Speed Advisory System Using Real-Time Actuated Traffic Light Phase Length Prediction

TL;DR

This paper presents a real-time prediction algorithm for actuated traffic light phases that enhances speed advisory systems, leading to significant fuel savings and improved traffic flow at signalized intersections.

Contribution

The paper introduces a novel algorithm for predicting actuated traffic light phases using traffic data, improving fuel efficiency and traffic progression in connected vehicle systems.

Findings

95% prediction accuracy of signal phases

Up to 30% reduction in fuel consumption

20% improvement in traffic progression at peak times

Abstract

Speed advisory systems for connected vehicles rely on the estimation of green (or red) light duration at signalized intersections. A particular challenge is to predict the signal phases of semi- and fully-actuated traffic lights. In this paper, we introduce an algorithm that processes traffic measurement data collected from advanced detectors on road links and assigns "PASS"/"WAIT" labels to connected vehicles according to their predicted ability to go through the upcoming signalized intersection within the current phase. Additional computations provide an estimate for the duration of the current green phase that can be used by the Speed Advisory System to minimize fuel consumption. Simulation results show 95% prediction accuracy, which yields up to 30% reduction in fuel consumption when used in a driver-assistance system. Traffic progression quality also benefits from our algorithm demonstrating an improvement of 20% at peak for medium traffic demand, reducing delays and idling at intersections.