Burdett, Daniel Simon (2018) Analysis of Thermal and Compute Performance of Data Centre Servers. PhD thesis, University of Leeds.
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.
Metadata
Supervisors: | Summers, Jon |
---|---|
Keywords: | data centre, energy efficiency, regression, wind tunnel |
Awarding institution: | University of Leeds |
Academic Units: | The University of Leeds > Faculty of Engineering (Leeds) > School of Mechanical Engineering (Leeds) |
Identification Number/EthosID: | uk.bl.ethos.745617 |
Depositing User: | Dr Dan Burdett |
Date Deposited: | 29 Jun 2018 12:04 |
Last Modified: | 18 Feb 2020 12:49 |
Open Archives Initiative ID (OAI ID): | oai:etheses.whiterose.ac.uk:20785 |
Download
Final eThesis - complete (pdf)
Filename: Burdett_DS_MechanicalEngineering_PhD_2018.pdf
Description: Analysis of Thermal and Compute Performance of Data Centre Servers
Licence:
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 2.5 License
Export
Statistics
You do not need to contact us to get a copy of this thesis. Please use the 'Download' link(s) above to get a copy.
You can contact us about this thesis. If you need to make a general enquiry, please see the Contact us page.