Dilated LSTM Networks for Short-Term Traffic Forecasting using Network-Wide Vehicle Trajectory Data

Short-term traffic forecasting is anticipated as an always evolving research topic, boosted by the tremendous recent advances of Machine Learning and Deep Learning, as well as computational power of modern PCs. In this paper, the Dilated Recurrent Neural Networks are introduced in traffic forecasting. Their architecture promotes the deployment of long-term relations and prevents common issues of RNNs, such as exploding and vanishing gradients. The Dilated LSTM Network is exploited to perform traffic conditions forecasting using network-wide data. The data consist of GPS trajectories of ride-hailing company DiDi's vehicles from November of 2016. After preprocessing the data and organizing them into section's travel speed of five-minute time resolution timeseries for each one of the 498 road sections of the road network of Xi'an, China, we fed them to the Dilated LSTM Network. The model consists of four hidden layers, each of them implementing an LSTM Network with one, two and four-step dilation correspondingly. The model achieves 85% accuracy, which is improved over a classic LSTM structure, trained on the same data.

I. Introduction

Short term forecasting of traffic conditions, meaning how traffic conditions will evolve up to one hour ahead, is vital to efficient traffic management, both for short term decision taking in order to face unexpected incidents and for long term planning of a road network’s operation. In addition, short term traffic flow forecasting is one of the most essential components of Intelligent Transportation Systems (ITS). Practically, in an ITS environment, short term traffic predictions can be incorporated into a traffic signal scheme and enhance traffic management in order to reduce traffic congestion [1]. Moreover, most navigating systems, which are core technology of ITS, are mainly dependent on traffic predictions [2]. The above-mentioned aim to improve the level of service of any urban transportation system and make it more sustainable, reliable and efficient in terms of cost, time waste, fuel consumption, environmental friendliness, safety etc. [3].