Umeå University's logo

umu.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • 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
Carbon-aware Scheduling in Kubernetes
Umeå University, Faculty of Science and Technology, Department of Computing Science.
2024 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

In recent years, escalating concerns over environmental sustainability have highlighted the urgent need to address excessive carbon emissions, which drive climate change and its detrimental effects, including severe weather, food shortages, and increased poverty. This thesis explores the implementation of carbon-aware scheduling within a Kubernetes cluster, aiming to minimize carbon emissions, and evaluating how the performance of the system is affected. Kubernetes, an open-source platform for automating the deployment, scaling, and management of containerized applications, offers a promising framework for integrating carbon-aware strategies. With the increase in the use of computing power, data centers have become a significant contributor to global carbon emissions due to their considerable energy consumption. By integrating carbon-aware strategies into Kubernetes, this study investigates the potential for reducing the carbon footprint of microservice-based applications. Microservices is an architectural style where the application is divided into small, independent services, each handling a specific function. This allows for greater flexibility, scalability, and ease of maintenance. This thesis proposes and develops a carbon-aware scheduler that tests various applications under different traffic loads to assess its effectiveness in reducing carbon emissions. The scheduler optimally allocates workloads to different geographical locations based on carbon intensity, aiming to leverage multiple data centers across the globe. Performing experiments within a controlled testbed environment demonstrates that the scheduler is able to reduce emissions effectively, up to 28.58%, although with trade-offs in response times and system performance during migration phases. This thesis contributes to the emerging field of green computing by providing a practical approach to carbon-aware scheduling in cloud environments, highlighting the balance between environmental impact and performance metrics. 

Place, publisher, year, edition, pages
2024.
Series
UMNAD ; 1495
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:umu:diva-227248OAI: oai:DiVA.org:umu-227248DiVA, id: diva2:1878128
External cooperation
Elastisys
Supervisors
Examiners
Available from: 2024-06-27 Created: 2024-06-26 Last updated: 2024-06-27Bibliographically approved

Open Access in DiVA

fulltext(1921 kB)382 downloads
File information
File name FULLTEXT01.pdfFile size 1921 kBChecksum SHA-512
c945ccffff2cceaaccb64d861e2ced7d602d715978fe8ab0f06bda88ef500e7099f99d1f6716d376bd78a2ae0bd5c55b620a6428e07837be65dc5b12c378dd71
Type fulltextMimetype application/pdf

By organisation
Department of Computing Science
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 382 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 980 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • 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