Analysis on Sag Bottleneck Phenomena Based on Multiclass Traffic State Estimation

Abstract

Abstract This study proposes a novel technique for analyzing traffic dynamics based on multiclass traffic state estimation. One of the most common causes of bottlenecks on Japan’s roads are sags. Considerable scientific attention has been paid to the bottleneck phenomena at sags in terms of both their microscopic and macroscopic aspects. However, the mechanisms of traffic breakdown at sags are not understood in detail yet. This paper presents a data assimilation system using a particle filter in which online observations from fixed detectors and probe vehicles are combined with multiclass traffic flow simulations to analyze the traffic dynamics that contribute to congestion at sags. The application of a particle filter enables the monitoring of the hidden traffic state described by the unobservable parameters of traffic flow models. On the application of this method to an existing sag bottleneck section, we found that i) the estimation results are a good fit to observation data from both fixed detectors and probes, ii) the integrated use of multiple data source enables estimation accuracy to be improved, iii) the traffic capacity of the upgrade section is lower than that of the other sections and this tendency is more marked for heavy vehicles than for regular vehicles.