CN-121981450-A - Digital twin-based dynamic fleet scheduling and energy consumption collaborative optimization method and system

CN121981450ACN 121981450 ACN121981450 ACN 121981450ACN-121981450-A

Abstract

The invention relates to the technical field of enterprise fleet management, in particular to a digital twin-based fleet dynamic scheduling and energy consumption collaborative optimization method and system, wherein a digital twin-scheduling cloud platform of a fleet is built, and a plurality of fleet participants for cooperatively executing transportation tasks are accessed; and carrying out space-time division on the transportation tasks according to the cooperative scheduling rights, generating a fleet scheduling block, issuing the fleet scheduling block, carrying out initial parameter definition on key factors such as vehicle allocation, path planning, load optimization, dynamic road condition response and the like by each participant based on block information, and constructing a plurality of fleet dynamic scheduling modeling spaces by combining with the scheduling parameter library through searching. And introducing an improved teaching and learning optimization algorithm module, and embedding a dynamic competition optimization algorithm to enhance the adaptability of the dynamic competition optimization algorithm module so as to form a fleet scheduling collaborative optimization algorithm module. And carrying out global optimization in a multi-modeling space based on the algorithm, outputting an optimal scheduling parameter set, and realizing the dynamic scheduling and energy consumption collaborative optimization of the transportation task.

Inventors

LIU ZHIYAN
LIU SIYU

Assignees

丽水梦飞网络科技有限公司

Dates

Publication Date: 20260505
Application Date: 20260108

Claims (10)

