Back to search

University of Birmingham

Realising the potential of rich energy datasets

Abstract

dc:description.abstract

In the last twenty years the availability of vast amounts of data has enabled industries to gain insight into numerous aspects of their operation whose trends were previously unknown. The result is an unprecedented ability to predict operational needs, to evaluate performance of individuals or assets and prepare such industries for uncertainties. The rail industry currently produces large amounts of data that are, in many cases, not used to their full potential. The first case study demonstrates a novel method to identify and cluster distinct driver styles in use on a DC rail network. Using the optimal driver styles identified, improved ‘driver cultures’ were designed that are shown to provide up to 10% energy savings without the need for expensive in cab driver advisory systems. The second case study details data taken from a full fleet that were used to develop a statistical method to identify the minimum amount of vehicles that required energy metering whilst still providing an accurate mean energy consumption estimate. The identification of this minimum amount was then used to validate the fleet size intended for partial fleet metering options for UK rail networks.

Degree

thesis:*
Name dc:type.qualificationname
d_ph
Level dc:type.qualificationlevel
d_ph
Grantor dc:publisher.institution
University of Birmingham
Year dc:date.issued
2017

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Ellis, Robert Joseph

Subjects

dc:subject × 3

Rights

Language dc:language.dcterms_iso639_2
eng

Chain of custody

source
Harvested from
University of Birmingham
Base URL
etheses.bham.ac.uk/cgi/oai2
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Ellis, Robert Joseph. Realising the potential of rich energy datasets. d_ph thesis, University of Birmingham, 2017.