Estimation and prediction of freeway traffic congestion propagation using tagged vehicle positioning data

Abstract

Effective estimation and prediction of freeway congestion propagation is the basis for formulating a traffic management strategy. A new estimation and prediction model for congestion propagation based on coordinated vehicle positioning data collected from fixed detectors is proposed. A shockwave-based method is established to model the propagation trajectory of congestion in time and space using data filtered by the Savitzy-Golay. Bayesian ridge regression is applied to determine the probability range of the propagation path of the congestion. The proposed method was tested with Wi-Fi positioning data from a section of the Beijing-Kunming Freeway in China. The results of our method were compared with filed traffic conditions estimated by loop data. The results show a difference of approximately 200s between the start time of the estimated congestion and the observed time on the selected road section. The predicted congestion start time differs from the observed results by around 100s.

KEYWORDS:

• Traffic congestion propagation
• shockwave estimation
• congestion prediction
• tagged vehicle positioning data
• Bayesian ridge regression

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Funding

This work was supported by National Natural Science Foundation of China [grant number 52002030]; Humanities and Social Sciences Foundation of the Ministry of Education [grant number 20XJCZH011]; Natural Science Foundation of Shannxi Province [grant number 2021JQ-256]; Humanities and Social Sciences Foundation of Shannxi Province [grant number 2020R035]; Fundamental Research Funds for the Central Universities CHD [grant number 300102341676], [grant number 300102342105], Opening Foundation of Zhejiang Intelligent Transportation Engineering Technology Research Center (2021ERCITZJ-KF04); Foundation of Power China Northwest Engineering Corporation Limited (2023610002003846).