Back to search

University of Leeds

Analysis of Thermal and Compute Performance of Data Centre Servers

Abstract

dc:description.abstract

Data centres are an increasingly large contributing factor to the consumption of electricity globally, and any improvements to their effectiveness are important in minimising their effect on the environment. This study aims to achieve this by looking at ways of understanding and more effectively utilising IT in data centre spaces. This was achieved through the testing of a range of ways of creating virtual load, and employing them on servers in a controlled thermal environment. A Generic Server Wind-tunnel was designed and built which afforded control of thermal environment and six different servers were tested within, yielding results on performance and thermal effect. Further testing was also conducted on a High Performance Computing server with a view to understanding the effect of internal temperature on performance. Transfer functions were created for each of the six servers, predicting behaviour reliability for five output functions and validating the developed methodology to an appropriate accuracy. The trends seen and the methodology presented should allowed data centre managers better insight into the behaviour of their servers.

Degree

thesis:*
Name dc:type.qualificationname
Ph.D
Level dc:type.qualificationlevel
doctoral
Grantor dc:publisher.institution
University of Leeds
Year dc:date.issued
2018

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Burdett, Daniel Simon
Advisor dc:contributor.advisor
  • Summers, Jon

Rights

Language dc:language.dcterms_iso639_2
eng

Identifiers

dc:identifier.*
Identifier
uk.bl.ethos.745617

Chain of custody

source
Harvested from
White Rose University Consortium
Base URL
etheses.whiterose.ac.uk/cgi/oai2
Last updated
2026-11-18
Source record
OAI-PMH GetRecord
related terms
citation

Burdett, Daniel Simon. Analysis of Thermal and Compute Performance of Data Centre Servers. doctoral thesis, University of Leeds, 2018.