•  
  •  
 

Journal of System Simulation

Abstract

Abstract: To address the issues of uneven traffic flow at urban intersections, limited road capacity, and the poor coordination of existing traffic signal control algorithms, a traffic signal control algorithm based on graph convolutional reinforcement learning was proposed. By utilizing a multilayer perceptron, the dynamic features of vehicles and phase information at the controlled intersection and its neighboring intersections were extracted. A graph convolutional neural network was then employed to aggregate these vehicle dynamic features into potential features representing regional traffic. The control strategy was derived through multiple iterations of an improved twin delayed deep deterministic policy gradient (TD3) algorithm. This control strategy was applied to the traffic phase timing of the urban road network, aiming to maximize the traffic efficiency of the road network. Simulation experiments demonstrate that the algorithm can adapt to dynamically changing and complex road network environments. Moreover, the control effect is significant under high saturation flow, effectively improving the traffic efficiency of the road network and alleviating congestion at intersections during peak hours.

First Page

2568

Last Page

2577

CLC

TP391.9

Recommended Citation

Huang Deqi, Tu Yating, Zhang Zhenhua, et al. Modeling and Simulation of Traffic Signal Control Based on MLP with Improved GCN-TD3[J]. Journal of System Simulation, 2025, 37(10): 2568-2577.

Corresponding Author

Tu Yating

DOI

10.16182/j.issn1004731x.joss.24-0523

Download

Share

COinS