CN112541627B - Method, device and equipment for planning path and optimizing performance of electric logistics vehicle - Google Patents

Method, device and equipment for planning path and optimizing performance of electric logistics vehicle Download PDF

Info

Publication number
CN112541627B
CN112541627B CN202011438086.8A CN202011438086A CN112541627B CN 112541627 B CN112541627 B CN 112541627B CN 202011438086 A CN202011438086 A CN 202011438086A CN 112541627 B CN112541627 B CN 112541627B
Authority
CN
China
Prior art keywords
path
sub
logistics vehicle
paths
electric
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202011438086.8A
Other languages
Chinese (zh)
Other versions
CN112541627A (en
Inventor
徐冠奇
金忠孝
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Secco Intelligent Technology Shanghai Co ltd
Original Assignee
Secco Intelligent Technology Shanghai Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Secco Intelligent Technology Shanghai Co ltd filed Critical Secco Intelligent Technology Shanghai Co ltd
Priority to CN202011438086.8A priority Critical patent/CN112541627B/en
Publication of CN112541627A publication Critical patent/CN112541627A/en
Application granted granted Critical
Publication of CN112541627B publication Critical patent/CN112541627B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
    • G06Q10/083—Shipping
    • G06Q10/0835—Relationships between shipper or supplier and carriers
    • G06Q10/08355—Routing methods
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/10—Internal combustion engine [ICE] based vehicles
    • Y02T10/40—Engine management systems

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Marketing (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Development Economics (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Game Theory and Decision Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Electric Propulsion And Braking For Vehicles (AREA)

Abstract

The application discloses a method, a device and equipment for planning a path and optimizing performance of an electric logistics vehicle, and aims to solve the problem that an optimal path cannot be obtained simultaneously and accurately at present and performance of the electric logistics vehicle is optimized. Firstly, acquiring logistics data of an electric logistics vehicle; and inputting the data into a pre-constructed electric logistics vehicle optimization model, carrying out comprehensive iterative processing on path planning optimization of the electric logistics vehicle and performance parameter optimization of the electric logistics vehicle according to a plurality of groups of co-evolution genetic algorithms, guiding the design of the performance of the electric logistics vehicle by data generated in the path optimization process of the electric logistics vehicle, and re-planning an optimal path through new performance parameters of the electric logistics vehicle, so that the two can be mutually promoted and respectively reach the optimal in the co-evolution process.

