DVS-RG: Differential Variable Speed Limits Control using Deep Reinforcement Learning with Graph State Representation

TL;DR

This paper introduces DVS-RG, a deep reinforcement learning approach that uses graph-based state representation to optimize variable speed limits, significantly improving traffic flow and safety in simulations.

Contribution

The paper presents a novel DRL method incorporating graph-structured traffic states for dynamic VSL control, enhancing efficiency and safety over existing methods.

Findings

Average waiting time reduced by 68.44%.

Potential collisions decreased by 15.93%.

Outperforms state-of-the-art DRL methods in simulations.

Abstract

Variable speed limit (VSL) control is an established yet challenging problem to improve freeway traffic mobility and alleviate bottlenecks by customizing speed limits at proper locations based on traffic conditions. Recent advances in deep reinforcement learning (DRL) have shown promising results in solving VSL control problems by interacting with sophisticated environments. However, the modeling of these methods ignores the inherent graph structure of the traffic state which can be a key factor for more efficient VSL control. Graph structure can not only capture the static spatial feature but also the dynamic temporal features of traffic. Therefore, we propose the DVS-RG: DRL-based differential variable speed limit controller with graph state representation. DVS-RG provides distinct speed limits per lane in different locations dynamically. The road network topology and traffic information(e.g., occupancy, speed) are integrated as the state space of DVS-RG so that the spatial features can be learned. The normalization reward which combines efficiency and safety is used to train the VSL controller to avoid excessive inefficiencies or low safety. The results obtained from the simulation study on SUMO show that DRL-RG achieves higher traffic efficiency (the average waiting time reduced to 68.44\%) and improves the safety measures (the number of potential collision reduced by 15.93\% ) compared to state-of-the-art DRL methods.