A multi-agent system for monitoring and regulating road traffic in a smart city

Modern cities, where millions of people live and drive vehicles every day, mean severe traffic congestion and yield long queues of vehicles, which wait in every single road section. Transiting to the smart city philosophy is an opportunity to better monitor road traffic thanks to information collected in real time from sensors and to profit from regulation abilities of software-based city resources' allocation. In this paper, we design a multi-agent system to monitor road traffic in a smart city and dynamically adjust, in a distributed manner, traffic lights durations to traffic densities at different road sections. The objective is to profit from reactive behavior of agents and their communication abilities to optimize both locally and globally waiting times of vehicles. We validate our work through simulating behavior of agents and generating city maps and models of traffic.