基于改进的蚁群算法求解单点交叉口信号配时优化问题

Solution to the Problem of Signal Timing Optimization in Isolated Intersection Based on the Improved Ant Colony Algorithm

蚁群算法是近几年优化领域中出现的一种启发式仿生类并行智能进化、通用型的随机优化算法,能够较好解决交通信号配时优化问题.由于交通信号分配不合理容易引发交通拥堵,基于传统的单点交叉口交通信号配时优化问题提出了改进的蚁群算法,即针对交通具有较强的实时性和动态性的特点,在蚁群算法更新的全局信息素中引入一个随着交叉口拥挤程度不同而变化的函数,并且在信息素变化量中引入一个交叉口通行能力权系数,从而提高算法对交通实时动态性的把控能力.通过实验仿真结果表明,该改进的蚁群算法优于传统的单点交叉口信号配时方法,从而为蚁群算法求解这类问题提供了一种可行有效的新方法.

In the field of optimization in recent years,ant colony algorithm is a general stochastic optimization with the parallel heuristic-bionic intelligent evolution and better solution to the problem of traffic signal matching optimization.As unreasonable traffic signal distribution is liable to trigger traffic jam,an improved ant colony algorithm was put forward,aiming at the optimization problem of the traditional single intersection traffic.In view of the strong real-time and dynamic characteristics of traffic,a function that changes in accordance with the crowding degree of the intersection was introduced into the updating global pheromone of ant colony algorithm.Moreover,a crossover capacity weight coefficient was introduced into the flux variation,so as to improve the ability of the algorithm to control traffic real-time dynamics.The experimental results showed that the improved ant colony algorithm is superior to the traditional single point intersection signal matching method,and thus provides a feasible and effective new method for ant colony algorithm to solve this kind of problem.