基于带容量约束Memetic算法的动态车辆调度问题研究  

Study on Dynamic Vehicle Scheduling Problem with Capacity Constraint Based on Memetic Algorithm

作　　者：曹云 向凤红[1] 毛剑琳[1] 郭宁[1] 

机构地区：[1]昆明理工大学信息工程与自动化学院,云南昆明650500

出　　处：《软件导刊》2017年第11期129-132,136,共5页Software Guide

基　　金：国家自然科学基金项目(61163051);云南省教育厅科学研究基金项目(2015Y071)

摘　　要：针对物流配送过程中带容量约束的动态车辆调度问题,提出一种Memetic算法,旨在最小化成本。Memetic算法中采用量子与遗传算法混合进行全局搜索,并根据搜索点目标函数变化率,设计了一种自适应量子旋转门更新方式,通过子代种群适应度变化确定量子旋转角大小与方向,明确了种群进化方向,扩展了全局搜索范围,引入了一种变异操作,使算法种群多样性得以保持,提高全局搜索宽度,采用2-opt法结合swap法增强算法局部搜索能力。仿真实验验证了所提算法的有效性与优越性。Aiming at the dynamic vehicle scheduling problem with capacity constraints in the process of logistics distribution,a memetic algorithm is proposed,which aims at making the distribution cost the lowest.In the memetic algorithm,aglobal search is carried out by using quantum and genetic algorithm.According to the rate of change of the target function,a new update mode of quantum rotation gate was presented.The magnitude and direction of the quantum rotation angle are changed by the adaptability of the progeny population to determine,so the direction of evolution of the population is more clear,the global search range is broader.Secondly,a mutation operation is introduced to keep the population diversity of the algorithm and improve the width of the global search.Finally,the 2-opt method combined with the swap method is used to enhance the local search capability of the algorithm.The simulation experiment verifies the validity and superiority of the proposed algorithm.

关 键 词：动态车辆调度 MEMETIC算法 量子旋转门 全局搜索 局部搜索 

分 类 号：TP319[自动化与计算机技术—计算机软件与理论]