[0120] If there is a power station that is reachable by the vehicle at the current insertion location, insert a power station that is reachable by the vehicle;

[0121] If there is no power station that is reachable by the vehicle at the current insertion location, no power station is inserted.

[0122] Through the above modules, the embodiment of the present application can insert power stations at multiple insertion positions during the reconstruction process, which can avoid the problem that the power constraint conditions cannot be met when only a single power station is inserted, and improve the practicality of electric vehicle path planning.

[0123] Optionally, the solution optimization module 132 is further configured to, when a power station that is reachable by the vehicle exists at the current insertion position, insert a power station that is reachable by the vehicle, specifically including:

[0124] For each power station that is reachable by the vehicle, calculate the increase in remaining power and the increase in transportation cost when the vehicle arrives at the first negative power station on the infeasible path after the power station is inserted at the current insertion position; based on the increase in remaining power and / or the increase in transportation cost corresponding to each power station, select a power station from the power stations that are reachable by the vehicle and insert it into the current insertion position.

[0125] Optionally, the first type of iterative optimization process is an iterative optimization process of a preset round in the multiple rounds of iterative processes.

[0126] Optionally, the iterative optimization process further includes: a second type of iterative optimization process for optimizing both the power station and the customer site, where the second type of iterative optimization process is an iterative optimization process in the multiple rounds of iterative processes except the first type of iterative optimization process.

[0127] Optionally, the solution optimization module 132 is further configured to, during the second type of iterative optimization process, decompose and reconstruct the current solution in the following manner:

[0128] removing at least one customer site from the delivery route;

[0129] Repeat the following steps until all customer sites have been inserted into the delivery route:

[0130] Determine whether there is a customer site that has not been inserted into the delivery path. If so, insert the customer site that has not been inserted into the delivery path into the delivery path, and determine whether the delivery path meets the power constraint condition after the customer site is inserted. If the power constraint condition is not met, insert a power station into the delivery path to make the delivery path meet the power constraint condition.

[0131] Optionally, the initial solution construction module is further used to:

[0132] Calculate a score for the customer site based on the priority of the customer site, a first distance between the customer site and the warehouse site, a second distance between the customer site and the power station closest to the customer site, and a shortest time window for the customer site to receive service; wherein the score is positively correlated with the priority level, the first distance, and the second distance, and negatively correlated with the length of the shortest time window;

[0133] Each client site is inserted into the initial solution in order from largest to smallest score.

[0134] Optionally, the initial solution construction module is further configured to calculate the score of the client site according to the following formula:

[0135] S=c pri ×pri+c d×(d d +d s )pri-c tw ×tw min

[0136] Among them, c pri 、c d 、c tw Respectively represent the preset coefficients of priority, distance, and shortest time window; pri, d d d s , tw min They respectively represent the priority, first distance, second distance, and length of the shortest time window of the client site.

[0137] Optionally, the initial solution construction module is further configured to calculate the power consumption of the vehicle between adjacent stations in the delivery path according to the following formula during the construction of the initial solution, and the solution optimization module is further configured to calculate the power consumption of the vehicle between adjacent stations in the delivery path according to the following formula during the multiple rounds of iterative optimization of the initial solution:

[0138] Δb=d×(1+pts load )

[0139] Where Δb represents the power consumption between adjacent stations in the delivery route, d represents the driving distance between the adjacent stations, pts load Indicates the vehicle load coefficient, which is positively correlated with the vehicle load, and pts load Greater than 0 and not greater than 1.

[0140] It should be noted that the various systems provided in the above embodiments are devices corresponding to the above-mentioned electric vehicle path planning method based on large-scale neighborhood search. The implementation methods in the above-mentioned embodiments are all applicable to the embodiments of the device and can achieve the same technical effects. The above-mentioned device provided in the embodiments of the present application can implement all the method steps implemented in the above-mentioned method embodiments and can achieve the same technical effects. The parts and beneficial effects of this embodiment that are the same as those in the method embodiments will not be described in detail here.

[0141] Please refer to Figure 14 , a structural diagram of another electric vehicle path planning system based on large-scale neighborhood search provided in an embodiment of the present application, the device includes: a processor 1401, a transceiver 1402, a memory 1403, a user interface 1404 and a bus interface.

[0142] In the embodiment of the present application, the device further includes: a program stored in the memory 1403 and executable on the processor 1401 .