1. The digital twin-based fleet dynamic scheduling and energy consumption collaborative optimization method is characterized by comprising the following steps of: building a fleet digital twin scheduling cloud platform, and accessing a plurality of fleet participants based on the fleet digital twin scheduling cloud platform, wherein the fleet participants are cooperative execution parties of transportation tasks; carrying out space-time division on the transportation tasks according to the task cooperative scheduling authority information to obtain fleet scheduling block information and transmitting the fleet scheduling block information to the plurality of fleet participants; the method comprises the steps of obtaining key factor information of fleet scheduling, wherein the key factor information of fleet scheduling comprises vehicle allocation, path planning, load optimization and dynamic road condition response; The fleet participants respectively define initial parameters of the fleet scheduling key factor information based on the fleet scheduling block information, determine a plurality of initial fleet scheduling parameter information, and perform traversal search in a scheduling parameter library based on the plurality of initial fleet scheduling parameter information to construct a plurality of fleet dynamic scheduling modeling spaces; Setting an improved teaching and learning optimization algorithm module, embedding a dynamic competition optimization algorithm module in the improved teaching and learning optimization algorithm module, adaptively enhancing the improved teaching and learning optimization algorithm module based on the dynamic competition optimization algorithm module, and determining a fleet scheduling collaborative optimization algorithm module; And carrying out global optimization in the dynamic scheduling modeling space of the multiple motorcades based on the motorcade scheduling collaborative optimization algorithm module, outputting multiple motorcade scheduling optimization parameter sets, and carrying out dynamic scheduling and energy consumption collaborative optimization on the transportation task based on the multiple motorcade scheduling optimization parameter sets.
2. The digital twin-based fleet dynamic scheduling and energy consumption collaborative optimization method according to claim 1, wherein the obtaining fleet scheduling block information comprises: Carrying out label division on the transport tasks according to the geographic areas and the dispatching levels respectively to obtain task geographic area label information and dispatching level label information; Creating a fleet scheduling task directory structure according to the task geographic area tag information and the scheduling hierarchy tag information; Performing authority matching with the fleet scheduling task directory structure based on the task cooperative scheduling authority information to obtain a task cooperative scheduling directory label set; and respectively carrying out scheduling content mapping based on the task cooperative scheduling directory label set, and determining the fleet scheduling block information.
3. The digital twin-based fleet dynamic scheduling and energy consumption collaborative optimization method according to claim 1, wherein the constructing a plurality of fleet dynamic scheduling modeling spaces comprises: extracting root node attributes based on the fleet scheduling key factor information, filling node contents, and constructing a fleet scheduling attribute knowledge graph; classifying and integrating the scheduling parameter library according to the fleet scheduling attribute knowledge graph to obtain a fleet scheduling attribute parameter library; Respectively carrying out similarity matching on the plurality of initial fleet scheduling parameter information and the fleet scheduling attribute parameter library, and screening to obtain a plurality of fleet scheduling characteristic parameter sets; And constructing a dynamic scheduling modeling space of the multiple motorcades according to the scheduling characteristic parameter sets of the multiple motorcades.
4. The digital twin based fleet dynamic scheduling and energy consumption collaborative optimization method according to claim 1, wherein the outputting a plurality of fleet scheduling optimization parameter sets comprises: Constructing a dispatching efficiency evaluation fitness function, and iteratively screening in the dynamic dispatching modeling space of the multiple motorcades based on the dispatching efficiency evaluation fitness function to obtain an optimal teacher solution and other student solutions; Setting a parameter dynamic step length, and dynamically updating the rest student solutions to the optimal teacher solution based on the parameter dynamic step length to generate a student update solution set; constructing a dynamic learning factor, and carrying out collaborative learning updating on the student updating solution set based on the dynamic learning factor to obtain a plurality of fleet scheduling population parameter sets; Evaluating and calculating the dispatching population parameter sets of the multiple motorcades through the dispatching efficiency evaluation fitness function to obtain multiple dispatching efficiency evaluation fitness; And carrying out partition clustering on the plurality of fleet scheduling group parameter sets based on the plurality of scheduling effectiveness evaluation fitness to obtain the plurality of fleet scheduling optimization parameter sets.
5. The digital twin-based fleet dynamic scheduling and energy consumption collaborative optimization method according to claim 4, wherein the constructing a scheduling effectiveness evaluation fitness function comprises: performing index extraction on the fleet scheduling efficiency requirements, and determining a scheduling efficiency evaluation index set, wherein the scheduling efficiency evaluation index set comprises timeliness, energy consumption and safety; constructing a scheduling effectiveness evaluation fitness function based on the scheduling effectiveness evaluation index set, wherein the scheduling effectiveness evaluation fitness function specifically comprises: Wherein alpha represents timeliness index weight, u is timeliness experience evaluation function, The method is characterized in that the method comprises the steps that (1) m is the total class number of scheduling key factor information, beta represents energy consumption index weight, v is an energy consumption experience assessment function, gamma is a safety index weight, w is a safety experience assessment function, the sum of the weights of alpha, beta and gamma is 1, and eta represents an assessment experience constant.
6. The digital twin based fleet dynamic scheduling and energy consumption collaborative optimization method according to claim 4, wherein the obtaining the plurality of fleet scheduling optimization parameter sets comprises: respectively dividing the plurality of fleet scheduling population parameter sets in proportion according to the scheduling efficiency evaluation fitness to obtain a plurality of priority fleet scheduling population parameter sets and a plurality of secondary fleet scheduling population parameter sets; Based on the plurality of priority fleet scheduling population parameter sets and the plurality of priority scheduling efficiency fitness, carrying out dynamic cluster allocation on the plurality of secondary fleet scheduling population parameter sets to determine a plurality of fleet scheduling population parameter clusters; Performing parameter iterative optimization in the plurality of fleet scheduling population parameter clusters until a preset convergence threshold is met, so as to obtain a plurality of fleet scheduling optimization population parameter clusters; And calculating the adaptability sum of the plurality of motorcade dispatching optimization group parameter clusters, and outputting the parameter cluster with the optimal adaptability sum to obtain the plurality of motorcade dispatching optimization parameter sets.
7. The digital twin based fleet dynamic scheduling and energy consumption collaborative optimization method according to claim 6, wherein the obtaining a plurality of fleet scheduling optimization cluster population parameter sets comprises: Taking the optimal scheduling parameters in the multiple fleet scheduling group parameter clusters as target optimization parameters, and optimizing and updating the scheduling parameters in the other multiple clusters according to dynamic step length to obtain multiple intra-cluster scheduling optimization parameter sets; Calculating a plurality of intra-cluster scheduling efficiency fitness of the plurality of intra-cluster scheduling optimization parameter sets, and performing difference iterative updating on the plurality of intra-cluster scheduling efficiency fitness and the target scheduling efficiency fitness of the target optimization parameter until the preset convergence threshold is met, so as to obtain the plurality of fleet scheduling optimization population parameter sets.
8. A digital twinning-based fleet dynamic scheduling and energy consumption collaborative optimization system, the system comprising: the platform construction module is used for constructing a fleet digital twin scheduling cloud platform, accessing a plurality of fleet participants based on the fleet digital twin scheduling cloud platform, wherein the fleet participants are cooperative execution parties of transportation tasks; the task partitioning module is used for performing space-time division on the transportation task according to the task cooperative scheduling authority information to obtain fleet scheduling block information and transmitting the fleet scheduling block information to the plurality of fleet participants; The factor perception module is used for acquiring key factor information of fleet scheduling, wherein the key factor information of fleet scheduling comprises vehicle allocation, path planning, load optimization and dynamic road condition response; The modeling mapping module is used for respectively carrying out initial parameter definition on the key factor information of the fleet scheduling by the fleet participants based on the fleet scheduling block information, determining a plurality of initial fleet scheduling parameter information, carrying out traversal search in a scheduling parameter library based on the plurality of initial fleet scheduling parameter information, and constructing a plurality of fleet dynamic scheduling modeling spaces; The algorithm enhancement module is used for setting an improved teaching and learning optimization algorithm module, embedding a dynamic competition optimization algorithm module in the improved teaching and learning optimization algorithm module, adaptively enhancing the improved teaching and learning optimization algorithm module based on the dynamic competition optimization algorithm module, and determining a fleet scheduling collaborative optimization algorithm module; The global optimization module is used for carrying out global optimization in the dynamic scheduling modeling space of the multiple motorcades based on the motorcade scheduling collaborative optimization algorithm module, outputting multiple motorcade scheduling optimization parameter sets, and carrying out dynamic scheduling and energy consumption collaborative optimization on the transportation task based on the multiple motorcade scheduling optimization parameter sets.
9. A digital twin based fleet dynamic scheduling and energy consumption co-optimizing device comprising a memory, a processor and a digital twin based fleet dynamic scheduling and energy consumption co-optimizing program stored on the memory and operable on the processor, the digital twin based fleet dynamic scheduling and energy consumption co-optimizing program configured to implement the steps of the digital twin based fleet dynamic scheduling and energy consumption co-optimizing method according to any one of claims 1 to 7.
10. A medium, wherein a digital twin-based fleet dynamic scheduling and energy consumption collaborative optimization program is stored on the medium, and the digital twin-based fleet dynamic scheduling and energy consumption collaborative optimization program, when executed by a processor, implements the steps of the digital twin-based fleet dynamic scheduling and energy consumption collaborative optimization method according to any one of claims 1 to 7.

