基于遗传灰狼算法的员工通勤合乘路径优化

Optimization of Personnel Commuting and Riding Path Based on Genetic Gray Wolf Optimizer

为了缓解小汽车过多使用造成的城市道路拥堵,达到整合交通资源、提高道路利用率的目的,以职住两地周围的通勤居民为研究对象,对员工通勤合乘路径进行研究。以通勤合乘路径最短、用户总出行成本最少为优化目标建立目标函数,在保留灰狼算法(GWO)参数少和收敛速度快等优点的基础上,融合遗传算法(GA)中精英个体的变异操作防止灰狼算法(GWO)后期陷入局部。结果表明:遗传灰狼算法(GAGWO)优化后的合乘路径能有效降低私家车的空驶率以及司机和乘客的出行成本。

In order to alleviate urban road congestion caused by excessive use of cars,to achieve the purpose of integrating traffic resources and improving road utilization.Taking the commuting residents around the two places as the research object,the research on the commuting and riding path of employees is carried out.The objective function is established with the shortest commuting and riding path and the least total travel cost of users as the optimization goal.On the basis of retaining the advantages of Gray Wolf Optimizer(GWO)with few parameters and fast convergence speed,it integrates the variation of elite individuals in Genetic Algorithm(GA).The operation prevents the Gray Wolf Optimizer(GWO)from falling into local in the later stage.The results show that the commuting and riding path optimized by the Genetic Gray Wolf Optimizer(GAGWO)can effectively reduce the empty driving rate of private cars and the travel cost of drivers and passengers.