Simulation-Assignment-Based Travel Time Prediction Model for Traffic Corridors

Abstract

Travel time prediction in Advanced Traveler Information Systems is an important issue, because travel time is a major factor in motorists' decisions to avoid congestion and incidents. A simulation-assignment-based travel time prediction model for traffic corridors is constructed in this paper. Based on the concept of simulation-assignment models, two algorithms-the flowand the vehicle-based models-are proposed for travel time prediction. One of the critical issues in simulation-assignment models is how reliable time-dependent origin-destination (O-D) trip tables are generated. A dynamic O-D estimation and prediction procedure is developed to generate time-dependent O-D demand data for simulating vehicle movements using DynaTAIWAN: a simulation-assignment model. The empirical travel time data that were collected from electronic toll stations are used to validate the travel times that were predicted by the proposed models. The mean absolute percentage errors (RMSPEs) and root-mean-square percentage errors are less than 20% and 26% for the vehicle-based model and less than 10% and 12% for the flow-based model, respectively. The results show that the proposed algorithms predict reasonable travel times for traffic corridors.