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


Loading...

Date

2022-08-24

Publication Type

Working Paper

ETH Bibliography

yes

Citations

Altmetric

Data

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.

Publication status

published

Editor

Book title

Journal / series

Volume

Pages / Article No.

2208.11344

Publisher

Cornell University

Event

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Signal Phase and Timing (SPaT); Time series forecasting; Supervised learning; Actuated traffic signal control

Organisational unit

08686 - Gruppe Strassenverkehrstechnik check_circle
02655 - Netzwerk Stadt u. Landschaft ARCH u BAUG / Network City and Landscape ARCH and BAUG

Notes

Funding: NYUAD Research Institute Award CG001.

Funding

ETH-27 16-1 - SPEED - Rethinking speed limits in urban networks (ETHZ)

Related publications and datasets