A GAN-Based Short-Term Link Traffic Prediction Approach for Urban Road Networks Under a Parallel Learning Framework

Road link speed is often employed as an essential measure of traffic state in the operation of an urban traffic network. Not only real-time traffic demand but also signal timings and other local planning factors are major influential factors. This paper proposes a short-term traffic speed prediction approach, called PL-WGAN, for urban road networks, which is considered an important part of a novel parallel learning framework for traffic control and operation. The proposed method applies Wasserstein Generative Adversarial Nets (WGAN) for robust data-driven traffic modeling using a combination of generative neural network and discriminative neural network. The generative neural network models the road link features of the adjacent intersections and the control parameters of intersections using a hybrid graph block. In addition, the spatial-temporal relations are captured by stacking a graph convolutional network (GCN), a recurrent neural network (RNN), and an attention mechanism. A comprehensive computational experiment was carried out including comparing model prediction and computational performances with several state-of-the-art deep learning models. The proposed approach has been implemented and applied for predicting short-term link traffic speed in a large-scale urban road network in Hangzhou, China. The results suggest that it provides a scalable and effective traffic prediction solution for urban road networks.

Automated summary

This paper proposes a short-term traffic speed prediction approach, called PL-WGAN, which uses Wasserstein Generative Adversarial Nets (WGAN) for data-driven traffic modeling. The proposed method combines generative and discriminative neural networks and captures spatial-temporal relations by stacking multiple neural networks. The results of the experiment demonstrate that this approach provides a scalable and effective traffic prediction solution for urban road networks.