Exploring the Efficacy of Large-Scale Connected Vehicle Data in Real-Time Traffic Applications

Abstract

Transportation agencies strive to optimize their spending on data collection by exploring efficient techniques that provide reliable traffic data. In recent years, the automobile industry has experienced vast developments in wireless technology that enables agencies to collect valuable traffic data in large volumes from connected vehicles (CVs). Unlike traditional data collection techniques, the CV or probe data are economically feasible for wide-area coverage. Therefore, this study aims to explore the CV data provided by Wejo Connected Vehicle Data Solutions for their feasibility in real-time traffic applications. The large volumes of the CV data are compared against a ground reference sensor to assess their reliability. The performance metrics such as market penetration rates, speed bias, and latency are used to understand the efficacy of the data for their usage over infrastructure-mounted sensors in regular traffic operations. The analysis resulted in an average market penetration of 6.3% in the study area with a mean speed error of less than 1 mph. The data also expressed potential event detection capabilities with relatively lower latencies. Furthermore, latent class models are developed on the penetration rate and speed bias data sets to identify the unobserved groups within the data, resulting in five-class models for both data sets. The paper concludes by summarizing the potential benefits of the CV data concerning the assessed metrics and provides opportunities to replace or augment the data to existing infrastructure-mounted traffic sensors.