Description

Method, device and equipment for planning path and optimizing performance of electric logistics vehicle
Technical Field
The application relates to the technical field of intelligent logistics, in particular to a method, a device and equipment for planning a path and optimizing performance of an electric logistics vehicle.
Background
With the development of electronic commerce, the application of logistics services in the life of people is becoming wider and wider. Meanwhile, in order to save fuel energy, the electric logistics vehicles are increasingly used for replacing the traditional fuel logistics vehicles to carry out logistics transportation so as to reduce transportation energy consumption and transportation cost, and on the basis, how to reasonably plan the logistics paths of the electric logistics vehicles so as to meet the logistics transportation requirements of logistics companies and users is very important.
At present, in the path planning of the electric logistics vehicle, the influence of charging equipment and charging characteristics of the electric vehicle on the path planning is not considered, but the charging equipment and the charging characteristics of the electric vehicle have important influence in the driving mileage supplementation of the electric vehicle, and if the charging equipment and the charging characteristics of the electric vehicle are not considered, the obtained path has larger deviation from the actual optimal path. In addition, when the conventional electric logistics vehicle performs logistics path planning, only how to select the path as short as possible is considered, and no optimization measures are provided for the electric logistics vehicle body. However, considering that the electric logistics vehicle is still an emerging product, there are still some unreasonable points in design, so how to optimize the vehicle performance index in combination with the service requirement while optimizing the logistics path has high guiding significance on the design and manufacture of the subsequent electric logistics vehicle.
Disclosure of Invention
The main purpose of the embodiment of the application is to provide a method, a device and equipment for planning and optimizing the performance of an electric logistics vehicle, which can adopt an iterative evolutionary strategy between the optimization of the logistics path and the performance design of the electric logistics vehicle, so as to achieve the cooperative optimization between the path planning and the performance of the electric logistics vehicle.
The embodiment of the application provides a method for planning a path and optimizing performance of an electric logistics vehicle, which comprises the following steps:
acquiring logistics data of the electric logistics vehicle; the logistics data comprise operation data and logistics business data of the electric logistics vehicle;
inputting the logistics data of the electric logistics vehicle into a pre-constructed electric logistics vehicle optimization model, and initializing a path corresponding to a first sub-group and a path corresponding to a second sub-group according to a plurality of group co-evolution genetic algorithms;
evaluating, crossing and mutating the paths corresponding to the first sub-group by using a first objective function to obtain a first optimized path; evaluating, crossing and mutating the paths corresponding to the second sub-group by using a second objective function to obtain a second optimized path; the first objective function is a function representing the driving range of the electric logistics vehicle; the second objective function is a weighted function representing the driving distance supplementing speed and the life loss degree of the electric logistics vehicle;
when the iteration number of the electric logistics vehicle optimization model reaches a preset value, the first sub-population and the second sub-population are combined, and the combined paths are evaluated by utilizing a third objective function, so that paths meeting preset conditions are determined from the first optimization path and the second optimization path according to an evaluation result.
In one possible implementation, the method further includes:
and inserting a charging station into the first optimized path and/or the second optimized path to charge the electric logistics vehicle.
In one possible implementation, the method further includes:
selecting the first N sub-paths with highest occurrence frequency from the first optimized path and the second optimized path, wherein N is a positive integer greater than 0;
randomly breaking and reconstructing the first N sub-paths, and inserting the obtained reconstructed sub-paths into the first optimized path and the second optimized path;
when the iteration number of the electric logistics vehicle optimization model reaches a preset value, merging the first sub-group and the second sub-group, and evaluating the merged paths by using a third objective function, so as to determine paths meeting preset conditions from the first optimization path and the second optimization path according to an evaluation result, wherein the method comprises the following steps:
when the iteration number of the electric logistics vehicle optimization model reaches a preset value, combining the first optimization path and the second optimization path inserted with the reconstructed sub-paths, and evaluating the combined paths by using a third objective function to determine paths meeting preset conditions from the combined paths according to an evaluation result.
In one possible implementation manner, after the acquiring the logistics data of the electric logistics vehicle, the method further includes
Cleaning abnormal data in the logistics data to obtain cleaned logistics data;
carrying out standardization processing on the cleaned logistics data, and determining data within a preset threshold range from the processed logistics data;
the step of inputting the logistics data of the electric logistics vehicle into a pre-constructed electric logistics vehicle optimization model, and initializing a path corresponding to a first sub-group and a path corresponding to a second sub-group according to a plurality of group co-evolution genetic algorithms, comprises the following steps:
inputting the data which is determined from the processed logistics data and is within a preset threshold range into a pre-constructed electric logistics vehicle optimization model, and initializing a path corresponding to a first sub-group and a path corresponding to a second sub-group according to a plurality of group co-evolution genetic algorithms.
In one possible implementation manner, the electric logistics vehicle optimization model is trained by using a fourth objective function, wherein the fourth objective function is used for representing the minimum value of the sum of the travel distance of the electric logistics vehicle and the cost consumed by charging the electric logistics vehicle.
The embodiment of the application also provides an electric logistics vehicle path planning and performance optimizing device, which comprises:
the acquisition unit is used for acquiring logistics data of the electric logistics vehicle; the logistics data comprise operation data and logistics business data of the electric logistics vehicle;
the input unit is used for inputting the logistics data of the electric logistics vehicle into a pre-constructed electric logistics vehicle optimization model, and initializing a path corresponding to the first sub-group and a path corresponding to the second sub-group according to a plurality of group co-evolution genetic algorithms;
the obtaining unit is used for evaluating, crossing and mutating the paths corresponding to the first sub-group by using a first objective function to obtain a first optimized path; evaluating, crossing and mutating the paths corresponding to the second sub-group by using a second objective function to obtain a second optimized path; the first objective function is a function representing the driving range of the electric logistics vehicle; the second objective function is a weighted function representing the driving distance supplementing speed and the life loss degree of the electric logistics vehicle;
and the determining unit is used for merging the first sub-group and the second sub-group when the iteration number of the electric logistics vehicle optimization model reaches a preset value, and evaluating the merged paths by utilizing a third objective function so as to determine paths meeting preset conditions from the first optimization path and the second optimization path according to an evaluation result.
In one possible implementation, the apparatus further includes:
the first inserting unit is used for inserting a charging station into the first optimized path and/or the second optimized path to charge the electric logistics vehicle.
In one possible implementation, the apparatus further includes:
a selecting unit, configured to select the first N sub-paths with the highest occurrence frequency from the first optimized path and the second optimized path, where N is a positive integer greater than 0;
