基于粒子群算法的城市单交叉口信号控制

A New Particle Swarm Optimization Algorithm and Real-time Control of Traffic Signal in Urban Intersection

在简要介绍基本PSO算法的基础上,提出一种在速度变迁公式中增加用组内的局部最优值来指导飞行的项的改进算法,并将其运用到单交叉路口的信号控制。通过对本周期及前一个周期的车流量进行实时测量,采用一个周期的滞留车流量评估,从而确定一周期的相位配时方案,最终以路口各周期滞留车辆量的变化作为控制性能评价。采用Matlab语言编程进行实时仿真实验,仿真验证了此算法对交叉路信号控制的有效性。

A real-time dynamic model on multiphase traffic flows is conducted in an urban intersection by using the Particle swarm optimization （PSO） which is a new population-based intelligence algorithm and exhibits good performance on optimization. In this paper, a new PSO algorithm is proposed in which a new part in the velocity model ,which a local best information was used to guide the particl to fly , was appended. Then it was applied to the real-time dymamic model on multiphase traffic flows. A simulation experiment for the traffic model at a four-phase intersection is also performed in the last section. The results show that the method is effective.