PDLight: A Deep Reinforcement Learning Traffic Light Control Algorithm with Pressure and Dynamic Light Duration

TL;DR

PDLight is a deep reinforcement learning-based traffic light control algorithm that optimizes signal timing by considering vehicle pressure and lane capacity, reducing travel time at urban intersections.

Contribution

This paper introduces PDLight, a novel DRL algorithm with a new reward function PRCOL that improves traffic signal control by incorporating lane capacity considerations.

Findings

Lower average travel time compared to state-of-the-art algorithms

Effective under both fixed and dynamic green light durations

Validated with synthetic and real-world datasets

Abstract

Existing ineffective and inflexible traffic light control at urban intersections can often lead to congestion in traffic flows and cause numerous problems, such as long delay and waste of energy. How to find the optimal signal timing strategy is a significant challenge in urban traffic management. In this paper, we propose PDlight, a deep reinforcement learning (DRL) traffic light control algorithm with a novel reward as PRCOL (Pressure with Remaining Capacity of Outgoing Lane). Serving as an improvement over the pressure used in traffic control algorithms, PRCOL considers not only the number of vehicles on the incoming lane but also the remaining capacity of the outgoing lane. Simulation results using both synthetic and real-world data-sets show that the proposed PDlight yields lower average travel time compared with several state-of-the-art algorithms, PressLight and Colight, under both fixed and dynamic green light duration.