Paper ThAT13.8
Chen, Huiyu (University of Alberta), Wu, Fan (University of Alberta), Qiu, Tony (University of Alberta)
Urban Arterial Route Travel Time Prediction Using Connected Vehicle Trajectories by Integrating Cloud and Edge Resources
Scheduled for presentation during the Poster Session "Traffic prediction and estimation III" (ThAT13), Thursday, September 26, 2024,
10:30−12:30, Foyer
2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC), September 24- 27, 2024, Edmonton, Canada
This information is tentative and subject to change. Compiled on October 14, 2024
|
|
Keywords Off-line and Online Data Processing Techniques, Simulation and Modeling, Traffic Theory for ITS
Abstract
In recent years, vehicle trajectory data has become increasingly available from connected vehicles (CVs). CVs, acting as mobile sensors, can cover almost every intersection and provide enriched traffic information. In this context, this study proposed a novel statistical model-based method to predict arterial travel time using CV trajectories. The queue clearing time during green time is assumed to follow a Gamma distribution, and a maximized log-likelihood estimation (MLLE) is utilized to calculate related parameters. A hierarchical framework is further developed to improve both prediction accuracy and efficiency. First, the cloud (i.e., Traffic Management Center [TMC]) estimates the CV penetration rate (PR) and calibrates necessary model parameters offline. Then, the network edge (i.e., Mobile Edge Computing [MEC]), conducts the prediction online. A route in the City of Edmonton, Canada, is simulated to test the proposed method. The simulated CVs’ trajectories are collected to estimate the PR and the cycle-by-cycle queue length at intersections. After that, the MEC at each intersection conducts travel time prediction with the parameters obtained from the TMC. The results achieved a low Root Mean Square Error (RMSE) of travel time prediction, averaging 0.9 minutes. Besides, the running time for a one-hour online prediction only costs 2.3 seconds.
|
|