查看文章

Traffic congestion causes significant problems such as longer travel time, energy consumption, and air pollution. Currently, we have proposed an adaptive traffic control algorithm based on back-pressure and Q-learning to efficiently reduce congestion. In this paper, we evaluate our proposed method using the road network simulated by a real structure. The simulation results show that our algorithm significantly decreases average vehicle traveling time from 17% to 37% compared with state-of-the-art algorithm.