Online Traffic Signal Control for Reducing Vehicle Carbon Dioxide Emissions

In Japan, carbon dioxide (CO2) emissions caused by vehicles have been increasing year by year and it is well known that CO2 causes a serious global warming problem. For urban traffic control systems, there is a great demand for realization of signal control measures as soon as possible due to the urgency of the recent environmental situation. This paper describes a new traffic signal control for reducing vehicle CO2 emissions on an arterial road. First, we develop a model for estimating the emissions using the traffic delay and the number of stops a driver makes. Second, to find the optimal control parameters, we introduce a random search method with rapid convergence suitable for an online traffic control. We conduct experiments in Kawasaki to verify the effectiveness of our method. The experiments show that our approach decreases not only the emissions but also congestion and travel time significantly, compared to the method implemented in the real system.