摘要
在区域交通多智能体信号控制系统中,由于传统遗传算法早熟收敛,全局搜索能力不强,无法快速找到最佳配时方案,同时没有考虑相邻交叉口的关联性,针对这种情况,提出交叉口子区Agent代替传统的交叉口Agent,在交叉口子区Agent中引入自适应遗传算法,算法根据交通流量的变化对绿信比λ进行优化,使交叉口平均延误时间D最短。实验结果表明交叉口子区Agent代替交叉口Agent后,控制效果相似,节省了硬件资源,在交叉口子区Agent中引入自适应遗传算法下的信号控制能迅速找到最佳配时方案,使平均延误时间最短。仿真实验表明,将基于自适应遗传算法的交叉口区域控制应用到交叉口信号控制中有更好的性能,证明了用交叉口区域智能体替代交叉口智能体的可行性。
The control model of multi-agent distributed road traffic signal is presented based on the analyses of the regionaltraffic signal control and the characteristics of multi-agent technology. Firstly, in order to conquer the shortcomings oftraditional genetic algorithm premature convergence, this paper brings the adaptive genetic algorithm into the intersectionsubarea agent, which improves the global optimization ability; secondly, according to the change of traffic flow, using thesubarea agent substituting traditional intersection agent can optimize green ratio λ , thus shortening the average delaytime D of intersection. The experimental results show that subarea agent instead of intersection agent, the control effect issimilar, and hardware resources are saved. In the subarea agent, the signal control under the adaptive genetic algorithm isintroduced which can quickly find the best timing plan, and make the average delay time shortest. Finally, the simulationexperiment shows that the combination of adaptive genetic algorithm and intersection subarea agent has better performancein intersection signal control, and proves the feasibility of subarea agent substituting intersection agent.
出处
《计算机工程与应用》
CSCD
北大核心
2016年第13期265-270,共6页
Computer Engineering and Applications
基金
国家科技支撑计划项目(No.2012BAF12B19)
