基于改进粒子群算法的单交叉口信号配时仿真

Simulation of Signal Timing for Single Intersection Based on Improved-PSO Algorithm

研究城市交通信号控制系统中的单交叉口优化交通流问题,由于交通流具有非线性和不确定性特点,很难建立精确模型。为解决上述问题,提出把每一相位的排队长度都作为优化的目标,采用多目标信号配时模型以满足不同交通需求,并采用改进粒子群(PSO)算法进行求解。在深入研究分析PSO算法的基础上,引入变异因子和惯性权重自适应策略对该算法进行改进,既发挥了PSO算法随机优化收敛速度快的优点,又克服了算法易陷入局部最优点的缺点,显著提高了优化算法的性能指标。仿真结果验证了方法的有效性和合理性。

With the development of economic and urbanization process,the contradiction between road capacity and traffic demands has become more and more severe.This paper took a single intersection as research object,took queue length of each phase as the optimization objectives,and used multi-objective signal timing model to satisfy diffident traffic demands,and introduced improved-PSO algorithm to solve the problem.On the basis of the research and analysis for PSO,the variability factor and inertia weight self-adaptability strategy were introduced to improve the PSO algorithm.The improved PSO algorithm not only has the advantage of fast convergence speed,but also overcomes the shortcoming of PSO algorithm which easily falls into the local minimums,and improves the performance of optimization greatly.The simulation experiments verify the effectiveness and rationality of the control method.