A Comprehensive Evaluation of Deep Learning-Based Techniques for Traffic Prediction

Abstract

Deep learning-based techniques are the state of the art in road traffic prediction or forecasting. Several deep neural networks have been proposed to predict the traffic but they have not been evaluated under common datasets. Current studies analyze their capacity to predict road traffic in general but do not focus on their capacity to predict the formation of congestions. This is critical for avoiding congestions or mitigate their negative impact. This paper progresses the current state of the art by presenting a comprehensive comparison of the state-of-the-art deep neural networks for road traffic prediction. The comparison is conducted using the same real traffic datasets, and under normal and congested traffic conditions. The evaluation includes new deep neural networks and error recurrent models. Our study first demonstrates that accurately predicting the traffic overall does not imply that a deep neural network can accurately predict the traffic when congestions are being formed. This reinforces the idea that prediction techniques must also be evaluated under congestion conditions. Our analysis also shows that exploiting the spatiotemporal evolution of the traffic (and not just the temporal one) provides better prediction accuracy overall and in particular under congestion conditions. The study also demonstrates that error recurrent models outperform deep neural networks that do not utilize an error feedback both under normal and congested traffic conditions. In particular, our study shows that the error recurrent model eRCNN is the deep learning technique that achieves to date the best traffic prediction accuracy. It is also important emphasizing that error recurrent models achieve better prediction accuracy with shallower neural networks and therefore lower computational cost.