A quantum particle swarm optimization driven urban traffic light scheduling model

作者：Hu, Wenbin^*; Wang, Huan; Qiu, Zhenyu; Nie, Cong; Yan, Liping

来源：Neural Computing & Applications, 2018, 29(3): 901-911.

DOI：10.1007/s00521-016-2508-0

• Traffic congestion
• Simulation
• Optimization
• BML
• Updating rules

Urban traffic congestion becomes a severe problem for many cities all around the world. How to alleviate traffic congestions in real cities is a challenging problem. Benefited from concise and efficient evolution rules, the Biham, Middleton and Levine (BML) model has a great potential to provide favorable results in the dynamic and uncertain traffic flows within an urban network. In this paper, an enhanced BML model (EBML) is proposed to effectively simulate the urban traffic where the timing scheduling optimization algorithm (TSO) based on the quantum particle swarm optimization is creatively introduced to optimize the timing scheduling of traffic light. The main contributions include that: (1) The actual urban road network with different two-way multi-lane roads is firstly mapped into the theoretical lattice space of BML. And the corresponding updating rules of each lattice site are proposed to control vehicle dynamics; (2) compared with BML, a much deeper insight into the phase transition and traffic congestions is provided in EBML. And the interference among different road capacities on forming traffic congestions is elaborated; (3) based on the scheduling simulation of EBML, TSO optimizes the timing scheduling of traffic lights to alleviate traffic congestions. Extensive comparative experiments reveal that TSO can achieve excellent optimization performances in real cases.

• 出版日期2018-2
• 单位武汉大学