[0143] The transceiver 1402 is configured to send and receive data under the control of the processor;

[0144] The processor 1401 is configured to read the computer program in the memory and perform the following operations:

[0145] Constructing an initial solution for electric vehicle routing, the initial solution comprising at least one delivery route, each delivery route comprising a station that the electric vehicle passes through in sequence, the stations comprising: a warehouse station, a customer station for loading and unloading goods, and a power station for charging and / or replacing batteries for the vehicle; wherein the warehouse station is the starting station for each delivery route;

[0146] The current solution of the electric vehicle path planning is subjected to multiple rounds of iterative optimization processes to obtain a final solution of the electric vehicle path planning, wherein the iterative optimization process includes: a first type of iterative optimization process that optimizes only the power station; in the first type of iterative optimization process, the current solution is disassembled and reconstructed in the following manner:

[0147] removing at least one power station from the delivery route, calculating the remaining power of the vehicle upon arrival at each station after the power station is removed, and filtering out infeasible routes that do not meet power constraint conditions; wherein the power constraint condition includes that the remaining power of the vehicle upon arrival at each station is positive;

[0148] Repeat at least one round of reconstruction for the infeasible path until the infeasible path satisfies the power constraint, and terminate the current round of iterative process after all infeasible paths satisfy the power constraint. Each round of reconstruction includes the following steps:

[0149] The position between each two adjacent stations in the first partial path is used as an insertion position. The first partial path is the path between the first station and the second station on the infeasible path. The first station is the first negative power station on the infeasible path, and the second station is the first power station or the warehouse station before the first station. The negative power station means that the calculated remaining power of the vehicle when arriving at the station is negative, and the positive power station means that the calculated remaining power of the vehicle when arriving at the station is not less than 0.

[0150] Performing the insertion process at each insertion position in order from back to front on the infeasible path until the first negative power site on the infeasible path is converted into a positive power site, wherein performing the insertion process at the current insertion position includes:

[0151] If there is a power station that is reachable by the vehicle at the current insertion location, insert a power station that is reachable by the vehicle;

[0152] If there is no power station that is reachable by the vehicle at the current insertion location, no power station is inserted.

[0153] It is understandable that in the embodiment of the present application, when the computer program is executed by the processor 1401, each process of the above-mentioned electric vehicle path planning method embodiment based on large-scale neighborhood search can be implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0154] exist Figure 14 In the embodiment, the bus architecture may include any number of interconnected buses and bridges, specifically linking together various circuits of one or more processors represented by processor 1401 and memory represented by memory 1403. The bus architecture may also link together various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. The bus interface provides an interface. The transceiver 1402 may be a plurality of components, i.e., a transmitter and a receiver, providing a unit for communicating with various other devices on a transmission medium. For different user devices, the user interface 1404 may also be an interface capable of connecting external or internal devices as required, and the connected devices include but are not limited to a keypad, a display, a speaker, a microphone, a joystick, etc.

[0155] The processor 1401 is responsible for managing the bus architecture and general processing, and the memory 1403 can store data used by the processor 1401 when performing operations.

[0156] It should be noted that the device in this embodiment is a device corresponding to the above-mentioned electric vehicle path planning method based on large-scale neighborhood search, and the implementation methods in the above-mentioned embodiments are all applicable to the embodiments of the device, and can also achieve the same technical effects. In the device, the transceiver 1402 and the memory 1403, as well as the transceiver 1402 and the processor 1401 can be connected through a bus interface communication, the function of the processor 1401 can also be implemented by the transceiver 1402, and the function of the transceiver 1402 can also be implemented by the processor 1401. It should be noted that the above-mentioned device provided in the embodiment of the present application can implement all the method steps implemented in the above-mentioned method embodiment, and can achieve the same technical effects. The parts and beneficial effects that are the same as those in the method embodiment in this embodiment will not be specifically described here.

