Increasing congestion challenges call for better utilization of existing infrastructure by opting for data-driven and cost-effective solutions. Intelligent transportation systems (ITS)-based solution like the variable speed limit (VSL) is a popular advanced data-driven solution to enhance mobility and safety by harmonizing speeds along a road. Prior to allocating resources to a road, a thorough analysis of travel and speed patterns is needed. This paper focuses on investigating road link-level data to identify the threshold of speeds for different peak hours and, thereby, investigating potential parameters influencing the speed of road links. Multivariate clustering analysis was first used to identify potential road links susceptible to speed variation for the implementation of VSL. A supervised machine learning algorithm, forest-based classification and regression, was then used to model and examine the influence of the average annual daily traffic (AADT), the historical speed of the road link, and the average speeds of upstream and downstream road links on the average speed of corresponding road link. Modeling and validation were performed using morning and evening peak hour data for Mecklenburg County, North Carolina, USA, for all the road links as well as for road links with low- and high-speed variation.
Investigating Road Link-Level Data during Peak Hours to Identify Potential Areas for Implementing Variable Speed Limit Signs
International Conference on Transportation and Development 2021 ; 2021 ; Virtual Conference
2021-06-04
Conference paper
Electronic Resource
English
Taylor & Francis Verlag | 2024
|European Patent Office | 2024
|Effects of variable speed limit signs on speed behaviour and recall of signs
Online Contents | 1998
|Speed variation during peak and off-peak hours on urban arterials in Shanghai
Online Contents | 2016
|