路网车流径路选择随机相关机会规划模型及其混合遗传算法  

Stochastic Dependent-chance Programming Model and Hybrid Genetic Algorithm for Car Flow Routing Plan

作　　者：王保华[1] 何世伟[1] 宋瑞[1] 汪波[1] 

机构地区：[1]北京交通大学交通运输学院,北京100044

出　　处：《铁道学报》2007年第4期6-11,共6页Journal of the China Railway Society

基　　金：国家自然科学基金项目(70371014);教育部高等学校博士学科点专项科研基金资助项目(20040004012)

摘　　要：研究随机环境下车流径路的选择问题,首先给出路网车流径路方案可靠性的定义,并在此基础上建立随机环境下车流径路选择问题的随机相关机会多目标规划模型。模型考虑了车流具有不同权重的情况,目标为极大化车流径路方案的可靠性及极小化期望总费用。用C++语言编写K短路算法,并在Visual Studio 6.0上基于该算法开发了软件,用于计算网络上任意两点之间的K短路。以该软件计算出的K短路作为节点间的可选径路集,提出一种基于随机模拟的混合遗传算法。算例表明,在不同交叉和变异概率的条件下算法均可在给定进化代数内收敛至相同的最优解,有较强的适应性。This paper addresses the car flow routing problem under the stochastic environment. Firstly, the paper presents the definition of reliability of the car flow routing plan. Based on the definition, the paper proposes a stochastic dependent-chance multi-objective programming model, which aims to maximize the reliability of the car flow routing plan and minimize the expected total cost. The paper takes the weight of different car flows into consideration. Based on the K-shortest path algorithm which is implemented in C＋ ＋, the paper develops a software with Visual Studio 6.0 to get the K-shortest path between any pair of nodes in the network. Taking the K-shortest path as the optional routes between two nodes, a hybrid genetic algorithm which is based on stochastic simulation is presented in the paper. The numerical experiments show that the algorithm can converge at the same optimal solution with varying probabilities of crossover and mutation and has strong adaptability.

关 键 词：车流径路方案 可靠性 相关机会规划 混合遗传算法 

分 类 号：U292.3[交通运输工程—交通运输规划与管理]