01555302

Component

https://doi.org/10.3141/2500-07

In a connected-vehicle environment, wireless subsecond data exchange connects vehicles, the infrastructure, and travelers’ mobile devices. These data have the promise to transform the geographic scope, precision, and latency of transportation system control; fulfillment of that promise could result in significant safety, mobility, and environmental benefits. However, the new data influx also has the potential to overburden legacy computational and communication systems. Although connected-vehicle technology can facilitate ubiquitous system coverage, the existing prediction methods, computational platforms, and data management methods are insufficient to process the data within a reasonable time frame for real-time predictions. An investigation of the ways in which advanced (big-data) analytics might be applied to realize the full potential of connected-vehicle technology is particularly relevant now as this technology evolves from research to deployment. This paper presents an approach combining big-data graph analytics with high-performance computing to predict traffic congestion by analyzing nearly 4 billion basic safety messages generated by the safety pilot model deployment conducted in 2012–2013. This paper provides an alternative approach for predicting congestion in 30.5-m segments anywhere on the network at 1-min intervals 30 to 60 min before actual congestion over a time window of 1 h. Despite sparseness of data, the proposed framework predicted highly congested locations 40% of the time. Severity of congestion was predicted with an accuracy of 77%. This combination of rapid computation and predictive accuracy may provide significant value in future real-time decision support systems that leverage connected-vehicle data.

01595984

15-5763

English

pp 59–66

2015

Transportation Research Record: Journal of the Transportation Research Board

9780309369558

Print

Figures (6) ; References (16) ; Tables (2)

Highway safety; Methodology; Mobile communication systems; Traffic congestion; Traffic forecasting

Big data; Graph analytics

Ann Arbor (Michigan)

Data and Information Technology; Highways; Planning and Forecasting

TRIS, TRB, ATRI

Dec 30 2014 1:56PM

• Comprehensive Analysis of the Built Environment Through the Introduction of Induced Impacts via Transportation: Detailed Case Study for the Urban Region of Munich, Germany
• Cycling to High School in Toronto, Ontario, Canada: Exploration of School Travel Patterns and Attitudes by Gender
• Designing the Modern Multimodal Urban Arterial: Case Study of the Webster Avenue Bus Rapid Transit Project
• Effects of Jobs–Residence Balance on Commuting Patterns: Differences in Employment Sectors and Urban Forms
• Implications of Changing Dynamics for Metered On-Street Parking: Washington, D.C., Case Study
• Influences of Neighborhood Characteristics and Personal Attitudes on University Commuters’ Public Transit Use
• Institutional Labyrinth: Beyond Establishing Lead Urban Transport Institutions
• Investigating the Role of Built Environment and Lifestyle Choices in Active Travel for Weekly Home-Based Nonwork Trips
• Is Sprawl Affordable for Americans? Exploring the Association Between Housing and Transportation Affordability and Urban Sprawl
• Methodology to Gather Multimodal Urban Trip Generation Data
• Office Rent Premiums with Respect to Light Rail Transit Stations: Case Study of Dallas, Texas, with Implications for Planning of Transit-Oriented Development
• Predicting Travel Impacts of New Development in America’s Major Cities: Testing Alternative Trip Generation Models
• Short- and Long-Term Effects of Land Use on Reducing Personal Vehicle Miles of Travel: Longitudinal Multilevel Analysis in Austin, Texas
• Strategies to Improve or Optimize Practices for Acquisition of Real Property
• Traffic Generated by Mixed-Use Developments: Thirteen-Region Study Using Consistent Measures of Built Environment
• Urban Streetscape Design and Crash Severity