Abstract:
The framework and field application of a simulation-based online system for travel time prediction are presented. The proposed system is designed to contend with most critical issues associated with real-time operations, which include estimation of missing volumes, detection of incidents, data filtering, and computation of traffic volumes for projected time intervals so as to activate the simulation function. The proposed system was deployed on two routes of 30 mi between Salisbury and Ocean City, Maryland, with a total of 10 detectors. The preliminary application results clearly indicate that with proper integration the proposed system offers a cost-effective tool for real-time travel time prediction.
