Decentralized Temporal Fuzzy Discrete Event Control in Urban Traffic Management

In this paper, a discrete event fuzzy based supervisory controller is applied to an urban traffic control problem also modeled from a discrete event perspective via state flow formalism. Time varying nature of intersections, involvement of human behavior in the system and large scale distributed nature of the problem makes the urban traffic control a challenging problem. Specifically, because of this large scale time varying nature, it is important to consider historical values of the linguistic variables as well as their current values in decision making process. Hence, we establish a novel fuzzy system which imposes green time event based on future-based temporal fuzzy rules, which has a great effect on coordination among intersections. Simulation results present the effectiveness of the proposed method.