Optimal Supervisory Control of Two Phases Intersection Using Hybrid-based Model Approach

Abstract

In the present paper, a hybrid approach that combines modular modelling and Timed Petri Nets model is proposed, the main interest of this combination is to ensure optimal supervisory control of urban traffic flows in two phases intersections of medium-sized cities. Each intersection is considered as a multi-agent system, composed of all agents who represent all physical spaces. The behaviours of interconnected agents are supervised by the Timed Petri Nets model that controls the traffic light cycles according to an optimal timing plan defined by the Continuous Genetic Algorithm. A real two phases intersection in Sidi Bel-Abbes City is presented as an example. The proposed timing plan is compared with the current one using SUMO software for the most important objective functions. Also, the proposed model's behaviour is compared with TSIS-CORSIM software's model, and all obtained experiments results show the effectiveness of the approach and its possibility to be extended and applied to a many-phases intersection.