the second inserting unit is used for randomly breaking and reconstructing the first N sub-paths and inserting the obtained reconstructed sub-paths into the first optimized path and the second optimized path;
the determining unit is specifically configured to:
when the iteration number of the electric logistics vehicle optimization model reaches a preset value, combining the first optimization path and the second optimization path inserted with the reconstructed sub-paths, and evaluating the combined paths by using a third objective function to determine paths meeting preset conditions from the combined paths according to an evaluation result.
In one possible implementation, the apparatus further includes:
the cleaning unit is used for cleaning abnormal data in the logistics data to obtain cleaned logistics data;
The processing unit is used for carrying out standardized processing on the cleaned logistics data and determining data within a preset threshold range from the processed logistics data;
the input unit is specifically configured to:
inputting the data which is determined from the processed logistics data and is within a preset threshold range into a pre-constructed electric logistics vehicle optimization model, and initializing a path corresponding to a first sub-group and a path corresponding to a second sub-group according to a plurality of group co-evolution genetic algorithms.
In one possible implementation manner, the electric logistics vehicle optimization model is trained by using a fourth objective function, wherein the fourth objective function is used for representing the minimum value of the sum of the travel distance of the electric logistics vehicle and the cost consumed by charging the electric logistics vehicle.
The embodiment of the application also provides an electric logistics vehicle path planning and performance optimizing device, which comprises: a processor, memory, system bus;
the processor and the memory are connected through the system bus;
the memory is configured to store one or more programs, the one or more programs comprising instructions, which when executed by the processor, cause the processor to perform any one of the implementations of the electric logistics vehicle path planning and performance optimization methods described above.
The embodiment of the application also provides a computer readable storage medium, wherein the computer readable storage medium stores instructions, and when the instructions run on the terminal equipment, the terminal equipment is caused to execute any implementation mode of the electric logistics vehicle path planning and performance optimizing method.
The embodiment of the application provides a method, a device and equipment for planning a path and optimizing performance of an electric logistics vehicle, which firstly acquire logistics data of the electric logistics vehicle; the logistics data comprise operation data and logistics business data of the electric logistics vehicle; inputting logistics data of the electric logistics vehicle into a pre-constructed electric logistics vehicle optimization model, and initializing a path corresponding to the first sub-group and a path corresponding to the second sub-group according to a plurality of group co-evolution genetic algorithms; then, evaluating, crossing and mutating the paths corresponding to the first sub-group and the paths corresponding to the second sub-group by using the first objective function and the second objective function respectively to obtain a first optimized path and a second optimized path; wherein the first objective function is a function representing the driving range of the electric logistics vehicle; the second objective function is a weighted function representing the driving distance supplementing speed and the life loss degree of the electric logistics vehicle; and when the iteration number of the electric logistics vehicle optimization model reaches a preset value, merging the first sub-group and the second sub-group, and evaluating the merged paths by using a third objective function to determine paths meeting preset conditions from the merged paths according to an evaluation result.
Therefore, in the embodiment of the application, the path planning optimization of the electric logistics vehicle and the performance parameter optimization of the electric logistics vehicle are subjected to comprehensive iteration processing according to the multiple swarm co-evolution genetic algorithm by utilizing the pre-constructed electric logistics vehicle optimization model, the data generated in the path optimization process of the electric logistics vehicle are used for guiding the design of the performance of the electric logistics vehicle, and the optimal path is re-planned through the new performance parameters of the electric logistics vehicle, so that the path planning optimization and the performance parameter optimization of the electric logistics vehicle are mutually promoted, and the optimal performance parameters of the electric logistics vehicle are respectively achieved in the co-evolution process.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, and it is obvious that the drawings in the following description are some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of an electric logistics vehicle path planning and performance optimizing method provided in an embodiment of the present application;
fig. 2 is a flowchart of acquiring logistics data of an electric logistics vehicle according to an embodiment of the present application;
Fig. 3 is a flowchart of processing logistics data of an electric logistics vehicle according to an embodiment of the present application;
fig. 4 is a schematic diagram of initializing a vehicle driving path according to an embodiment of the present application;
fig. 5 is a schematic diagram of a reconstructed vehicle driving path according to an embodiment of the present application;
fig. 6 is a schematic diagram of a path planning and performance optimizing device for an electric logistics vehicle according to an embodiment of the present application.
Detailed Description
At present, although electric logistics vehicles are increasingly adopted to replace traditional fuel logistics vehicles for logistics transportation, current logistics service providers generally still use a dispatching mode of the traditional fuel logistics vehicles, namely, electric logistics vehicles with one or more specifications are purchased in a unified way, certain routing dispatching is carried out on the electric logistics vehicles, and goods flowing from a warehouse or a distribution center to customers are realized within a specified service time window. For the electric logistics vehicle, performance indexes such as a continuous voyage mileage, an optimal charge remaining capacity interval, battery performance decay along with temperature, available charging equipment power and the like are directly related to scheduling, and if the parameters are not taken into consideration, a calculated scheduling scheme cannot meet the limit condition of a distribution task or has a great margin for optimization. Therefore, how to optimize the vehicle performance index in combination with the business requirement while optimizing the logistics path has high guiding significance on the design and manufacture of the subsequent electric logistics vehicle
In order to solve the above-mentioned defect, the embodiment of the application provides a route planning and performance optimizing method of an electric logistics vehicle, firstly, logistics data of the electric logistics vehicle are obtained; the logistics data comprise operation data and logistics business data of the electric logistics vehicle; inputting logistics data of the electric logistics vehicle into a pre-constructed electric logistics vehicle optimization model, and initializing a path corresponding to the first sub-group and a path corresponding to the second sub-group according to a plurality of group co-evolution genetic algorithms; then, evaluating, crossing and mutating the paths corresponding to the first sub-group and the paths corresponding to the second sub-group by using the first objective function and the second objective function respectively to obtain a first optimized path and a second optimized path; wherein the first objective function is a function representing the driving range of the electric logistics vehicle; the second objective function is a weighted function representing the driving distance supplementing speed and the life loss degree of the electric logistics vehicle; and when the iteration number of the electric logistics vehicle optimization model reaches a preset value, merging the first sub-group and the second sub-group, and evaluating the merged paths by using a third objective function to determine an optimal path meeting preset conditions from the merged paths according to an evaluation result.
