Estimating the robustness of public transport schedules using machine learning

The planning of attractive and cost efficient public transport schedules, i.e., timetables and corresponding vehicle schedules is a highly complex optimization process involving many steps. Integrating robustness from a passenger’s point of view makes the task even more challenging. With numerous different definitions of robustness in the literature, a standard way to evaluate the robustness of a public transport system is to simulate its performance under a large number of possible scenarios. Unfortunately, this is computationally very expensive. In this paper, the authors therefore explore a new way of such a scenario-based robustness approximation by using regression models from machine learning. Training of these models is based on carefully selected key features of public transport systems and passenger demand. The trained model is then able to predict the robustness of untrained instances with high accuracy using only its key features, allowing for a robustness oracle for transport planners that approximates the robustness in constant time. Such an oracle can be used as black box to increase the robustness of public transport schedules. The authors provide a first proof of concept for the special case of robust timetabling, using a local search framework. In computational experiments with different benchmark instances the authors demonstrate an excellent quality of their predictions.

• Record URL:
  https://doi.org/10.1016/j.trc.2022.103566
• Record URL:
  http://www.sciencedirect.com/science/article/pii/S0968090X22000146
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/issn/0968090X
• Supplemental Notes:
  • © 2022 Published by Elsevier Ltd. Abstract reprinted with permission of Elsevier.
• Authors:
  • Müller-Hannemann, Matthias
  • Rückert, Ralf
  • 0000-0002-6307-2189
  • Schiewe, Alexander
  • 0000-0002-1055-2066
  • Schöbel, Anita
  • 0000-0002-9306-5529
• Publication Date: 2022-4

Language

• English

Media Info

• Media Type: Web
• Features: Appendices; Figures; References; Tables;
• Pagination: 103566
• Serial:
  • Transportation Research Part C: Emerging Technologies
  • Volume: 137
  • Issue Number: 0
  • Publisher: Elsevier
  • ISSN: 0968-090X
  • Serial URL: http://www.sciencedirect.com/science/journal/0968090X

Subject/Index Terms

• TRT Terms: Machine learning; Optimization; Public transit; Schedules; Timetables
• Subject Areas: Operations and Traffic Management; Planning and Forecasting; Public Transportation;

Filing Info

• Accession Number: 01839883
• Record Type: Publication
• Files: TRIS
• Created Date: Mar 24 2022 5:26PM