遗传算法求解VRP的种群初始化改进  

Improvement on Population Initialization of Genetic Algorithm Solution for VRP

作　　者：徐鹏[1,2] 王雷[1] 张文义[1] 

机构地区：[1]河海大学交通学院,江苏南京210098 [2]河海大学海岸灾害及防护教育部重点实验室,江苏南京210098

出　　处：《南京师范大学学报（工程技术版）》2009年第3期70-74,共5页Journal of Nanjing Normal University(Engineering and Technology Edition)

基　　金：河海大学自然科学基金(2008429911)资助项目

摘　　要：传统的遗传算法求解VRP时,初始种群多半采取随机生成法形成染色体方案,以致于迭代开始就可能形成许多不可行的方案,要进行大量的计算后才能得到优化的方案,这在很大程度上降低了算法的运算效率.论文提出的遗传编码策略,对初始种群给予基于知识型启发策略,使得初始种群一开始就表现为一种较优的状态.When traditional Genetic Algorithms （GA） was applied in VRP, most of the initial population generate the chromosome program by taking a random method, which leads to a lot of infeasible schemes in the beginning, and a great deal of calculations before obtaining an optimize one. This reduced the calculating efficiency of the algorithm to the great extent. The genetic coding strategy, proposed by the paper, gives initial population a knowledge-based heuristic strategy, which makes initial population a better performance at the very start.

关 键 词：VRP 初始种群 遗传编码 遗传算法 改进遗传算法 

分 类 号：U491.2[交通运输工程—交通运输规划与管理]