Time-to-Green predictions for fully-actuated signal control systems with supervised learning

TL;DR

This paper develops a machine learning-based framework to predict signal phase durations in fully-actuated traffic control systems, improving prediction accuracy over traditional methods and aiding traffic management.

Contribution

It introduces a novel time series prediction approach using ML models specifically for fully-actuated systems, which are more complex to predict than semi-actuated ones.

Findings

ML models outperform naive baselines

Random Forest achieves highest accuracy

Models meet practical application requirements

Abstract

Recently, efforts have been made to standardize signal phase and timing (SPaT) messages. These messages contain signal phase timings of all signalized intersection approaches. This information can thus be used for efficient motion planning, resulting in more homogeneous traffic flows and uniform speed profiles. Despite efforts to provide robust predictions for semi-actuated signal control systems, predicting signal phase timings for fully-actuated controls remains challenging. This paper proposes a time series prediction framework using aggregated traffic signal and loop detector data. We utilize state-of-the-art machine learning models to predict future signal phases' duration. The performance of a Linear Regression (LR), a Random Forest (RF), and a Long-Short-Term-Memory (LSTM) neural network are assessed against a naive baseline model. Results based on an empirical data set from a fully-actuated signal control system in Zurich, Switzerland, show that machine learning models outperform conventional prediction methods. Furthermore, tree-based decision models such as the RF perform best with an accuracy that meets requirements for practical applications.