Short-Term Travel Time Prediction for Congested Urban Road Networks

Prediction of short-term future traffic condition on real-time basis is important as it can allow travelers to avoid traffic congestion and react to the traffic incidents immediately after they occur. In this paper, a solution algorithm is proposed for short-term travel time prediction in congested urban roads of Hong Kong. The travel times in the next five-minute interval are predicted by using the historical travel time estimates together with their updated temporal variance-covariance relationships. The historical travel times are estimated by a real-time travel information system (RTIS) using the automatic vehicle identification data available in Hong Kong. Observation surveys are conducted on a selected path in Hong Kong urban area to validate the travel times predicted by the proposed algorithm. With the use of the same set of historical travel time estimates, comparison is also made to the forecasting results of the other two methods: the k-nearest neighorhood and historical average. The results show that the proposed algorithm could predict satisfactorily the travel times for the study periods with the minimum mean absolute errors and mean absolute percentage errors. Moreover, it was found that use of the updated temporal variance-covariance relationships of travel times can greatly improve the accuracy of the short-term travel time prediction.

• Corporate Authors:

  Transportation Research Board

  500 Fifth Street, NW
  Washington, DC  United States  20001
• Authors:
  • Tam, Mei Lam
  • Lam, William H. K.
• Conference:
  • Transportation Research Board 88th Annual Meeting
  • Location: Washington DC, United States
  • Date: 2009-1-11 to 2009-1-15
• Date: 2009

Language

• English

Media Info

• Media Type: DVD
• Features: Figures; Photos; References; Tables;
• Pagination: 16p
• Monograph Title: TRB 88th Annual Meeting Compendium of Papers DVD

Subject/Index Terms

• TRT Terms: Advanced traveler information systems; Incident management; Information technology; Operations; Real time information; Traffic congestion; Traffic forecasting; Traffic incidents; Travel time; Traveler information and communication systems; Urban highways
• Geographic Terms: Hong Kong (China)
• Subject Areas: Highways; Operations and Traffic Management; I73: Traffic Control;

Filing Info

• Accession Number: 01126659
• Record Type: Publication
• Report/Paper Numbers: 09-2313
• Files: TRIS, TRB
• Created Date: Apr 17 2009 9:56AM