Computer Engineering and Applications ›› 2015, Vol. 51 ›› Issue (20): 246-252.

Previous Articles     Next Articles

Two-layer hierarchical control solutions for traffic signal

GE Jun1, ZHOU Lianying2   

  1. 1.Department of Computer Science, Suqian College, Suqian, Jiangsu 223800, China
    2.College of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang, Jiangsu 212013, China
  • Online:2015-10-15 Published:2015-10-30

面向交通信号的两层递阶控制解决方案

戈  军1,周莲英2   

  1. 1.宿迁学院 计算机科学系,江苏 宿迁 223800
    2.江苏大学 计算机科学与通信工程学院,江苏 镇江 212013

Abstract: In view of the existing deficiencies of traffic signal control system, this paper proposes two-layer hierarchical multi-Agent system solution for traffic signal control. Through regional division of the traffic network, it uses the bottom level Agent to control the intersection, the top level Agent to control areas, so as to achieve the two-layer hierarchical control. The bottom level Agent uses the classical Q-learning to synchronize the optimal strategy, the top level Agent utilizes the special continuous space processing ability of Tile Coding to achieve Q learning of action value function approximation method. The simulation test results show that, the hierarchical control not only improves the efficiency of traffic signal control system, but also provides a good scalable solution for large-scale applications.

Key words: multi-Agent systems, hierarchical control, traffic signals, Q-learning, Tile Coding

摘要: 针对现有交通信号控制系统的诸多不足,提出了一种用于交通信号控制的两层递阶多Agent系统解决方案。通过将交通网络进行区域划分,利用底层Agent控制各交叉口,顶层Agent控制区域,从而实现两层递阶控制。底层Agent采用经典Q学习同步学习最优策略,顶层Agent利用Tile Coding非凡的连续空间处理能力,实现Q学习的动作值函数逼近方法。仿真实验结果表明,该分层递阶控制不但提高了交通信号控制系统效率,而且也为大规模应用提供了很好的可伸缩解决方案。

关键词: 多Agent系统, 递阶控制, 交通信号, Q-学习, Tile Coding