Short Term Travel Time Prediction on Freeways in Conjunction with Detector Coverage Analysis

As the technological complexities of and public demands upon our Intelligent Transportation Systems (ITS) infrastructure increase, new opportunities and requirements arise regarding how best to manage existing ITS assets and select future deployments. This research project aims to support such decision making by developing methods that clearly relate sensor coverage (and other ITS data sources) to Dynamic Message Sign (DMS) performance via algorithms that predict freeway traffic time. The report documents the research conducted as a part of this project. A detailed literature review of the state-of-the-art and the state of the practice in travel time prediction has been conducted and some of the limitations of the existing models have been identified. Two innovative travel time prediction models have been proposed and their performance has been tested with both simulation and real data. Both of these models use as input traffic counts obtainable from single loop detectors, which are the most widely deployed traffic sensor. The first model is based on an integrated statistical simulation framework and the second model is based on comparing cumulative counts. Methodologies have been developed to arrive at optimal detector location and spacing for better travel time prediction. Some of the issues involved in real-time deployment have been studied and summarized.

Language

  • English

Media Info

  • Media Type: Web
  • Edition: Technical Report
  • Features: Appendices; Figures; Photos; References; Tables;
  • Pagination: 140p

Subject/Index Terms

Filing Info

  • Accession Number: 01099055
  • Record Type: Publication
  • Report/Paper Numbers: 'FHWA/TX-08/0-5141-1, Report No. 0-5141-1
  • Contract Numbers: Project 0-5141
  • Files: TRIS, USDOT, STATEDOT
  • Created Date: May 15 2008 3:47PM