Real-Time Traffic Speed Variability Modeling and Prediction

Traffic condition reliability is very important for developing a robust transportation management and control system and travel time variability. It has been investigated extensively over the past several years. In this paper -- targeting providing more insight into traffic variability -- traffic speed variability is investigated and modeled. In this paper, using traffic speed variability has been computed as the variance of vehicle speeds at a fixed time interval. Then, the traffic speed variance series is modeled using the classical time series models. Real time traffic data that was collected from loop detectors installed on the roadway systems in the United Kingdom has been used for this purpose. Finally, traffic speed variances are predicted in a real-time fashion using the Kalman filter approach constructed from the time series model. Empirical results showed that traffic speed variability can be modeled and predicted reliably.

Language

  • English

Media Info

  • Media Type: Web
  • Features: References;
  • Pagination: pp 528-534
  • Monograph Title: CICTP 2014: Safe, Smart, and Sustainable Multimodal Transportation Systems

Subject/Index Terms

Filing Info

  • Accession Number: 01536314
  • Record Type: Publication
  • ISBN: 9780784413623
  • Files: TRIS, ASCE
  • Created Date: Jul 2 2014 3:02PM