Optimal sizing of a globally distributed low carbon cloud federation (2023)
Data creators :
Miguel Vasconcelos [1] [2],
Daniel Cordeiro [2],
Georges Da Costa [3],
Fanny Dufossé [1],
Jean-Marc Nicod [4],
Veronika Rehn-Sonigo [5]
[1] : Laboratoire d'Informatique de Grenoble
[2] : University of São Paulo
[3] : Institut de recherche en informatique de Toulouse
[4] : Franche-Comté Electronique Mécanique Thermique et Optique - Sciences et Technologies (UMR 6174) (École Nationale Supérieure de Mécanique et des Microtechniques)
[5] : Franche-Comté Electronique Mécanique Thermique et Optique - Sciences et Technologies (UMR 6174) (Université de Franche-Comté)
Description :
The carbon footprint of IT technologies has been a significant concern in recent years. This concern mainly focuses on the electricity consumption of data centers; many cloud suppliers commit to using 100% of renewable energy sources. However, this approach neglects the impact of device manufacturing. We consider in this work the question of dimensioning the renewable energy sources of a geographically distributed cloud with considering the carbon impact of both the grid electricity consumption in the considered locations and the manufacturing of solar panels and batteries. We design a linear program to optimize cloud dimensioning over one year, considering worldwide locations for data centers, real-life workload traces, and solar irradiation values. Our results show a carbon footprint reduction of about 30% compared to a cloud fully supplied by solar energy and of 85% compared to the 100% grid electricity model.
Disciplines :
computer science, hardware & architecture (engineering science), operations research & management science (engineering science)
General metadata
Data acquisition date :
from Apr 2022 ongoing
Data acquisition methods :
- Simulation or computational data : Considering given inputs (datacenter federation, appropriate configuration files, weather conditions, etc.), the software is able to propose an optimal sizing for the globally distributed low carbon cloud federation: surface area of solar panels, battery capacity for each data center location. . Scripts are available to shape the optimal configuration.
Formats :
application/json, application/x-sh, text/csv, text/plain, text/x-python
Audience :
Research, Policy maker
Publications :
- Miguel Vasconcelos, Daniel Cordeiro, Georges Da Costa, Fanny Dufossé, Jean-Marc Nicod and Veronika Rehn-Sonigo. Optimal sizing of a globally distributed low carbon cloud federation. in Cluster, Cloud and Internet Computing'23, Bangalore, India, May 2023. (hal:04032094)
Publisher :
GitLab
Record created 3 Feb 2023 by Jean-Marc Nicod.
Last modification : 16 Jun 2023.
Local identifier: FR-13002091000019-2023-02-03.
