Expressway Vehicle Arrival Time Estimation Algorithm Based on Electronic Toll Collection Data

Precise travel time prediction benefits travelers and traffic managers by enabling anticipation of future roadway conditions, thus aiding in pre-trip planning and the development of traffic control strategies. This approach contributes to reducing travel time and alleviating traffic congestion issue...

Full description

Saved in:
Bibliographic Details
Published in:Sustainability 2024-07, Vol.16 (13), p.5581
Main Authors: Lai, Shukun, Xu, Hongke, Luo, Yongyu, Zou, Fumin, Hu, Zerong, Zhong, Huan
Format: Article
Language:English
Subjects:
Air quality management
Aircraft
Algorithms
Emissions
Genetic algorithms
Neural networks
Regression analysis
Roads & highways
Tolls
Traffic congestion
Traffic control
Traffic flow
Transportation planning
Travel
Travelers
Vehicles
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Precise travel time prediction benefits travelers and traffic managers by enabling anticipation of future roadway conditions, thus aiding in pre-trip planning and the development of traffic control strategies. This approach contributes to reducing travel time and alleviating traffic congestion issues. To achieve real-time state perception of vehicles on expressways, we propose an algorithm to estimate the arrival time of vehicles in the next segment using Electronic Toll Collection (ETC) data. Firstly, the characteristics of ETC data and GPS data are meticulously described. We devise algorithms for data cleaning and fusion, subsequently segmenting the vehicle journey into multiple sub-segments. In the following step, feature vectors are constructed from the fused data to detect service areas and analyze the expressway segment characteristics, vehicle traits, and the influence of service areas. Finally, an algorithm utilizing LightGBM is introduced for estimating the arrival time of vehicles at various segments, corroborated by empirical tests using authentic traffic data. The MAE of the algorithm is recorded as 20.1 s, with an RMSE of 32.6 s, affirming its efficacy. The method proposed in this paper can help optimize transportation systems for improving efficiency, alleviating congestion, reducing emissions, and enhancing safety.
ISSN:2071-1050
2071-1050
DOI:10.3390/su16135581