Therefore, in the embodiment of the application, the path planning optimizing of the electric logistics vehicle and the performance parameter optimizing of the electric logistics vehicle are subjected to comprehensive iteration processing according to the multi-group co-evolution genetic algorithm by utilizing the pre-constructed electric logistics vehicle optimizing model, the data generated in the path optimizing process of the electric logistics vehicle are used for guiding the design of the performance of the electric logistics vehicle, and the optimal path is re-planned through the performance parameters of the new electric logistics vehicle, so that the path planning optimizing and the performance parameter optimizing of the electric logistics vehicle can be mutually promoted, and the optimal performance parameter of the electric logistics vehicle can be respectively achieved in the co-evolution process.
For the purposes of making the objects, technical solutions and advantages of the embodiments of the present application more clear, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.
First embodiment
Referring to fig. 1, a schematic flow chart of a method for planning a path and optimizing performance of an electric logistics vehicle according to the present embodiment is provided, and the method includes the following steps:
S101: acquiring logistics data of the electric logistics vehicle; the logistics data comprise operation data and logistics business data of the electric logistics vehicle.
In the embodiment, in order to realize iterative improvement of both optimal path planning and performance parameter design of the electric logistics vehicle, the cooperative optimization between the path planning and performance of the electric logistics vehicle is achieved. First, the logistics data of the electric logistics vehicle needs to be acquired to execute the following step S102.
The logistics data comprise operation data and logistics business data of the electric logistics vehicle. As shown in fig. 2, the operation data of the electric current car may include a remaining power, a charging voltage, a number of times of daily charging, a daily travel distance, etc. when the electric current car enters a station to be charged. The service data of the electric logistics vehicle can comprise the vehicle load, the vehicle loading volume and the like.
In one possible implementation manner of this embodiment, in order to improve accuracy of the logistics data, after the logistics data of the electric logistics vehicle is obtained, abnormal data in the logistics data is further required to be cleaned, so as to obtain cleaned logistics data, and then the cleaned logistics data is subjected to standardization processing, and data within a preset threshold range is determined from the processed logistics data, so as to execute a subsequent step S102. Specifically, the method comprises the following steps (1) - (7):
Step (1): in this implementation manner, after the logistics data of the electric logistics vehicle is obtained, firstly, abnormal values need to be removed from each data feature, and normalization is performed, that is, the data mean value of each feature is 1, and the variance is 1.
Step (2): will add threshold F α F value when α=0.05, and deletion threshold F α F value when α=0.2.
Step (3): the operation cost of the electric logistics vehicle is set as a dependent variable Y, and the independent variable characteristic is { X ] 1 ，X 2 ，...，X r Selecting the most relevant independent variable characteristic according to the Pearson correlation coefficientThe statistical data is used for linear fitting, and the specific fitting formula is as follows:
wherein the F-test is used for testingIf the F value is greater than F α The variables were considered significant. If->Not significant, do not include->Model y=β0+epsilon is the best model and the algorithm ends; if it is significant, add it to the model, enter the follow-upAnd (4) a step (4).
Step (4): checking first-order bias correlation coefficientj+.i1 finds the variable with the largest partial correlation coefficientThe statistical data is used for linear fitting, and the specific fitting formula is as follows:
at the same time, get the target hypothesis H 0 ：Test statistics of->And for hypothesis H 0 ：/>Test statistics of->
Step (5): comparison of And a deletion threshold F α F value when set to α=0.2 (this time is defined as F r ). If F S <F r Reject F from model S And (3) corresponding to the variables, returning to the execution step (3), and reselecting the variables for fitting. If F S >F r The new equation is defined as the above equation (2), and the step (4) is executed back, and the partial correlation coefficient used in the F test becomesj≠i 1 ,i 2 。
Step (6): the addition and deletion of arguments is repeated until all features are verified. And outputting a variable and a coefficient, wherein the variable represents the most relevant characteristic for the operation cost of the electric logistics vehicle, and the coefficient represents the relative importance degree of the characteristics.
The final output results indicate which parts are most required to be subjected to design optimization, so as to provide guidance for optimizing the performance parameters of the electric logistics vehicle.
S102: and inputting the logistics data of the electric logistics vehicle into a pre-constructed electric logistics vehicle optimization model, and initializing a path corresponding to the first sub-group and a path corresponding to the second sub-group according to a plurality of group co-evolution genetic algorithms.
It should be noted that, in order to realize the iterative improvement of the optimal path planning and the performance parameter design of the electric logistics vehicle, the cooperative optimization between the path planning and the performance of the electric logistics vehicle is achieved. In this embodiment, an electric logistics vehicle optimization model is pre-built, and an optional implementation manner is that the electric logistics vehicle optimization model is obtained by training a fourth objective function, where the fourth objective function is used to represent a minimum value of a sum of a driving distance of the electric logistics vehicle and a cost consumed by charging the electric logistics vehicle.
Specifically, first, parameters need to be defined, in this implementation, j and k are defined as two customer numbers to be serviced, E is a vehicle number of the distribution center, E is a set of all available vehicles in the fleet, and C is a set of customers and warehouses. Then c can be utilized jk Representing the travel distance from customer j to customer k; by means ofRepresenting the cost (e.g., consumed power germany) required to charge from customer j to customer k; by t jk Representing the travel time from customer j to customer k; by s j Representing the service time allocated to customer j; by d j Representing the demand of customer j (e.g., the amount of goods delivered or the number of orders scheduled, etc.); let Ye denote the maximum load of the vehicle e; benefit (benefit)By g j Representing the earliest time allowed to reach customer j; let hj denote the latest time allowed to reach customer j; by r e Representing the maximum travel time of the vehicle e; using a ej Representing the time when vehicle e arrives at customer j; by->Indicating whether the vehicle is charged when running from customer j to customer k, charging takes 1, otherwise taking 0; by z ejk Indicating that 1 is taken when vehicle e is assigned to travel from customer j to customer k; otherwise take 0, so the fourth objective function of the model can be defined as: / >
Specific constraints may include, among others: each customer is limited to only receive one service of one vehicle, i.e.,∑ k∈C z e0k ＝1,/> the total demand of the customer on a defined route must not exceed the maximum load of the vehicle, i.e./>The conservation of traffic is defined, i.e., the number of times (i.e., frequency) that vehicles enter and leave the node is equal for each node; defining that the time when the vehicle reaches the customer must fall within a given time window, i.e. +.>Wherein w is j Representing a vehicle waiting time; defining a maximum operating time of the vehicle, i.e. +.>Wherein w is k Representing a vehicle waiting time; the total travel distance of the vehicle is limited to be within the electric quantity allowable range, i.e./>Wherein D is e Representing the maximum driving distance of the vehicle e, +.>Representing the power of the charging device selected on the path from customer j to customer k,indicating the charge time on the path from customer j to customer k.
In this way, after the logistics data (preferably, the logistics data after the washing and standardization process) of the electric logistics vehicle is obtained in step S101, the logistics data may be further input into the electric logistics vehicle optimization model constructed in advance, and the path corresponding to the first sub-group and the path corresponding to the second sub-group may be initialized according to the multiple-group co-evolution genetic algorithm.