[0157] In some embodiments of the present application, a computer-readable storage medium is further provided, on which a program is stored. When the program is executed by a processor, the following steps are implemented:

[0158] Constructing an initial solution for electric vehicle routing, the initial solution comprising at least one delivery route, each delivery route comprising a station that the electric vehicle passes through in sequence, the stations comprising: a warehouse station, a customer station for loading and unloading goods, and a power station for charging and / or replacing batteries for the vehicle; wherein the warehouse station is the starting station for each delivery route;

[0159] The current solution of the electric vehicle path planning is subjected to multiple rounds of iterative optimization processes to obtain a final solution of the electric vehicle path planning, wherein the iterative optimization process includes: a first type of iterative optimization process that optimizes only the power station; in the first type of iterative optimization process, the current solution is disassembled and reconstructed in the following manner:

[0160] removing at least one power station from the delivery route, calculating the remaining power of the vehicle upon arrival at each station after the power station is removed, and filtering out infeasible routes that do not meet power constraint conditions; wherein the power constraint condition includes that the remaining power of the vehicle upon arrival at each station is positive;

[0161] Repeat at least one round of reconstruction for the infeasible path until the infeasible path satisfies the power constraint, and terminate the current round of iterative process after all infeasible paths satisfy the power constraint. Each round of reconstruction includes the following steps:

[0162] The position between each two adjacent stations in the first partial path is used as an insertion position. The first partial path is the path between the first station and the second station on the infeasible path. The first station is the first negative power station on the infeasible path, and the second station is the first power station or the warehouse station before the first station. The negative power station means that the calculated remaining power of the vehicle when arriving at the station is negative, and the positive power station means that the calculated remaining power of the vehicle when arriving at the station is not less than 0.

[0163] Performing the insertion process at each insertion position in order from back to front on the infeasible path until the first negative power site on the infeasible path is converted into a positive power site, wherein performing the insertion process at the current insertion position includes:

[0164] If there is a power station that is reachable by the vehicle at the current insertion location, insert a power station that is reachable by the vehicle;

[0165] If there is no power station that is reachable by the vehicle at the current insertion location, no power station is inserted.

[0166] When the program is executed by the processor, it can implement all the implementation methods of the above-mentioned electric vehicle path planning method based on large-scale neighborhood search, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0167] An embodiment of the present application also provides a computer program product, including computer instructions. When the computer instructions are executed by a processor, the various processes of the above-mentioned electric vehicle path planning method embodiment based on large-scale neighborhood search are implemented, and the same technical effects can be achieved. To avoid repetition, they are not described here.

[0168] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0169] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0170] In the embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0171] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of the present application.

[0172] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0173] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.

[0174] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A path planning method for electric vehicles based on large-scale neighborhood search, characterized in that: include: Constructing an initial solution for electric vehicle routing, the initial solution comprising at least one delivery route, each delivery route comprising a station that the electric vehicle passes through in sequence, the stations comprising: a warehouse station, a customer station for loading and unloading goods, and a power station for charging and / or replacing batteries for the vehicle; wherein the warehouse station is the starting station for each delivery route; Performing multiple rounds of iterative optimization on the current solution of the electric vehicle path planning to obtain a final solution of the electric vehicle path planning, the iterative optimization process including: a first type of iterative optimization process that optimizes only the power station; in the first type of iterative optimization process, the current solution is disassembled and rebuilt (i.e., ruin-recreate) in the following manner: removing at least one power station from the delivery route, calculating the remaining power of the vehicle upon arrival at each station after the power station is removed, and filtering out infeasible routes that do not meet power constraint conditions; wherein the power constraint condition includes that the remaining power of the vehicle upon arrival at each station is positive; Repeat at least one round of reconstruction for the infeasible path until the infeasible path satisfies the power constraint, and terminate the current round of iterative process after all infeasible paths satisfy the power constraint. Each round of reconstruction includes the following steps: The position between each two adjacent stations in the first partial path is used as an insertion position. The first partial path is the path between the first station and the second station on the infeasible path. The first station is the first negative power station on the infeasible path, and the second station is the first power station or the warehouse station before the first station. The negative power station means that the calculated remaining power of the vehicle when arriving at the station is negative, and the positive power station means that the calculated remaining power of the vehicle when arriving at the station is not less than 0. Performing the insertion process at each insertion position in order from back to front on the infeasible path until the first negative power site on the infeasible path is converted into a positive power site, wherein performing the insertion process at the current insertion position includes: If there is a power station that is reachable by the vehicle at the current insertion location, insert a power station that is reachable by the vehicle; If there is no power station that is reachable by the vehicle at the current insertion location, no power station is inserted.

2. The method according to claim 1, wherein If there is a power station that is accessible to the vehicle at the current insertion location, inserting a power station that is accessible to the vehicle includes: For each power station that is reachable by the vehicle, calculate the increase in remaining power and the increase in transportation cost when the vehicle arrives at the first negative power station on the infeasible path after the power station is inserted at the current insertion position; based on the increase in remaining power and / or the increase in transportation cost corresponding to each power station, select a power station from the power stations that are reachable by the vehicle and insert it into the current insertion position.

