On Exploring a Quantum Particle Swarm Optimization Method for Urban Traffic Light Scheduling

Abstract

Because of concise and efficient evolution rules, the BML model (BML) has a great potential for the two-dimension urban traffic scheduling. However, the theoretical lattice space of BML makes it difficult for the existing models based on BML to simulate the actual traffic flow. In this paper, an extended BML model (EBML) is proposed to effectively simulate the urban traffic where the quantum particle swarm optimization (QPSO) is creatively introduced to optimize traffic lights management. The main contributions include that: (1) EBML is constructed to be more consistent with the actual urban road network with different two-way multi-lane roads. Its lattice sites act as obstacles, overpasses, underground tunnels, and roads. The actual urban road network can be mapped into the lattice space of EBML. And the corresponding updating rules of each lattice site are presented; (2) A deep insight into the traffic characters is provided in EBML. And the effect of the interference among different road capacities on forming traffic congestions is elaborated. Overpasses are applied to alleviate the interferences; (3) By the scheduling simulation of EBML, QPSO optimizes the timing scheduling of traffic lights. Extensive experiments reveal that QPSO achieves excellent optimization performances in real cases.