基于并行粒子群算法的带时间窗车辆路径问题

Parallel particle swarm optimization algorithm for vehicle routing problems with time windows

提出求解带时间窗车辆路径问题的多群并行的粒子群算法。为了提高算法的收敛速度,在每个粒子群中嵌入了记忆功能。针对基本粒子群算法在求解有时间窗车辆路径问题时初始解的单一性导致局部收敛的问题,对两个种群采用了两种不同的初始化方法,并在进化过程中,两个种群相互用记忆粒子替换对方种群中的较差粒子。最后将该算法的运行结果与其他算法进行比较,表明该算法的有效性。

This paper introduces the parallel particle swarm optimization algorithm with multiswarm.In order to speed up convergence,it implants the memory mechanism in each particle swarm.Aiming at the local convergence caused by the oneness on the initialization in original PSO algorithm for VRPTW,this paper uses two different initializing methods on two particle swarms.During the evolution,memory particles are used to replace inferior particles each other.In comparison with other algorithms,the parallel algorithm is proved an efficient method for VRPTW.