01552837

Component

This study aims to address the problem of short-term traffic prediction on freeway by using a mixture auto-regressive model (MAR). Short-term traffic prediction plays a fundamental role in traffic control system and provides valuable information to commuters and decision makers. The goal is to provide both point and interval estimates of the traffic flow in a near future by fitting the MAR model on historical data. It is known that, on urban freeways, traffic flow is mainly contributed by the commute trips and exhibits transition between on and off-peak regimes. However, most of the existing short-term prediction models ignore the transition behavior and thus mischaracterize the traffic dynamics as being identical for both off and on-peak periods. Here, the authors build a reliable prediction model that takes into account the dynamics of the traffic system. The proposed mixture model is able to explain the heteroscedasticity in traffic flow data and explicitly account for the switching of modes.

This paper was sponsored by TRB committee ABJ30 Urban Transportation Data and Information Systems.

01550057

15-0293

English

16p

2015

Transportation Research Board 94th Annual Meeting

Digital/other

Figures; References; Tables

Heteroscedasticity; Mathematical models; Time intervals; Time series; Traffic flow; Traffic forecasting

Autoregressive models

Irvine (California)

Data and Information Technology; Highways; I72: Traffic and Transport Planning

Transportation Research Board Annual Meeting 2015 Paper #15-0293

TRIS, TRB, ATRI

Dec 30 2014 12:14PM