Specifically, the first and second sub-groups contain two gene segments. As shown in fig. 4, the length of the gene segment a is the number of electric logistics vehicles available in the warehouse, and each gene location indicates the number of customers visited by each vehicle; the length of the gene segment B is the number of customers, and indicates the order of accessing customers. In generating the actual path, the number of visiting customers is allocated to each car according to the gene segment a, and the number of visiting customers and the order of visiting the car are decided according to the gene segment B. Thus, the paths corresponding to the first sub-population and the paths corresponding to the second sub-population can be initialized according to the multiple population co-evolution genetic algorithm. For example, as shown in fig. 4, the vehicle travel path generated from two gene segments is: 0-3-2-1-0,0-10-5-4-8-7-0,0-11-12-9-6-0 (wherein 0 represents a warehouse).
S103: evaluating, crossing and mutating the paths corresponding to the first sub-group by using a first objective function to obtain a first optimized path; evaluating, crossing and mutating the paths corresponding to the second sub-group by using a second objective function to obtain a second optimized path; wherein the first objective function is a function representing the driving range of the electric logistics vehicle; the second objective function is a weighted function representing the range supplement speed and the degree of life loss of the electric logistics vehicle.
In this embodiment, after initializing the path corresponding to the first sub-group and the path corresponding to the second sub-group in step S102, the path corresponding to the first sub-group may be further evaluated, crossed and mutated by using the first objective function to obtain a first optimized path, as shown in fig. 3. The first objective function is a function representing the driving mileage of the electric logistics vehicle, and the specific formula is as follows:
that is, before the iteration number of the electric logistics vehicle optimization model reaches a preset value, the path corresponding to the first sub-group can be evaluated according to the total driving range, and it is noted that the driving range does not consider the extra driving range caused by the charging at the station.
Meanwhile, the second objective function may be further used to evaluate, cross, and mutate the paths corresponding to the second sub-group, so as to obtain a second optimized path, as shown in fig. 3. The second objective function is a function representing the driving mileage of the electric logistics vehicle, and the specific formula is as follows:
wherein the charge costThe method consists of two parts of weighting: firstly, the life of the electric vehicle is damaged by charging, if a piezoelectric pile is used as C 1 If a high-voltage pile is used, the pile is 1.5C 1 The method comprises the steps of carrying out a first treatment on the surface of the Secondly, for charging, the distance from node j to the charging station, and the distance from the charging station to node k.
Further, not only the objective function is required to be used for evaluation, but also crossover and mutation operations can be performed. And for Two different types of gene segments contained in the Two sub-groups, different operators are used for processing, specifically, for the gene segment a shown in fig. 4, two-point crossover (Two-point crossover) and Uniform mutation (mutation) may be used for processing, and for the gene segment B shown in fig. 4, partial matching crossover (PMX) and shift picture (Shuffle index mutation) may be used for processing, so as to obtain a first optimized path and a second optimized path.
On the basis, an alternative implementation manner is that after the crossover and mutation, a charging station can be inserted into the first optimized path and/or the second optimized path to charge the electric logistics vehicle.
Specifically, in the present implementation, firstly, all generated routes are evaluated based on a saving algorithm, and if a certain route is not feasible in the driving distance of the electric vehicle, a node with the waiting time greater than 0 is searched between customer nodes with the driving distance of 20-80% of the maximum driving distance ratio, and a charging station with the minimum cost increase is tried to be inserted by the comprehensive distance and the charging power; then, if the charging station is inserted, the charging station is still insufficient in the mileage supplemented for the electric vehicle in the available time (constrained by the latest arrival time of the next node) to complete the distribution task, and the insertion operation is repeated; and if the charging station is inserted, the supplementary mileage is enough to complete the distribution task, and the insertion operation is exited; then, if no node with waiting time longer than 0 exists in the interval of 20-80% of the maximum mileage relative to the maximum mileage ratio, the route is split, the second sub-route which is split is put into a new route, and then the insertion position and charging time of the charging station and the travel distance from the last node to the charging station and from the charging station to the next node can be recorded, so that the insertion operation of the charging station is completed.
Further, in one possible implementation manner of this embodiment, in order to determine the optimal path, the first N sub-paths with the highest occurrence frequency may be selected from the first optimal path and the second optimal path, where N is a positive integer greater than 0; then, the first N sub-paths are randomly broken and reconstructed, and the obtained reconstructed sub-paths are inserted into the first optimized path and the second optimized path to replace part of the sub-paths. As shown in fig. 5, for the selected sub-path 0-5-4-7-0, after random disruption and reconstruction, a new sub-path is obtained as follows: 3-5-4-0-0, which can be inserted into the first optimized path and the second optimized path by means of charging insertion, for performing the subsequent step S104.
S104: when the iteration number of the electric logistics vehicle optimization model reaches a preset value, the first sub-population and the second sub-population are combined, and the combined paths are evaluated by utilizing a third objective function, so that paths meeting preset conditions are determined from the first optimization path and the second optimization path according to an evaluation result.
In this embodiment, when the number of iterations of the electric current vehicle optimization model reaches a preset value, the first sub-population and the second sub-population may be further combined, as shown in fig. 3, and the combined paths are evaluated by using a third objective function, where, in order to enable the obtained individuals (transmission paths between customers) to satisfy the time constraint, the following penalty term is applied to each individual:
Further, each of the obtained merged paths may be evaluated using a third objective function as shown below, specifically:
fitness1+fitness2+(0.5×t) 2 ×penatly (6)
where t represents the number of iterations. Thus, as the iteration proceeds, constraints are progressively applied to ensure that a viable solution (i.e., a viable path) that satisfies the time constraint can be obtained. And stopping iteration until the iteration times reach a given preset value or meet a convergence condition, and outputting a recorded historical optimal solution, namely outputting an optimal path meeting the preset condition.
In summary, in the method for planning a path and optimizing performance of an electric logistics vehicle provided in this embodiment, logistics data of the electric logistics vehicle is first obtained; the logistics data comprise operation data and logistics business data of the electric logistics vehicle; inputting logistics data of the electric logistics vehicle into a pre-constructed electric logistics vehicle optimization model, and initializing a path corresponding to the first sub-group and a path corresponding to the second sub-group according to a plurality of group co-evolution genetic algorithms; then, evaluating, crossing and mutating the paths corresponding to the first sub-group and the paths corresponding to the second sub-group by using the first objective function and the second objective function respectively to obtain a first optimized path and a second optimized path; wherein the first objective function is a function representing the driving range of the electric logistics vehicle; the second objective function is a weighted function representing the driving distance supplementing speed and the life loss degree of the electric logistics vehicle; and when the iteration number of the electric logistics vehicle optimization model reaches a preset value, merging the first sub-group and the second sub-group, and evaluating the merged paths by using a third objective function to determine paths meeting preset conditions from the merged paths according to an evaluation result.
