An Empirical Model of Occupancy-Queue Relation

Abstract

One of the key indicators of traffic control quality in urban traffic control (UTC) systems is the queue length. Even in unsaturated conditions, longer queues indicate longer travel delays and higher fuel consumption. With the exception of some expensive surveillance equipment, the queue length itself cannot be measured directly. Many methods that estimate the queue length from detector measurements are used in engineering practice, ranging from simple to elaborate ones. The proposed method is based on Gaussian process (GP) model of the occupancy-queue relationship. It can handle data uncertainties and provides more information about the quality of the queue length prediction.

Modelling Occupancy-Queue Relation Using Gaussian Process

“…Another approach has been taken in [29], where the authors start with thorough theoretical analysis of the time-occupancy measurements and follow with a Kalman filter implementation of vehicle count estimator in the follow-up paper [40]. In our publication [30] we presented an empirical time-occupancy based queue-length model which combines two separate Gaussian-process (GP) models for the low and high occupancy ranges.…”