carbon-efficient-karpenter-thesis
Carbon Efficient Karpenter: Optimizing Kubernetes Cluster Autoscaling for Carbon Efficiency
https://github.com/jacobvaldemar/carbon-efficient-karpenter-thesis
Science Score: 44.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
✓CITATION.cff file
Found CITATION.cff file -
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
○DOI references
-
○Academic publication links
-
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (8.0%) to scientific vocabulary
Repository
Carbon Efficient Karpenter: Optimizing Kubernetes Cluster Autoscaling for Carbon Efficiency
Statistics
- Stars: 14
- Watchers: 2
- Forks: 1
- Open Issues: 0
- Releases: 0
Metadata Files
README.md
Carbon Efficient Karpenter (Master’s Thesis)
CarbonEfficientKarpenter.pdf © 2024 Jacob Valdemar Andreasen
Abstract
Data centers are responsible for 0.6% of global greenhouse gas emissions. To reduce these emissions, existing research focus mostly on carbon-aware scheduling and scaling of short-running workloads. This thesis introduces a novel method called carbon efficient cluster autoscaling to reduce operational and embodied carbon emissions from all workloads on cloud-based Kubernetes clusters. A carbon efficient cluster autoscaler for Kubernetes is developed by adapting Karpenter, an open-source state-of-the-art cluster autoscaler, to minimize cloud instance carbon emission estimates from BoaviztAPI. The developed Carbon Efficient Karpenter shows a statistically significant median reduction in cloud instance carbon emissions when compared to the original Karpenter. In locations where electricity has low, moderate, and high carbon intensity, the 25th/75th percentile reductions are 26%/45%, 7%/32%, and 4%/5%, respectively. This suggests that carbon efficient cluster autoscaling is a viable method for reducing the carbon footprint of Kubernetes clusters that run on cloud infrastructure. Widespread adoption could incentivize carbon emission optimizations throughout the cloud computing supply chain. An array of research questions emerge from these findings.
Software
The software in this master’s thesis is available in two Git repositories at the thesis tag: - https://github.com/JacobValdemar/carbon-efficient-karpenter/tree/thesis - https://github.com/JacobValdemar/carbon-efficient-karpenter-utilities/tree/thesis
Sharing
Please share a link to this repository instead of sharing the pdf directly.
Citing
If you use this master’s thesis in your work, please cite it using the following entry.
bib
@thesis{andreasenCarbonEfficientKarpenter2024,
title = {Carbon {{Efficient Karpenter}}: {{Optimizing Kubernetes Cluster Autoscaling}} for {{Carbon Efficiency}}},
shorttitle = {Carbon {{Efficient Karpenter}}},
author = {Andreasen, Jacob Valdemar},
date = {2024-01-03},
institution = {{Aarhus University}},
location = {{Aarhus, Denmark}},
langid = {english},
language = {en},
url = {https://github.com/JacobValdemar/carbon-efficient-karpenter-thesis}
}
J. V. Andreasen, “Carbon Efficient Karpenter: Optimizing Kubernetes Cluster Autoscaling for Carbon Efficiency,” Aarhus University, Aarhus, Denmark, Jan. 3, 2024. [Online]. Available: https://github.com/JacobValdemar/carbon-efficient-karpenter-thesis
Owner
- Name: Jacob Valdemar
- Login: JacobValdemar
- Kind: user
- Location: Aarhus, Denmark
- Company: @lunarway
- Repositories: 2
- Profile: https://github.com/JacobValdemar
Platform Engineer at @lunarway
Citation (CITATION.cff)
cff-version: 1.2.0
message: "If you use this work in your research, please cite it as below."
title: "Carbon Efficient Karpenter: Optimizing Kubernetes Cluster Autoscaling for Carbon Efficiency"
type: thesis
authors:
- family-names: Andreasen
given-names: Jacob Valdemar
date-released: 2024-01-03
institution: Aarhus University
location: Aarhus, Denmark
langid: english
language: en
url: "https://github.com/JacobValdemar/carbon-efficient-karpenter-thesis"
GitHub Events
Total
- Watch event: 2
Last Year
- Watch event: 2
Issues and Pull Requests
Last synced: 10 months ago
All Time
- Total issues: 0
- Total pull requests: 0
- Average time to close issues: N/A
- Average time to close pull requests: N/A
- Total issue authors: 0
- Total pull request authors: 0
- Average comments per issue: 0
- Average comments per pull request: 0
- Merged pull requests: 0
- Bot issues: 0
- Bot pull requests: 0
Past Year
- Issues: 0
- Pull requests: 0
- Average time to close issues: N/A
- Average time to close pull requests: N/A
- Issue authors: 0
- Pull request authors: 0
- Average comments per issue: 0
- Average comments per pull request: 0
- Merged pull requests: 0
- Bot issues: 0
- Bot pull requests: 0