Therefore, in the embodiment of the application, the path planning optimizing of the electric logistics vehicle and the performance parameter optimizing of the electric logistics vehicle are subjected to comprehensive iteration processing according to the multi-group co-evolution genetic algorithm by utilizing the pre-constructed electric logistics vehicle optimizing model, the data generated in the path optimizing process of the electric logistics vehicle are used for guiding the design of the performance of the electric logistics vehicle, the optimal path is re-planned through the performance parameters of the new electric logistics vehicle, and the two paths are mutually promoted to be optimal in the co-evolution process.
Second embodiment
The embodiment will be described with reference to an electric logistics vehicle path planning and performance optimizing device, and the related content refers to the above method embodiment.
Referring to fig. 6, a schematic composition diagram of an electric logistics vehicle path planning and performance optimizing apparatus provided in this embodiment, the apparatus 600 includes:
an acquiring unit 601, configured to acquire logistics data of an electric logistics vehicle; the logistics data comprise operation data and logistics business data of the electric logistics vehicle;
the input unit 602 is configured to input the logistics data of the electric logistics vehicle to a pre-constructed electric logistics vehicle optimization model, and initialize a path corresponding to the first sub-population and a path corresponding to the second sub-population according to a plurality of population co-evolution genetic algorithms;
An obtaining unit 603, configured to perform evaluation, crossover and mutation operations on the paths corresponding to the first sub-group by using a first objective function, so as to obtain a first optimized path; evaluating, crossing and mutating the paths corresponding to the second sub-group by using a second objective function to obtain a second optimized path; the first objective function is a function representing the driving range of the electric logistics vehicle; the second objective function is a weighted function representing the driving distance supplementing speed and the life loss degree of the electric logistics vehicle;
and the determining unit 604 is configured to combine the first sub-population and the second sub-population when the iteration number of the electric logistics vehicle optimization model reaches a preset value, and evaluate the combined paths by using a third objective function, so as to determine a path that meets a preset condition from the first optimization path and the second optimization path according to an evaluation result.
In one implementation of this embodiment, the apparatus further includes:
the first inserting unit is used for inserting a charging station into the first optimized path and/or the second optimized path to charge the electric logistics vehicle.
In one implementation of this embodiment, the apparatus further includes:
a selecting unit, configured to select the first N sub-paths with the highest occurrence frequency from the first optimized path and the second optimized path, where N is a positive integer greater than 0;
the second inserting unit is used for randomly breaking and reconstructing the first N sub-paths and inserting the obtained reconstructed sub-paths into the first optimized path and the second optimized path;
the determining unit 604 is specifically configured to:
when the iteration number of the electric logistics vehicle optimization model reaches a preset value, combining the first optimization path and the second optimization path inserted with the reconstructed sub-paths, and evaluating the combined paths by using a third objective function to determine paths meeting preset conditions from the combined paths according to an evaluation result.
In one implementation of this embodiment, the apparatus further includes:
the cleaning unit is used for cleaning abnormal data in the logistics data to obtain cleaned logistics data;
the processing unit is used for carrying out standardized processing on the cleaned logistics data and determining data within a preset threshold range from the processed logistics data;
The input unit 602 is specifically configured to:
inputting the data which is determined from the processed logistics data and is within a preset threshold range into a pre-constructed electric logistics vehicle optimization model, and initializing a path corresponding to a first sub-group and a path corresponding to a second sub-group according to a plurality of group co-evolution genetic algorithms.
In one implementation manner of this embodiment, the electric logistics vehicle optimization model is trained by using a fourth objective function, where the fourth objective function is used to represent a minimum value of a sum of a driving distance of the electric logistics vehicle and a cost consumed by charging the electric logistics vehicle.
In summary, in the path planning and performance optimizing device for the electric logistics vehicle provided in this embodiment, logistics data of the electric logistics vehicle is first obtained; the logistics data comprise operation data and logistics business data of the electric logistics vehicle; inputting logistics data of the electric logistics vehicle into a pre-constructed electric logistics vehicle optimization model, and initializing a path corresponding to the first sub-group and a path corresponding to the second sub-group according to a plurality of group co-evolution genetic algorithms; then, evaluating, crossing and mutating the paths corresponding to the first sub-group and the paths corresponding to the second sub-group by using the first objective function and the second objective function respectively to obtain a first optimized path and a second optimized path; wherein the first objective function is a function representing the driving range of the electric logistics vehicle; the second objective function is a weighted function representing the driving distance supplementing speed and the life loss degree of the electric logistics vehicle; and when the iteration number of the electric logistics vehicle optimization model reaches a preset value, merging the first sub-group and the second sub-group, and evaluating the merged paths by using a third objective function to determine paths meeting preset conditions from the merged paths according to an evaluation result.
Therefore, in the embodiment of the application, the path planning optimizing of the electric logistics vehicle and the performance parameter optimizing of the electric logistics vehicle are subjected to comprehensive iteration processing according to the multi-group co-evolution genetic algorithm by utilizing the pre-constructed electric logistics vehicle optimizing model, the data generated in the path optimizing process of the electric logistics vehicle are used for guiding the design of the performance of the electric logistics vehicle, the optimal path is re-planned through the performance parameters of the new electric logistics vehicle, and the two paths are mutually promoted to be optimal in the co-evolution process.
Further, the embodiment of the application also provides an electric logistics vehicle path planning and performance optimizing device, which comprises: a processor, memory, system bus;
the processor and the memory are connected through the system bus;
the memory is for storing one or more programs, the one or more programs comprising instructions, which when executed by the processor, cause the processor to perform any of the implementations of the electric logistics vehicle path planning and performance optimization methods described above.
Further, the embodiment of the application also provides a computer readable storage medium, wherein the computer readable storage medium stores instructions, and when the instructions run on a terminal device, the terminal device is caused to execute any implementation method of the electric logistics vehicle path planning and performance optimizing method.
Further, the embodiment of the application also provides a computer program product, which when run on a terminal device, causes the terminal device to execute any implementation method of the electric logistics vehicle path planning and performance optimization method.
From the above description of embodiments, it will be apparent to those skilled in the art that all or part of the steps of the above described example methods may be implemented in software plus necessary general purpose hardware platforms. Based on such understanding, the technical solutions of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a storage medium, such as a ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, a server, or a network communication device such as a media gateway, etc.) to perform the methods described in the embodiments or some parts of the embodiments of the present application.
It should be noted that, in the present description, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different manner from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
It is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims (6)

