A conditional Bayesian delay propagation model for large-scale railway traffic networks

Zhang, Y; Li, R; Guo, T; Li, Z; Wang, Y; Chen, F

A conditional Bayesian delay propagation model for large-scale railway traffic networks

Zhang, Y Li, R Guo, T

Li, Z

Wang, Y Chen, F

Permalink

Publication Type:: Conference Proceeding
Citation:: Australasian Transport Research Forum, ATRF 2019 - Proceedings, 2019, pp. 1-12
Issue Date:: 2019-01-01

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Download Published versionAdobe PDF (847.77 kB)

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Zhang, Y
dc.contributor.author	Li, R
dc.contributor.author	Guo, T https://orcid.org/0000-0001-5130-3237
dc.contributor.author	Li, Z https://orcid.org/0000-0002-0784-157X
dc.contributor.author	Wang, Y
dc.contributor.author	Chen, F
dc.date	2019-09-30
dc.date.accessioned	2020-06-12T09:01:28Z
dc.date.available	2020-06-12T09:01:28Z
dc.date.issued	2019-01-01
dc.identifier.citation	Australasian Transport Research Forum, ATRF 2019 - Proceedings, 2019, pp. 1-12
dc.identifier.uri	http://hdl.handle.net/10453/141390
dc.description.abstract	© 2019 Australasian Transport Research Forum, ATRF 2019 - Proceedings. All rights reserved. Reliability is one of the critical success factors for both passenger and freight rail service delivery. One major factor that significantly impacts reliability performance is delays spanning over spatial and temporal dimensions. One way to increase reliability is to avoid systematic delay propagation through better timetable design to reduce the interdependencies between trains caused by route conflicts and train connections. In this paper, we aim to predict the propagation of delays on a railway network by developing a conditional Bayesian delay propagation model. In the model, the propagation satisfies the Markov property that determination of delay propagation for the future of the process is based solely on its present state, and that the history does not have an influence on the future. For the cases of delay caused by cross line conflicts and train connection, throughput estimation is considered in the model. The proposed model benefits from scalable computing time and complexity advantages over the Markov property. Implementation of actual operational data shows the feasibility and accuracy of the proposed model when compared to traditional probability models. The proposed model can be used for timetable evaluation and operations management decision support.
dc.language	en
dc.relation.ispartof	Australasian Transport Research Forum, ATRF 2019 - Proceedings
dc.rights	info:eu-repo/semantics/openAccess
dc.title	A conditional Bayesian delay propagation model for large-scale railway traffic networks
dc.type	Conference Proceeding
utslib.location.activity	Canberra, Australia
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/A/DRsch The Data Science Institute
pubs.organisational-group	/University of Technology Sydney
utslib.copyright.status	open_access	*
pubs.consider-herdc	false
dc.date.updated	2020-06-12T09:01:25Z
pubs.finish-date	2019-10-02
pubs.publication-status	Published
pubs.start-date	2019-09-30

Abstract:

© 2019 Australasian Transport Research Forum, ATRF 2019 - Proceedings. All rights reserved. Reliability is one of the critical success factors for both passenger and freight rail service delivery. One major factor that significantly impacts reliability performance is delays spanning over spatial and temporal dimensions. One way to increase reliability is to avoid systematic delay propagation through better timetable design to reduce the interdependencies between trains caused by route conflicts and train connections. In this paper, we aim to predict the propagation of delays on a railway network by developing a conditional Bayesian delay propagation model. In the model, the propagation satisfies the Markov property that determination of delay propagation for the future of the process is based solely on its present state, and that the history does not have an influence on the future. For the cases of delay caused by cross line conflicts and train connection, throughput estimation is considered in the model. The proposed model benefits from scalable computing time and complexity advantages over the Markov property. Implementation of actual operational data shows the feasibility and accuracy of the proposed model when compared to traditional probability models. The proposed model can be used for timetable evaluation and operations management decision support.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/141390