Traffic Flow Prediction Using Optimal Autoregressive Moving Average with Exogenous Input-Based Predictors

Abstract

Traffic management centers want to improve the performance of road networks and reduce congestion by actively managing the infrastructure of a freeway corridor. A promising avenue for proactive traffic management is the prediction of near-future traffic conditions in real time by using a traffic flow model. Important calibration parameters of such a model include boundary flows (i.e., amount of traffic expected to enter the network during the prediction horizon). A boundary flow prediction method is proposed that combines the most recent traffic data with historical traffic data. An autoregressive moving average with an exogenous input (ARMAX) model is estimated online with the most recent vehicle detector station data. An optimal multiple-step-ahead predictor of traffic demand is obtained from the estimated ARMAX model by solving a corresponding Bezout equation for each predictor. Results obtained with empirical data collected along a freeway mainline and an on-ramp indicate that this method outperforms prediction methods that rely on only the historical average of the data, especially during days with unusual traffic flow demands, such as a Super Bowl Sunday. The simplicity and robustness make this method useful in practical applications.