1. The method for planning the path and optimizing the performance of the electric logistics vehicle is characterized by comprising the following steps of:
acquiring logistics data of the electric logistics vehicle; the logistics data comprise operation data and logistics business data of the electric logistics vehicle;
inputting the logistics data of the electric logistics vehicle into a pre-constructed electric logistics vehicle optimization model, and initializing a path corresponding to a first sub-group and a path corresponding to a second sub-group according to a plurality of group co-evolution genetic algorithms;
evaluating, crossing and mutating the paths corresponding to the first sub-group by using a first objective function to obtain a first optimized path; evaluating, crossing and mutating the paths corresponding to the second sub-group by using a second objective function to obtain a second optimized path; the first objective function is a function representing the driving range of the electric logistics vehicle; the second objective function is a weighted function representing the driving distance supplementing speed and the life loss degree of the electric logistics vehicle;
when the iteration number of the electric logistics vehicle optimization model reaches a preset value, combining the first sub-family group with the second sub-family group, and evaluating the combined paths by using a third objective function to determine paths meeting preset conditions from the first optimization path and the second optimization path according to an evaluation result;
Selecting the first N sub-paths with highest occurrence frequency from the first optimized path and the second optimized path, wherein N is a positive integer greater than 0;
randomly breaking and reconstructing the first N sub-paths, and inserting the obtained reconstructed sub-paths into the first optimized path and the second optimized path to replace part of sub-paths;
when the iteration number of the electric logistics vehicle optimization model reaches a preset value, merging the first sub-group and the second sub-group, and evaluating the merged paths by using a third objective function, so as to determine paths meeting preset conditions from the first optimization path and the second optimization path according to an evaluation result, wherein the method comprises the following steps:
when the iteration number of the electric logistics vehicle optimization model reaches a preset value, combining the first optimization path and the second optimization path inserted with the reconstructed sub-paths, and evaluating the combined paths by using a third objective function to determine paths meeting preset conditions from the combined paths according to an evaluation result;
wherein in order to enable the resulting individual, i.e. the transmission path between customers, to meet the time constraint, the following penalty term is applied to each individual:
Further, each of the obtained merged paths may be evaluated using a third objective function as shown below, specifically:
fitness1+fitness2+(0.5×t) 2 ×penatly
wherein t represents the iteration number, e is the vehicle number of the distribution center, j is the customer needing serviceHousehold number, a j Indicating the time when the vehicle arrives at customer j, h j Representing the latest time allowed to reach customer j, fitness1 is the first objective function, fitness2 is the second objective function, and penatly is the penalty term;
cleaning abnormal data in the logistics data to obtain cleaned logistics data;
carrying out standardization processing on the cleaned logistics data, and determining data within a preset threshold range from the processed logistics data;
the step of inputting the logistics data of the electric logistics vehicle into a pre-constructed electric logistics vehicle optimization model, and initializing a path corresponding to a first sub-group and a path corresponding to a second sub-group according to a plurality of group co-evolution genetic algorithms, comprises the following steps:
inputting the data which is determined from the processed logistics data and is within a preset threshold range into a pre-constructed electric logistics vehicle optimization model, and initializing a path corresponding to a first sub-group and a path corresponding to a second sub-group according to a plurality of group co-evolution genetic algorithms;
The electric logistics vehicle optimization model is trained by adopting a fourth objective function, and the fourth objective function is used for representing the minimum value of the sum of the running distance of the electric logistics vehicle and the cost consumed by charging the electric logistics vehicle.
2. The method according to claim 1, wherein the method further comprises:
and inserting a charging station into the first optimized path and/or the second optimized path to charge the electric logistics vehicle.
3. An electric logistics vehicle path planning and performance optimizing device, which is characterized by comprising:
the acquisition unit is used for acquiring logistics data of the electric logistics vehicle; the logistics data comprise operation data and logistics business data of the electric logistics vehicle;
the input unit is used for inputting the logistics data of the electric logistics vehicle into a pre-constructed electric logistics vehicle optimization model, and initializing a path corresponding to the first sub-group and a path corresponding to the second sub-group according to a plurality of group co-evolution genetic algorithms;
the obtaining unit is used for evaluating, crossing and mutating the paths corresponding to the first sub-group by using a first objective function to obtain a first optimized path; evaluating, crossing and mutating the paths corresponding to the second sub-group by using a second objective function to obtain a second optimized path; the first objective function is a function representing the driving range of the electric logistics vehicle; the second objective function is a weighted function representing the driving distance supplementing speed and the life loss degree of the electric logistics vehicle;
The determining unit is used for merging the first sub-group and the second sub-group when the iteration number of the electric logistics vehicle optimization model reaches a preset value, and evaluating the merged paths by utilizing a third objective function so as to determine paths meeting preset conditions from the first optimization path and the second optimization path according to an evaluation result;
a selecting unit, configured to select the first N sub-paths with the highest occurrence frequency from the first optimized path and the second optimized path, where N is a positive integer greater than 0;
the second inserting unit is used for randomly breaking and reconstructing the first N sub-paths, inserting the obtained reconstructed sub-paths into the first optimized path and the second optimized path, and replacing part of sub-paths;
the determining unit is specifically configured to:
when the iteration number of the electric logistics vehicle optimization model reaches a preset value, combining the first optimization path and the second optimization path inserted with the reconstructed sub-paths, and evaluating the combined paths by using a third objective function to determine paths meeting preset conditions from the combined paths according to an evaluation result;
Wherein in order to enable the resulting individual, i.e. the transmission path between customers, to meet the time constraint, the following penalty term is applied to each individual:
further, each of the obtained merged paths may be evaluated using a third objective function as shown below, specifically:
fitness1+fitness2+(0.5×t) 2 ×penatly
wherein t represents the iteration number, e is the vehicle number of the distribution center, j is the customer number of the service, a j Indicating the time when the vehicle arrives at customer j, h j Representing the latest time allowed to reach customer j, fitness1 is the first objective function, fitness2 is the second objective function, and penatly is the penalty term;
the cleaning unit is used for cleaning abnormal data in the logistics data to obtain cleaned logistics data;
the processing unit is used for carrying out standardized processing on the cleaned logistics data and determining data within a preset threshold range from the processed logistics data;
the input unit is specifically configured to:
inputting the data which is determined from the processed logistics data and is within a preset threshold range into a pre-constructed electric logistics vehicle optimization model, and initializing a path corresponding to a first sub-group and a path corresponding to a second sub-group according to a plurality of group co-evolution genetic algorithms;
The electric logistics vehicle optimization model is trained by adopting a fourth objective function, and the fourth objective function is used for representing the minimum value of the sum of the running distance of the electric logistics vehicle and the cost consumed by charging the electric logistics vehicle.
4. A device according to claim 3, characterized in that the device further comprises:
the first inserting unit is used for inserting a charging station into the first optimized path and/or the second optimized path to charge the electric logistics vehicle.
5. An electric logistics vehicle path planning and performance optimizing device, comprising: a processor, memory, system bus;
the processor and the memory are connected through the system bus;
the memory is for storing one or more programs, the one or more programs comprising instructions, which when executed by the processor, cause the processor to perform the method of any of claims 1-2.
6. A computer readable storage medium, characterized in that the computer readable storage medium has stored therein instructions, which when run on a terminal device, cause the terminal device to perform the method of any of claims 1-2.
CN202011438086.8A 2020-12-10 2020-12-10 Method, device and equipment for planning path and optimizing performance of electric logistics vehicle Active CN112541627B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011438086.8A CN112541627B (en) 2020-12-10 2020-12-10 Method, device and equipment for planning path and optimizing performance of electric logistics vehicle