3. The method according to claim 1, wherein The first type of iterative optimization process is an iterative optimization process of a preset round in the multiple rounds of iterative processes.

4. The method according to claim 1, wherein The iterative optimization process further includes: a second type of iterative optimization process for optimizing both the power station and the customer site, wherein the second type of iterative optimization process is an iterative optimization process in the multiple-round iterative process except the first type of iterative optimization process.

5. The method according to claim 4, wherein In the second type of iterative optimization process, the current solution is disassembled and reconstructed in the following way: removing at least one customer site from the delivery route; Repeat the following steps until all customer sites have been inserted into the delivery route: Determine whether there is a customer site that has not been inserted into the delivery path. If so, insert the customer site that has not been inserted into the delivery path into the delivery path, and determine whether the delivery path meets the power constraint condition after the customer site is inserted. If the power constraint condition is not met, insert a power station into the delivery path to make the delivery path meet the power constraint condition.

6. The method according to claim 1, wherein Construct an initial solution for electric vehicle path planning, including: Calculate a score for the customer site based on the priority of the customer site, a first distance between the customer site and the warehouse site, a second distance between the customer site and the power station closest to the customer site, and a shortest time window for the customer site to receive service; wherein the score is positively correlated with the priority level, the first distance, and the second distance, and negatively correlated with the length of the shortest time window; Each client site is inserted into the initial solution in order from largest to smallest score.

7. The method according to claim 6, wherein The score of the client site is calculated according to the following formula: S=c pri ×pri+c d ×(d d +d s )pri-c tw ×tw min Among them, c pri 、c d 、c tw Respectively represent the preset coefficients of priority, distance, and shortest time window; pri, d d d s , tw min They respectively represent the priority, first distance, second distance, and length of the shortest time window of the client site.

8. The method according to claim 1, wherein During the construction of the initial solution and the multiple rounds of iterative optimization of the initial solution, the power consumption between adjacent stops on the delivery route is calculated according to the following formula: △b=d×(1+pts load ) Where Δb represents the power consumption between adjacent stations in the delivery route, d represents the driving distance between the adjacent stations, pts load Indicates the vehicle load coefficient, which is positively correlated with the vehicle load, and pts load Greater than 0 and not greater than 1.

9. An electric vehicle path planning system based on large-scale neighborhood search, characterized in that: include: An initial solution construction module, configured to construct an initial solution for electric vehicle route planning, the initial solution comprising at least one delivery route, each delivery route comprising a station that the electric vehicle passes through in sequence, the stations comprising: a customer station for loading and unloading goods, and a power station for charging and / or replacing batteries for the vehicle; A solution optimization module is configured to perform multiple rounds of iterative optimization on the current solution of the electric vehicle path planning to obtain a final solution of the electric vehicle path planning, wherein the iterative optimization process includes: a first type of iterative optimization process that optimizes only the power station; in the first type of iterative optimization process, the current solution is disassembled and reconstructed in the following manner: removing at least one power station from the delivery route, calculating the remaining power of the vehicle upon arrival at each station after the power station is removed, and filtering out infeasible routes that do not meet power constraint conditions; wherein the power constraint condition includes that the remaining power of the vehicle upon arrival at each station is positive; Repeat at least one round of reconstruction for the infeasible path until the infeasible path satisfies the power constraint, and terminate the current round of iterative process after all infeasible paths satisfy the power constraint. Each round of reconstruction includes the following steps: Starting from the first negative power station on the infeasible path, the position between each station and the adjacent previous station is used as an insertion position. A negative power station means that the calculated remaining power of the vehicle when arriving at the station is negative, and a positive power station means that the calculated remaining power of the vehicle when arriving at the station is not less than 0; Performing the insertion process at each insertion position in order from back to front on the infeasible path until the first negative power site on the infeasible path is converted into a positive power site, wherein performing the insertion process at the current insertion position includes: If there is a power station that is reachable by the vehicle at the current insertion location, insert a power station that is reachable by the vehicle; If there is no power station that is reachable by the vehicle at the current insertion location, no power station is inserted.

10. A computer program product, characterized in that The method comprises computer instructions, which, when executed by a processor, implement the steps of the method according to any one of claims 1 to 8.

Images