Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Reliability Analysis of Internal Power Supply Architecture of Data Centers in Terms of Power Losses
Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.ORCID iD: 0000-0001-5870-0112
Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.ORCID iD: 0000-0003-4443-7653
Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.ORCID iD: 0000-0003-4074-9529
2021 (English)In: Electric power systems research, ISSN 0378-7796, E-ISSN 1873-2046, Vol. 193, article id 107025Article in journal (Refereed) Published
Abstract [en]

The number of data centers and the energy demand are increasing globally with the development of information and communication technology (ICT). The data center operators are facing challenges to limit the internal power losses and the unexpected outages of the computational resources or servers. The power losses of the internal power supply system (IPSS) increase with the increasing number of servers that causes power supply capacity shortage for the devices in IPSS. The aim of this paper is to address the outage probability of the computational resources or servers due to the power supply capacity shortage of the power distribution units (PDUs) in the IPSS. The servers outage probability at rack-level defines the service availability of the data center since the servers are the main computational resource of it. The overall availability of the IPSS and the power consumption models of the IPSS devices are also presented in this paper. Quantitative studies are performed to show the impacts of the power losses on the service availability and the overall availability of the IPSS for two different IPSS architectures, which are equivalent to the Tier I and Tier IV models of the data center.

Place, publisher, year, edition, pages
Elsevier, 2021. Vol. 193, article id 107025
Keywords [en]
availability, data center, internal power supply system, power losses, reliability
National Category
Other Electrical Engineering, Electronic Engineering, Information Engineering
Research subject
Electric Power Engineering
Identifiers
URN: urn:nbn:se:ltu:diva-82716DOI: 10.1016/j.epsr.2021.107025ISI: 000632342800006Scopus ID: 2-s2.0-85099786563OAI: oai:DiVA.org:ltu-82716DiVA, id: diva2:1523940
Funder
Swedish Energy Agency, 43090-2Norrbotten County Council
Note

Validerad;2021;Nivå 2;2021-01-29 (alebob)

Available from: 2021-01-29 Created: 2021-01-29 Last updated: 2023-09-05Bibliographically approved
In thesis
1. On the Energy Efficiency and Reliability of Data Centers in Operation
Open this publication in new window or tab >>On the Energy Efficiency and Reliability of Data Centers in Operation
2023 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

The new generation information technology (IT) services like mobile Internet, Internet of things (IoT), cloud computing, processing of big data, applications of artificial intelligence, etc. are becoming popular with the development of the information and communication technology (ICT) industry. In this industry, the dependency on the data centers is also increasing to ensure the quality of services (QoS). Thus, the energy consumption of the data centers is increasing with the increasing demand for computational resources in it because the load sections of the data center with sensitive equipment run $24$ hours a day, $365$ days of the year. Regarding data center operation, it is becoming a technical challenge to make a trade-off between reducing the energy consumption to limit the operational costs and ensuring higher reliability of the data center.

A way to help data center operators to cope with the posed challenges is by identifying the ``right size of the computational resource'', considering the power losses and service availability of the data center. This endeavor requires power consumption models that can consider different load sections with different types of equipment. The power consumption models of the load sections can address the electrical load demand and the power losses, especially losses in the internal power conditioning system (IPCS). On the other hand, the service availability of the data center mainly depends on the availability of the computational resources like servers and on the availability of the power supply through the IPCS. It is important to characterize the servers' failure and repair times to develop the stochastic model of the server unavailability in operation. The availability of adequate power supply through the IPCS depends on its component failures and the power supply capacity of its components. The bottleneck of the power supply capacity of the IPCS is subjected to the power losses of the equipment in the IPCS. Additionally, the voltage disturbances like voltage dips and swells in the IPCS also interrupt the power supply units (PSUs) of the servers, which also degrades the QoS of the data center.

The outcomes of this thesis can be synthesized as follows: 1) A comparative analysis of the energy consumption models of the major load sections in the data center, and an analysis of the impact of the power losses in the IPCS on the outage probability of the servers. 2) Reliability indices to assess the adequacy of the computational resources in the data center considering the outages of power supplies and the servers in operation. 3) The impacts of voltages disturbances in the IPCS on the power supply outages, hence on the interruptions of servers. 4) An analysis of the trade-off between the energy efficiency and reliability in operational planning of the data center.

Place, publisher, year, edition, pages
Luleå: Luleå tekniska universitet, 2023. p. 210
Series
Doctoral thesis / Luleå University of Technology 1 jan 1997 → …, ISSN 1402-1544
National Category
Other Electrical Engineering, Electronic Engineering, Information Engineering
Research subject
Electric Power Engineering
Identifiers
urn:nbn:se:ltu:diva-96599 (URN)978-91-8048-307-0 (ISBN)978-91-8048-308-7 (ISBN)
Public defence
2023-06-16, Hörsal A, Luleå tekniska universitet, Skellefteå, 09:00 (English)
Opponent
Supervisors
Funder
Swedish Energy Agency, 24559
Available from: 2023-04-17 Created: 2023-04-16 Last updated: 2023-09-05Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records

Ahmed, Kazi Main UddinAlvarez, ManuelBollen, Math H.J.

Search in DiVA

By author/editor
Ahmed, Kazi Main UddinAlvarez, ManuelBollen, Math H.J.
By organisation
Energy Science
In the same journal
Electric power systems research
Other Electrical Engineering, Electronic Engineering, Information Engineering

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 319 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf