Short-Term Traffic Volume Prediction for Sustainable Transportation in an Urban Area

Abstract

Accurate short-term traffic volume prediction is essential for the realization of sustainable transportation as providing traffic information is widely known as an effective way to alleviate congestion. In practice, short-term traffic predictions require a relatively low computation cost to perform calculations in a timely manner and should be tolerant to noise. Traffic measurements of variable quality also arise from sensor failures and missing data. There is no optimal prediction model so far fulfilling these challenges. This paper proposes a so-called absorbing Markov chain (AMC) model that utilizes historical traffic database in a single time series to carry out predictions. This model can predict the short-term traffic volume of road links and determine the rate in which traffic eases once congestion has occurred. This paper uses two sets of measured traffic volume data collected from the city of Enschede, Netherlands, for the training and testing of the model, respectively. The main advantages of the AMC model are its simplicity and low computational demand while maintaining accuracy. When compared with the established seasonal autoregressive integrated moving average (ARIMA) and neural network models, the results show that the proposed model significantly outperforms these two established models.