Short Term Intersection Traffic Flow Forecasting

Although there are many tools and online services, such as Google Maps, that can show drivers the roadway traffic conditions in real-time, it’s often too late given that drivers may well be approaching the bottlenecks already. Being able to accurately predict traffic congestions in about a half-hour advance is very critical for advanced trip planning and traffic management. To address this problem, this study is to develop a model that can accurately forecast the traffic conditions at a signalized intersection up to a half-hour in advance. To achieve this goal, existing methods for intersection traffic flow forecasting will be reviewed and synthesized. Cycle by cycle traffic data will be collected from a real-world signalized intersection for model development and evaluation. New models for short term intersection traffic flow forecasting will be developed with different data mining methods. The performance of the developed models will be evaluated based on the collected traffic data, and the one with the best performance will be selected. The developed model can be used for advanced trip planning and traffic management. For example, it can help the freight and logistic companies to better plan their truck dispatching schedules and routes, thereby reduce their operation cost caused by traffic congestion.

Language

• English

Project

• Status: Completed
• Funding: $83334
• Contract Numbers:

  69A3551747133

• Sponsor Organizations:

  Center for Advanced Multimodal Mobility Solutions and Education

  University of North Carolina, Charlotte
  Charlotte, NC  United States  28223

  Office of the Assistant Secretary for Research and Technology

  University Transportation Centers Program
  Department of Transportation
  Washington, DC  United States  20590
• Managing Organizations:

  University of North Carolina, Charlotte

  Department of Civil and Environmental Engineering
  9201 University City Boulevard
  Charlotte, NC  United States  28223-0001
• Project Managers:

  Fan, Wei

• Performing Organizations:

  Texas Southern University, Houston

  3100 Cleburne Street
  Houston, TX  United States  77004
• Principal Investigators:

  Qi, Yi

  Azimi, Mehdi

• Start Date: 20201001
• Expected Completion Date: 20220930
• Actual Completion Date: 20220930

Subject/Index Terms

• TRT Terms: Data mining; Dispatching; Forecasting; Mathematical prediction; Routing; Scheduling; Signalized intersections; Traffic congestion; Traffic flow; Truck traffic
• Subject Areas: Freight Transportation; Highways; Operations and Traffic Management; Planning and Forecasting;

Filing Info

• Accession Number: 01754806
• Record Type: Research project
• Source Agency: Center for Advanced Multimodal Mobility Solutions and Education
• Contract Numbers: 69A3551747133
• Files: UTC, RIP
• Created Date: Oct 17 2020 1:58PM