交通信号自适应遗传控制算法及其仿真研究  

Adaptive Genetic Algorithm Based Scheme for Traffic Lights Control and Its Simulation Study

作　　者：卫星[1,2] 张利[3,4] 魏振春[2,4] 翟琰[2] 

机构地区：[1]合肥工业大学计算机科学与技术博士后科研流动站,合肥230009 [2]合肥工业大学计算机与信息学院,合肥230009 [3]合肥工业大学机械与汽车工程学院,合肥230009 [4]安全关键工业测控技术教育部工程研究中心,合肥230009

出　　处：《系统仿真学报》2012年第11期2255-2258,共4页Journal of System Simulation

基　　金：中央高校基本科研业务费专项资金资助(2011HGBZ1321;2012HGQC0012)

摘　　要：针对传统的交通信号控制方法时效性不强、运算量大等缺陷,提出了一种基于自适应遗传算法的单点交通信号控制策略。首先构建了多相位单交叉路口的数学模型,并推导出平均延误时间目标与绿灯配时之间的关系,在此模型的基础上采用自适应遗传算法进行优化,并对该方法的有效性以及相对于传统遗传算法的快速收敛性进行了仿真验证。结果表明,相对于固定配时方案和传统的遗传算法配时方案,该方法有效的提高了控制效果和时效性。In order to avoid the drawbacks of traditional methods for traffic lights control, such as poor timeliness and superfluous computation, an adaptive genetic algorithm based scheme of isolated intersection control was brought forth. Firstly, the mathematical model of the actual isolated intersection was constructed. The relationship between average lateness and effective green time was also deduced. Then an adaptive genetic algorithm was adopted to optimize average lateness based on before-mentioned problem. The effectiveness of the scheme was finally verified through simulation. The results show that when compared with fixed timing control method and the traditional control methods just based on genetic algorithm, the proposed scheme has great superiority in improving the performance and timeliness.

关 键 词：自适应遗传算法 平均延误时间 单点信号控制 时效性 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]