Introduction of a Simple Estimation Method for Lane-Based Queue Lengths with Lane-changing Movements

Abstract

Trafc congestions are increased globally due to rapid urbanization and expedited economic developments in many countries. Vehicle queue is a governing aspect of trafc congestion, studied over the past decades. Most of the existing queue estimation approaches are limited to homogeneous trafc conditions. However, the trafc conditions in many developing countries are heterogeneous and are heavily infuenced by mixed vehicle composition, lane changing, and gap-flling behaviours. This study aims to estimate the queue length at signalized intersections having heterogeneous trafc conditions. The heterogeneity was assimilated with the consideration of Passenger Car Units (PCU) in the measurements of the trafc fow and the lanechanging movement within the considered road section. The infuential factors of the queue length were contemplated with the arrival fow, discharge fow, outbound lane change, inbound lane change, and signal confguration. A Vector Auto Regression (VAR) model was developed to estimate queue length, with a lag time of 15 s for each variable. The results have indicated a higher accuracy in the queue estimation as well as the practical application for prediction, constituting the trafc characteristics of the formed vehicle queue. The R squared of the VAR model was 0.97, along with a Mean Absolute Percentage Error (MAPE) of 21.55%. The model estimation results of right turning lanes were well accurate with MAPE ranging from 15 to 17%, whilst for through movement lanes, accuracy was slightly low with MAPE in the range of 23–26%. The study manifests the functionality of the developed methodology for accurate queue estimations, asserting the practical applicability of VAR models in other locations constituting mixed trafc.