Abstract:

Aiming at the problems of the local optimum of the genetic algorithm in solving traffic signal timing models, this paper presents an optimized traffic signal controller with a golden ratiobased genetic algorithm (TSCGRGA) for urban signalized intersections. This controller employs numerical simulation to analyze the correlation between the traditional performance indicators of traffic signal benefit and their correlation degree with timing parameters, select time delays, stop rate and throughput to establish relative evaluation indices of traffic signals, and a multiobjective timing model of traffic signals is developed by weighted coefficient method. Then, an adaptive golden ratiobased genetic algorithm is presented to solve the optimized models, which uses real number encoding, and introduces golden ratio calculator to enhance the local optimal capability of genetic algorithm. Experiments are conducted on a typical urban isolated intersection and the performance of the developed model and algorithm is validated by comparison with those of fixedtime, actuated, and simple realcoded genetic algorithmbased controllers for different traffic conditions. Extensive numerical circulation and VISSIM simulation results have demonstrated the potential of the developed algorithm in the quality of solutions and time efficiency, and indicated that the signal strategies derived from TSCGRGA have better performance.

Key words: intelligent transportation, traffic signal, correlation analysis, timing model, genetic algorithm, golden ratio

摘要：

针对遗传算法求解交通信号配时模型容易陷入局部最优的问题，提出一种基于黄金分割点遗传算法的城市交通信号建模与优化方法.该方法采用数值模拟分析各交通信号常用性能指标间的相关性及其与配时参数间的关联程度，选取延误、停车率和通过量构建相对评价指标体系；并采用加权系数法建立交通信号多目标配时模型；同时，设计一种基于黄金分割点的自适应遗传算法对交通信号配时模型进行求解.该算法采用实数编码，引入黄金分割点算子增强遗传算法的局部搜索能力.以典型城市单交叉口进行试验，设计多种交通场景，在三种控制策略下采用数值计算和VISSIM仿真对提出的模型及算法进行效用评价.结果表明，所设计的算法求解质量好和计算效率高，提出的配时模型具有良好的控制效果.

关键词: 智能交通, 交通信号, 相关性分析, 配时模型, 遗传算法, 黄金分割