A Decision Support Tool for Energy-Optimising Railway Timetables Based on Behavioural Data

Mathias Bejlegaard Madsen, Matthias Villads Hinsch Als, Rune Møller Jensen, Sune Edinger Gram

Research output: Conference Article in Proceeding or Book/Report chapterArticle in proceedingsResearchpeer-review

Abstract

Energy-efficient train operation can reduce operating costs
and contribute to a reduction in CO2 emissions. To utilise the full
potential of energy-efficient driving, energy-efficient timetabling is crucial.
To address this problem, we propose a decision support tool to
give timetable planners insight into energy consumption for a given
timetable. The decision support tool uses a recommendation based on
quadratic optimisation of a given timetable. Differently to previous work,
the optimisation uses actual data from the train operation, which is preprocessed by data reduction, outlier detection, and second-degree regression modelling. With this approach, our results show that the optimised
timetables can save up to 33.07% energy on a single section and up to
6.23% for a complete timetable. Solutions are computed in less than a
microsecond.
Original languageEnglish
Title of host publicationProceedings of the 10th International Conference on Computational Logistics (ICCL19)
Number of pages16
PublisherSpringer
Publication date30 Sept 2019
Pages397-412
ISBN (Print)978-3-030-31139-1
DOIs
Publication statusPublished - 30 Sept 2019
Event10th International Conference on Computational Logistics - Barranquilla, Colombia
Duration: 30 Sept 20192 Oct 2019
Conference number: 10

Conference

Conference10th International Conference on Computational Logistics
Number10
Country/TerritoryColombia
CityBarranquilla
Period30/09/201902/10/2019
SeriesLecture Notes in Computer Science
Volume11756
ISSN0302-9743

Keywords

  • Energy-efficient train operation
  • Timetabling optimisation
  • Decision support tool
  • Quadratic optimisation
  • Data preprocessing

Fingerprint

Dive into the research topics of 'A Decision Support Tool for Energy-Optimising Railway Timetables Based on Behavioural Data'. Together they form a unique fingerprint.

Cite this