A Hybrid Cellular Automaton Mechanism Inspired Approach for Dynamic and Real-Time Traffic Lights Scheduling

摘要

How to optimize and schedule hundreds of traffic lights has become a challenging and pressing problem. The key point lies on how to manage them dynamically and timely. This paper proposes an inner and outer cellular automaton mechanism combined with particle swa445rm optimization (IOCA-PSO) method to achieve a dynamic and real-time optimization scheduling of urban traffic lights. The proposed IOCA-PSO method includes three parts: the inner cellular model (ICM), the outer cellular model (OCM), and the fitness function. Our main contributions lie on three points: (1) The concise basic transition rules and affiliated transition rules are proposed in ICM, which help to achieve a global sophisticated scheduling. (2) The proposed inner and outer cellular PSO (IOPSO) algorithm in OCM offers a strong search ability to find the optimal timing scheduling. (3) The proposed fitness function can evaluate and conduct the optimization of the traffic light scheduling dynamically for different aims. Extensive experiments in real cases show that the IOCA-PSO method has distinct improvements under different traffic conditions.