An application of Q-value-based dynamic programming with Boltzmann distribution to real-world road networks

In order to alleviate traffic congestionand improve the efficiency of trafficsystems from a global perspective, a dynamic traffic managementmodel is proposed in this paper. The proposed model is applied to the large-scale microscopic simulator SOUND/4U based on the real-world road network of Kurosaki, Kitakyushu, Japan. All the vehicles in the simulator follow the direction from the route guidance of the dynamic traffic managementmodel, in which the extended Q-value-based dynamic Programming with Boltzmann distribution(QDP-BD) and the time-varying trafficinformation are used to generate the routes from the origins to the destinations. The simulation results show that the proposed QDP-BD can reduce traffic congestionand improve the efficiency of the whole trafficsystem effectively compared with the greedy method in the real-world road network. © 2013 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.