A novel adaptive traffic signal control based on cloud/fog/edge computing

This paper proposes the Internet of Things-based real-time adaptive traffic signal control strategy. The proposed model consists of three-layer; edge computing layer, fog computing layer, and cloud computing layer. The edge computing layer provides real-time and local optimization. The middle layer, which is the fog computing layer, performs a real-time and global optimization process. The cloud computing layer, which is the top layer, acts as a control center and optimizes the parameters of the fog layer and the edge layer. The proposed strategy uses the Deep Q-Learning algorithm for the optimization process in all three layers. This study employs the SUMO traffic simulator for performance evaluation. These results are compared with the results of adaptive traffic control methods. The output of this study shows that the proposed model can reduce waiting times and travel times while increasing travel speed.