Vehicle path optimization method based on multi-population coevolution

Abstract

The invention discloses a vehicle path optimization method based on multi-population coevolution, and the method comprises the steps: firstly building a network data set of a research region, and obtaining a distance cost matrix between research object points; then, enabling the client points to be subjected to natural number encoding, and completing initialization of multiple populations; carrying out crossover and mutation operations on chromosomes in the population, then carrying out chromosome replacement among the sub-populations, achieving coevolution of multiple populations, and repeating crossover, mutation and coevolution selection operations until an iteration termination condition is met; finally, outputting the chromosome with the highest fitness in the population, and after decoding operation is completed, obtaining the optimal path scheme of vehicle scheduling. The invention provides a vehicle path optimization method based on multi-population coevolution, which is more suitable for practical application.

Description

technical field [0001] The invention relates to the fields of GIS technology, logistics distribution, computing intelligence, and computer application, and in particular to a vehicle route optimization method based on multi-population cooperative evolution. Background technique [0002] With the continuous development of Internet technology and the deepening reform of the supply-side structure, the logistics industry has become an important source of power to promote my country's economic development and improve residents' living standards. Since 2014, my country began to implement the "Medium and Long-Term Plan for the Development of Logistics Industry (2014-2020)", which requires improving the level of informatization and intelligence of the logistics industry, and the development and application of e-commerce logistics engineering, logistics information platform engineering, and new logistics technologies. The project is listed as the main project, and the active promotion...

AI Technical Summary

Problems solved by technology

[0006] In order to solve the defect that the existing vehicle routing problem method is not accurate in solving the actual distribution problem, the present invention proposes a vehicle routing optimization method based on multi-population collaborative evolution, combined with GIS technology, the actual geographic information of the distribution area , carry out vector modeling, create a feature network dataset, construct a "starting point-destination" distance cost analysis matrix, obtain the actual road network distance between each customer point, and then use a variety of co-evolutionary ideas to improve the genetic The algorithm, which assigns different crossover probabilities and mutation probabilities to different populations, enhances the optimization ability in the iterative process and avoids the problem of premature convergence of solutions

Images