Research on Traffic Congestion Resolution Mechanism based on Genetic Algorithm and Multi-Agent
Zehua Zhang, Jiahao Ye, Shuo Cheng
Available Online April 2019.
- https://doi.org/10.2991/icmeit-19.2019.77How to use a DOI?
- Traffic congestion; Multi-agent; Green-signal and red-signal ratio; Genetic algorithm.
- In recent years, the number of motor vehicles in China has grown rapidly, and the contradiction between supply and demand of vehicles and roads has become more apparent. The problem of urban traffic congestion has become increasingly prominent, and the mechanism of congestion resolution has emerged. At present, there are still many shortcomings in China's traffic congestion control system. The phenomenon of urban road congestion is still widespread. The existing traffic control system cannot meet the complicated traffic network and cannot alleviate the deterioration of traffic conditions. This paper proposes a multi-agent traffic control system, which aims to control the green-signal and red-signal ratio of traffic flow at multiple adjacent intersections in the traffic network, thereby improving the driving ability of the traffic flow. This paper starts from the traffic control network and uses a single agent as the unit. Through multi-agent technology, the information between multiple agents at each intersection can be circulated, and each agent can quickly respond and automatically adapt to changes in traffic information. A genetic algorithm is used to establish a distributed urban traffic control system that can be continuously optimized. It is hoped that through the research in this paper, the problem of urban road traffic congestion deterioration can be effectively solved, thereby improving the vehicle traffic capacity and the efficiency of social activities.
- Open Access
- This is an open access article distributed under the CC BY-NC license.
Cite this article
TY - CONF AU - Zehua Zhang AU - Jiahao Ye AU - Shuo Cheng PY - 2019/04 DA - 2019/04 TI - Research on Traffic Congestion Resolution Mechanism based on Genetic Algorithm and Multi-Agent PB - Atlantis Press SP - 473 EP - 483 SN - 2352-538X UR - https://doi.org/10.2991/icmeit-19.2019.77 DO - https://doi.org/10.2991/icmeit-19.2019.77 ID - Zhang2019/04 ER -