Traffic Estimation for Proactive Freeway Traffic Control

Abstract

Many operating agencies are developing computerized traffic management systems that support traffic operations as part of intelligent transportation system (ITS) user service improvements. To facilitate the prediction, diagnosis, and control decisions made with uncertain information, several numerical analysis methods are available for predictive traffic control. However, these methods cannot predict short-term traffic demand accurately. A neural network approach was proposed to improve short-term traffic demand prediction for the development of advanced traffic control strategies. A promising neural network approach to improving demand prediction and traffic data modeling to support proactive traffic control was examined. Specifically, the use of time-series detector data from a real-world freeway management system that were processed through neural network models was analyzed and the results were compared with real-world observations. In all cases, the proposed neural network approach can successfully predict traffic demand patterns. The proposed study approach of combining both neural networks and error correction was found to be promising for traffic prediction. Once the neural nets are successfully trained, the system can quickly pick up traffic demand trends for proactive traffic demand management. The error correction algorithm can further smooth out errors that may be caused by sharp neural net prediction.