Description

Digital twin-based dynamic fleet scheduling and energy consumption collaborative optimization method and system Technical Field The invention relates to the technical field of enterprise fleet management, in particular to a digital twin-based fleet dynamic scheduling and energy consumption collaborative optimization method and system. Background With the rapid development of intelligent traffic systems and logistics informatization, the intellectualization and greenization of fleet scheduling have become key requirements of modern transportation management. The traditional fleet scheduling method mainly depends on experience rules or static optimization models, is difficult to cope with complex and dynamic traffic environments, changeable transportation task demands and scheduling scenes with multi-party cooperative participation, and particularly has the problems of lag response, weak global optimization capability, high energy consumption and the like when facing multiple constraints such as large-scale vehicle allocation, real-time road condition change, fuel oil/electric energy consumption control and the like. Although part of researches introduce intelligent optimization means such as genetic algorithm, particle swarm optimization and the like to carry out path planning and resource allocation, the methods are easy to fall into local optimization in a high-dimensional complex space, and lack dynamic feedback and cooperative regulation and control mechanisms for the whole operation process of a motorcade. In recent years, digital twin technology provides a new technical path for realizing real-time mapping of physical world and virtual space, and has great potential in the fields of traffic management and vehicle scheduling. By constructing digital twin bodies of entities such as vehicles, roads, tasks and the like, accurate perception, prediction and simulation deduction of the running state of a motorcade can be realized, so that more intelligent decision making is supported. However, the existing dispatching system based on digital twin focuses on state monitoring and visual display, and has the defects in the automatic optimization level, especially in the aspects of multi-objective collaborative optimization (such as timeliness, safety and energy consumption balance), and the support of an intelligent algorithm with high efficiency is lacking. In addition, in the scenario of cooperative transportation involving multiple parties, how to realize reasonable division of tasks, distributed modeling of parameters and consistency optimization is still a technical bottleneck to be solved. The foregoing is provided merely for the purpose of facilitating understanding of the technical solutions of the present invention and is not intended to represent an admission that the foregoing is prior art. Disclosure of Invention The invention mainly aims to provide a digital twin-based dynamic fleet scheduling and energy consumption collaborative optimization method and system, and aims to solve the technical problems that the existing fleet scheduling method is difficult to consider dynamic environment adaptability, multi-objective collaborative optimization and global optimization under multiparty participation, and a real-time efficient scheduling and energy consumption collaborative optimization mechanism integrating digital twin and intelligent algorithms is lacking. In order to achieve the above purpose, the invention provides a digital twin-based fleet dynamic scheduling and energy consumption collaborative optimization method, which comprises the following steps: building a fleet digital twin scheduling cloud platform, and accessing a plurality of fleet participants based on the fleet digital twin scheduling cloud platform, wherein the fleet participants are cooperative execution parties of transportation tasks; carrying out space-time division on the transportation tasks according to the task cooperative scheduling authority information to obtain fleet scheduling block information and transmitting the fleet scheduling block information to the plurality of fleet participants; the method comprises the steps of obtaining key factor information of fleet scheduling, wherein the key factor information of fleet scheduling comprises vehicle allocation, path planning, load optimization and dynamic road condition response; The fleet participants respectively define initial parameters of the fleet scheduling key factor information based on the fleet scheduling block information, determine a plurality of initial fleet scheduling parameter information, and perform traversal search in a scheduling parameter library based on the plurality of initial fleet scheduling parameter information to construct a plurality of fleet dynamic scheduling modeling spaces; Setting an improved teaching and learning optimization algorithm module, embedding a dynamic competition optimization algorithm module in the improved teaching and lear