Swarm-based Traffic Lights Policy Selection

Abstract

Improving the efficiency of urban vehicular mobility, also via the optimized management of the dynamic behavior of traffic lights with limited infrastructure investments and limited operational costs, is widely recognized as a crucial goal for smart cities, capable of relevant economic impacts in terms of travel time/cost reduction and better sustainability. Within this context, in the framework of the ongoing EU FP7 COLOMBO project, we are investigating, developing, and thoroughly evaluating innovative locality-based vehicular cooperation protocols for the determination of traffic characteristics in proximity of intersections, with no need for communication towards global data collection centers. One of the specific and original goals in COLOMBO is to achieve reasonable and sufficiently accurate traffic estimations with limited penetration rates of actively participating vehicles equipped with differentiated V2X capabilities (full-fledged V2X-enabled cars but also vehicles with only onboard smartphones). In this paper, we specifically focus on our recent research work of implementation and evaluation of our protocols on top of the iTETRIS simulation platform, a state-of-the-art integrated platform resulted from the synergic interworking of the ns-3 network and the SUMO vehicular mobility simulators. In particular, here we originally describe how to effectively and efficiently implement V2X protocols on iTETRIS, as well as lessons learned from our practical experience of deployment, evaluation, and protocol/iTETRIS fine-tuning. The reported simulation results (obtained through realistic simulations based on real traffic traces and the real road topology of the city of Bologna) show the feasibility of the proposed approach also with very limited penetration rates.