A Self-Adaptive Approach for Traffic Lights Control in an Urban Network

The use of adaptive traffic lights controllers represents an affordable approach to improve vehicular traffic conditions. In isolated intersections or local areas with a limited number of traffic lights, numerous works from the related open literature have achieved excellent results in key performance metrics. Nevertheless, an urban network environment poses important challenges for adaptive control, mainly due to the stochastic and non-linear nature of the events and the increasing number of interdependencies among them. In this paper, we introduce a self-adaptive method able to control traffic lights in an urban network. Our policy relies on both current traffic data and a "window" of historical data, from which each intersection controller proactively decides the measures to be taken. Simulations have been conducted to evaluate the performance of our proposal obtaining interesting findings to discuss.