Developing Predictive Border Crossing Delay Models

Increased demand for international travel along with tighter security have increased border wait times.

In recent years, and as a result of the continued increase in travel demand across the border coupled with the need for tighter security and inspection procedures after September 11, border crossing delay has become a critical problem with tremendous economic and social costs. 

This project aims at taking advantage of the wealth of data, now available thanks to the recent advances in sensing and communications, to develop predictive models which can be used to predict the delay a passenger car or a truck is likely to encounter by the time the vehicle arrives at the border.

The project, which is building on some initial work done by UB TransInfo researchers, breaks down the problem into two steps: (1) the short-term prediction of the hourly traffic volume at the border; and (2) the development of queueing models which predict delay given knowledge of the predicted volume from step 1, the number of customs inspection stations open, and the distribution of service and inter-arrival times.  The project will also develop mechanisms to adjust delay predictions in real-time, and will validate the predictions against blue-tooth data from the Niagara Frontier borders.

Partners: Peace Bridge Authority, Niagara Falls Bridge Commission, and the Niagara International Transportation Technology Coalition (NITTEC)

Data Sources: (1) Historical hourly traffic volume datasets available from the Peace Bridge Authority and the Niagara Falls Bridge Commission; (2) blue-tooth measurements of queue delay.