一种改进的遗传算法在动态交通分配中的应用  

An Improved Genetic Algorithm and Its Application in Dynamic Traffic Assignment

作　　者：李超[1] 郑长江[1] 

机构地区：[1]河海大学交通学院,江苏南京210098

出　　处：《交通科技与经济》2008年第5期101-103,共3页Technology & Economy in Areas of Communications

摘　　要：以遗传思想为基础设计了新的启发式优化算法,针对动态交通分配问题,对遗传操作中的选择、交叉、变异算子进行修改,同时采用了模拟退火收敛准则,克服了传统遗传算法早熟收敛的弊端,并提高了全局寻优能力。仿真实验表明,该算法有快速高效的特点,提高了该动态交通分配模型的实用价值。Based on the genetic algorithm idea, a new illumination optimization algorithm is proposed aiming at dynamic traffic assignment. This new algorithm overcomes the disadvantages of premature convergence in simple genetic algorithm and enhances the ability of global searching by using the modification of the selection operator, crossover operator and mutation operator and the adoption of the termination condition of simulated annealing. The computer simulation results show that this algorithm is fast and efficient and improve the dynamic traffic assignment model＇s practicality a lot.

关 键 词：遗传优化算法 动态交通分配 模拟优化 动态用户均衡 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]