PROJECT TITLE :

Traffic network micro-simulation model and control algorithm based on approximate dynamic programming

ABSTRACT:

This study presents the adaptive traffic signal control algorithm during a distributed traffic network system. The proposed algorithm relies on a micro-simulation model and a Reinforcement Learning method, namely approximate dynamic programming (ADP). By considering traffic surroundings in discrete time, the microscopic traffic dynamic model is constructed. In particular, the authors explore a vehicle-following model using cellular automata theory. This vehicle-following model theoretically contributes to traffic network loading surroundings in an accessible approach. To form the network coordinated, tunable state with weights of queue length and vehicles on lane is taken into account. The intersection will share info with each other in this state representation and build a joint action for intersection coordination. Moreover, the traffic signal control algorithm based mostly on ADP technique performs quite well in several performance measures witnessed by simulations. By comparing with alternative control strategies, experimental results present that the proposed algorithm may be a potential candidate in an application of traffic network management system.