Predicting Coordinated Actuated Traffic Signal Change Times using LSTM Neural Networks

TL;DR

This paper presents a four-step LSTM-based methodology for estimating traffic signal switching times at actuated intersections, improving fuel efficiency by accurately predicting signal changes despite missing data.

Contribution

The study introduces a novel loss function for LSTM models and demonstrates its effectiveness in predicting signal change times under varying traffic conditions.

Findings

Proposed loss function outperforms traditional ones in overall error.

Prediction accuracy varies with horizon and loss function choice.

Method is robust to missing data and applicable to real intersection data.

Abstract

Vehicle acceleration and deceleration maneuvers at traffic signals results in significant fuel and energy consumption levels. Green light optimal speed advisory systems require reliable estimates of signal switching times to improve vehicle fuel efficiency. Obtaining these estimates is difficult for actuated signals where the length of each green indication changes to accommodate varying traffic conditions. This study details a four-step Long Short-Term Memory deep learning-based methodology that can be used to provide reasonable switching time estimates from green to red and vice versa while being robust to missing data. The four steps are data gathering, data preparation, machine learning model tuning, and model testing and evaluation. The input to the models included controller logic, signal timing parameters, time of day, traffic state from detectors, vehicle actuation data, and pedestrian actuation data. The methodology is applied and evaluated on data from an intersection in Northern Virginia. A comparative analysis is conducted between different loss functions including the mean squared error, mean absolute error, and mean relative error used in LSTM and a new loss function is proposed. The results show that while the proposed loss function outperforms conventional loss functions in terms of overall absolute error values, the choice of the loss function is dependent on the prediction horizon. In particular, the proposed loss function is outperformed by the mean relative error for very short prediction horizons and mean squared error for very long prediction horizons.