PROJECT TITLE :

On-Street and Off-Street Parking Availability Prediction Using Multivariate Spatiotemporal Models

ABSTRACT:

Parking guidance and information (PGI) systems are becoming necessary elements of intelligent transportation systems due to the very fact that cars and infrastructure are becoming additional and more connected. One major challenge in developing economical PGI systems is the uncertain nature of parking availability in parking facilities (each on-street and off-street). A reliable PGI system ought to have the capability of predicting the availability of parking at the arrival time with reliable accuracy. During this paper, we study the character of the parking availability knowledge in a huge town and propose a multivariate autoregressive model that takes into consideration each temporal and spatial correlations of parking availability. The model is employed to predict parking availability with high accuracy. The prediction errors are used to suggest the parking location with the highest probability of having a minimum of one parking spot accessible at the estimated arrival time. The results are demonstrated using real-time parking knowledge in the areas of San Francisco and Los Angeles.