Predicting Congestion States from Basic Safety Messages by Using Big-Data Graph Analytics

Abstract

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.

Assessing Surrogate Safety Measures using a Safety Pilot Model Deployment Dataset

“…SPMD data have been applied in studies on transportation planning, traffic volume/congestion estimation, and extreme events identification ( 28–32 ). Deering processed spatial aggregation of trips into origin and destination zones for transportation planning by organizing SPMD data (basic safety message and driving data) into a trip-level dataset ( 28 ).…”

“…Deering processed spatial aggregation of trips into origin and destination zones for transportation planning by organizing SPMD data (basic safety message and driving data) into a trip-level dataset ( 28 ). Vasudevan et al predicted congestion states from BSMs by using big-data graph analytics ( 31 ), and Zheng et al used SPMD data to estimate traffic volumes for signalized intersections ( 32 ). The authors in Zheng’s study developed an approach to estimate traffic volume using GPS trajectory data from connected vehicle (CV) devices under low market penetration rates ( 32 ).…”

Breakdown Prediction Utilizing Data Mining Algorithms in Combination With Performance Measures Derived From Connected Vehicle Data

“…For urban street segments, however, this data quality cannot be achieved until the market penetration of CV exceeds 10%-15%. (Vasudevan et al 2015) summarized a method to estimate the travel time and back of queue location using CV data. This research provided an alternative approach for predicting congestion by combining big-data analytics for analyzing nearly 4 billion BSM generated by the safety pilot model.…”

Data Infrastructure for Connected Vehicle Applications

“…Wang et al used the RANSAC algorithm to detect the departure shockwave and estimated the shockwave speed and saturation flow rate at signalized intersections ( 8 ). Vasudevan et al used sparse BSMs to predict the congestion state with a high temporal and spatial resolution ( 14 ).…”