Return to the VTRC Home Page
Click here to print the printer friendly version of this page.
Page Title: VTRC Report Detail

The contents of this report reflect the views of the author(s), who is responsible for the facts and the accuracy of the data presented herein. The contents do not necessarily reflect the official views or policies of the Virginia Department of Transportation, the Commonwealth Transportation Board, or the Federal Highway Administration. This report does not constitute a standard, specification, or regulation. Any inclusion of manufacturer names, trade names, or trademarks is for identification purposes only and is not to be considered an endorsement.


Traffic Flow Forecasting for Intelligent Transportation Systems
Michael J. Demetsky
Brian L. Smith
Year: 1995
VTRC No.: 95-R24
Abstract: The capability to forecast traffic volume in an operational setting has been identified as a critical need for intelligent transportation systems (ITS). In particular, traffic volume forecasts will directly support proactive traffic control and accurate travel time estimation. However, previous attempts to develop traffic volume forecasting models have met with limited success. This research focused on developing such models for two sites on the Capital Beltway in Northern Virginia. Four models were developed and tested for the single-interval forecasting problem, which is defined as estimating traffic flow 15 min into the future. The four models were the historical average, time series, neural network, and nonparametric regression models. The nonparametric regression model significantly outperformed the others. Based on its success on the single-interval forecasting problem, the nonparametric regression approach was used to develop and test a model for the multiple-interval forecasting problem. This problem is defined as estimating traffic flow for a series of time periods into the future in 15-min intervals. The model performed well in this application. In general, the model was portable, accurate, and easy to deploy in a field environment. Finally, an ITS system architecture was developed to take full advantage of the forecasting capability. The architecture illustrates the potential for significantly improved ITS services with enhanced analysis components, such as traffic volume forecasting.