Distributed traffic signal control approach based on multi-agent

  • Authors:

  • Xiangjun Cheng;Zhaoxia Yang

  • Affiliations:

  • Traffic and Transportation School, Beijing Jiaotong University, Beijing, China;Traffic and Transportation School, Beijing Jiaotong University, Beijing, China

  • Venue:
  • FSKD'09 Proceedings of the 6th international conference on Fuzzy systems and knowledge discovery - Volume 5
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper establishes a distributed and coordinated traffic signal control system based on multi-agent (DTCMAS), in which there is no control center. Each intersection is controlled by a local agent independently. In the meantime, the signal control agents improves the control effect of global network by communication and coordination among agents in adjacent intersections. Because every agent comprises knowledge-database and reasoning mechanism, the DTCMAS not only fully considers the information of fleets of cars and traffic conditions in around intersections, but also takes the realization of global optimizing for traffic control of road network into account and reduces the complexity of control algorithm greatly. The result of simulation shows that the DTCMAS signal control approach reduces 37.8% total stop delay of cars averagely than the fixed-time method and reduces 17.8% total stop delay of cars averagely than the actuated method under the same condition.