A low carbon kubernetes scheduler

Aled James, Daniel Schien

Research output: Chapter in Book/Report/Conference proceedingConference Contribution (Conference Proceeding)

3 Citations (Scopus)

Abstract

A major source of global greenhouse gas emissions is the burning of fossil fuels for the generation of electricity. The portion of electricity generated from fossil fuel varies across regions, and within a region with demand for electricity and the availability of renewable energy sources. Cloud providers operate data centres in locations around the planet. And certain kind of server computation can tolerate migrating between data centres. In this paper we describe the design and implementation of a low carbon scheduling policy for the open-source Kubernetes container orchestrator. We apply this scheduler in a form of demand side management by migrating consumption of electric energy to countries with the lowest carbon intensity of electricity. The primary contributions of this text are (i) the scheduler’s design, which provides a generic model for optimising workload placement in regions with the lowest carbon intensity (ii) an evaluation of its performance in a case study with a major public cloud provider (iii) an implementation of a demand side management solution that consumes electricity where, instead of when, grid carbon intensity is lowest.

Original languageEnglish
Title of host publication6th International Conference on ICT for Sustainability, ICT4S 2019
PublisherCEUR-WS
Volume2382
Publication statusPublished - 17 Jun 2019
Event6th International Conference on ICT for Sustainability, ICT4S 2019 - Lappeenranta, Finland
Duration: 10 Jun 201914 Jun 2019

Publication series

NameCEUR Workshop Proceedings
ISSN (Print)1613-0073

Conference

Conference6th International Conference on ICT for Sustainability, ICT4S 2019
Country/TerritoryFinland
CityLappeenranta
Period10/06/1914/06/19

Research Groups and Themes

  • Bristol Interaction Group

Fingerprint

Dive into the research topics of 'A low carbon kubernetes scheduler'. Together they form a unique fingerprint.

Cite this