抄録
In order to improve the efficiency of traffic systems in the global perspective, a traffic control strategy for the dynamic traffic management in the road network has been proposed in this paper. The main idea of the proposed traffic control strategy is based on Q value-based Dynamic Programming with Boltzmann Distribution, and the temperature parameters in Boltzmann Distribution are adjusted by the proposed temperature parameter control strategies, which are Network Method and Intersection Method, depending on the time-varying traffic situations. In the simulation, it is supposed that the route guidance is given to each vehicle and all the vehicles in the traffic system follow the guidance. The simulation results show that temperature parameter control in Q value-based Dynamic Programming with Boltzmann Distribution could improve the performance of the traffic system.
