Congestion Prediction in Transportation Networks

Accurate real-time traffic prediction has a key role in traffic management strategies and intelligent transportation systems. Building a prediction model for transportation networks is challenging because spatio-temporal dependencies of traffic data in different roads are complex and the graph constructed from road networks is very large. It is computationally expensive to build and run a prediction algorithm for the whole network.

Our work in this area combines ideas from data science and signal processing on the space-time graph that describes the evolution of travels times over road segments. We use spatio-temporal clustering to split the graph into multiple connected disjoint subgraphs. Within each subgraph we use a Graph Signal Processing (GSP)  to decouple spatial dependencies and obtain independent time series in graph frequency domain. We make predictions along independent graph frequencies using adaptive ARMA models and later transform the predicted time series along each graph frequency to the subgraph vertex domain. Evaluation of our model on an extensive dataset of fine-grained highway travel times in the Dallas-Fort Worth area shows substantial improvement achieved by our proposed method compared to existing methods.

Team and Collaborators

  • Byron Chigoy (Texas A&M Transportation Institute)
  • Prof. Nick Duffield (Electrical and Computer Engineering)
  • Arman Hasanzadeh (PhD student, Electrical and Computer Engineering)
  • Xi Liu (PhD student, Electrical and Computer Engineering)
  • Prof. Krishna Narayanan (Electrical and Computer Engineering)
  • Shawn Turner (Texas A&M Transportation Institute)

Funding

  • [NSF 2018b] EAGER: Real-Time: Learning-Mediated Control for Traffic Shaping, National Science Foundation, Award 1839816, 10/1/2018-9/30/2020, PI N. Duffield, Co-PI’s, K. Narayanan, S. Shakkottai, A. Talebpour,  Total $300,000 / Duffield $75,000
  • Improving Understanding of 
Travel Behavior and Transportation Systems through Big Data Analytics, Texas A&M Big Data Seed Grant, January 2016, PI: Shawn Turner (Texas A&M Transportation Institute) co-PI: N. Duffield. Total $50,000 / Duffield $25,000

Publications and Talks