Agent Based Monitoring for Smart Cities: Application to Traffic Lights

International audience; Traffic congestion in large cities became a huge problem, which can lead to a lot of losses especially at the human and material levels. This paper proposes a decentralized model based on multi-agent systems (MAS) and complex event processing (CEP). The new control scheme aims to improve green light time in order to reduce the average waiting time of vehicles in front of the traffic light, especially if the road is empty, and to reduce congestion at crossroad. This improvement is provided by the observation of the intersection through Cyber Physical Systems (CPS). This paper propose an auto-adaptive model for smart regulation traffic lights. The developed model will be evaluated and analyzed using different metrics and scenarios so as to test their influence on system performance.