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011438086.8A CN112541627B (en) 2020-12-10 2020-12-10 Method, device and equipment for planning path and optimizing performance of electric logistics vehicle

Publications (2)

Publication Number Publication Date
CN112541627A CN112541627A (en) 2021-03-23
CN112541627B true CN112541627B (en) 2023-08-01

Family

ID=75019914

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011438086.8A Active CN112541627B (en) 2020-12-10 2020-12-10 Method, device and equipment for planning path and optimizing performance of electric logistics vehicle

Country Status (1)

Country Link
CN (1) CN112541627B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113780676B (en) * 2021-09-23 2023-06-23 河南科技大学 Method for optimizing distribution path of bottled liquefied gas vehicle

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107909228A (en) * 2017-12-23 2018-04-13 深圳大学 Based on mould because of the dynamic vehicle shipping and receiving paths planning method and device of calculating
CN109978274A (en) * 2019-04-02 2019-07-05 海南阿凡题科技有限公司 Dispatch the planing method in path
CN110097234A (en) * 2019-05-13 2019-08-06 江苏中烟工业有限责任公司 Industrial cigarette transport intelligent dispatching method and system

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9536192B2 (en) * 2014-06-23 2017-01-03 International Business Machines Corporation Solving vehicle routing problems using evolutionary computing techniques
CN108776612A (en) * 2018-04-11 2018-11-09 深圳大学 A kind of cloud computing method for allocating tasks, device, equipment and storage medium

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107909228A (en) * 2017-12-23 2018-04-13 深圳大学 Based on mould because of the dynamic vehicle shipping and receiving paths planning method and device of calculating
CN109978274A (en) * 2019-04-02 2019-07-05 海南阿凡题科技有限公司 Dispatch the planing method in path
CN110097234A (en) * 2019-05-13 2019-08-06 江苏中烟工业有限责任公司 Industrial cigarette transport intelligent dispatching method and system

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
联网中物流配送车辆调度目标定位设计与仿真;冯亮等;《计算机仿真》;20170415(第04期);全文 *

Also Published As

Publication number Publication date
CN112541627A (en) 2021-03-23

Similar Documents

Publication Publication Date Title
Alba et al. Computing nine new best-so-far solutions for capacitated VRP with a cellular genetic algorithm
Koch et al. Route-based approximate dynamic programming for dynamic pricing in attended home delivery
Li et al. A multiagent deep reinforcement learning based approach for the optimization of transformer life using coordinated electric vehicles
Gupta et al. A generic framework for multi-criteria decision support in eco-friendly urban logistics systems
Dimitrov et al. Reinforcement learning based algorithm for the maximization of EV charging station revenue
CN112541627B (en) Method, device and equipment for planning path and optimizing performance of electric logistics vehicle
Prencipe et al. A mathematical programming model for optimal fleet management of electric car-sharing systems with vehicle-to-grid operations
Hu et al. Dynamic rebalancing optimization for bike-sharing system using priority-based MOEA/D algorithm
CN112507506A (en) Multi-objective optimization method for sharing automobile pricing planning model based on genetic algorithm
Duan et al. Reforming mixed operation schedule for electric buses and traditional fuel buses by an optimal framework
Zhang et al. The effect of nonlinear charging function and line change constraints on electric bus scheduling
Wang et al. A dual-population based co-evolutionary algorithm for capacitated electric vehicle routing problems
Lee et al. An approximate dynamic programming algorithm for short-term electric vehicle fleet operation under uncertainty
Cai et al. Delivery routing problem of pure electric vehicle with multi-objective pick-up and delivery integration
Adetunji et al. A two-tailed pricing scheme for optimal ev charging scheduling using multiobjective reinforcement learning
Lu et al. Customer segmentation algorithm based on data mining for electric vehicles
Costa Affonso et al. Modelling of User Behaviour for Static Rebalancing of Bike Sharing System: Transfer of Demand from Bike‐Shortage Stations to Neighbouring Stations
Chauhan et al. Scheduling of Electric Vehicle’s Power in V2G and G2V Modes Using an Improved Charge–Discharge Opportunity-Based Approach
Narayanan et al. A Reinforcement Learning Approach for Electric Vehicle Routing Problem with Vehicle-to-Grid Supply
Li et al. A hybrid multi-objective genetic algorithm for bi-objective time window assignment vehicle routing problem
Zhou et al. Customer-oriented multi-objective optimization on a novel collaborative multi-heterogeneous-depot electric vehicle routing problem with mixed time windows
Narayanan et al. Agent-Based Learning Approach to Electric Vehicle Routing Problem with Vehicle-to-Grid Supply and Battery Swapping
Wang et al. A combined genetic algorithm and A* search algorithm for the electric vehicle routing problem with time windows.
Wang et al. A branch-and-price algorithm for a green two-echelon capacitated location routing problem
Bagherinejad et al. A non-dominated sorting ant colony optimization algorithm approach to the bi-objective multi-vehicle allocation of customers to distribution centers

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant