Seeking for the Optimal Energy Modelisation Accuracy to Allow Efficient Datacenter Optimizations

Abstract : As cloud computing is being more and more used, datacenters play a large role in the overall energy consumption. We propose to tackle this problem, by continuously and autonomously optimizing the cloud datacenters energy efficiency. To this end, modeling the energy consumption for these infrastructures is crucial to drive the optimization process, anticipate the effects of aggressive optimization policies, and to determine precisely the gains brought with the planned optimization. Yet, it is very complex to model with accuracy the energy consumption of a physical device as it depends on several factors. Do we need a detailed and fine-grained energy model to perform good optimizations in the datacenter? Or is a simple and naive energy model good enough to propose viable energy-efficient optimizations? Through experiments, our results show that we don't get energy savings compared to classical bin-packing strategies but there are some gains in using precise modeling: better utilization of the network and the VM migration processes.
Type de document :
Communication dans un congrès
16th International Symposium on Cluster, Cloud and Grid Computing, May 2016, Cartagena, Italy. 2016, IEEE/ACM 16th International Symposium on Cluster, Cloud and Grid Computing. 〈https://ccgrid2016.uniandes.edu.co/〉. 〈10.1109/CCGrid.2016.67〉
Liste complète des métadonnées

Littérature citée [8 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01356099
Contributeur : Olivier Barais <>
Soumis le : mercredi 24 août 2016 - 18:07:19
Dernière modification le : mercredi 2 août 2017 - 10:07:00
Document(s) archivé(s) le : vendredi 25 novembre 2016 - 13:52:41

Fichier

paper_CCGrid.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Citation

Edouard Outin, Jean-Emile Dartois, Olivier Barais, Jean-Louis Pazat. Seeking for the Optimal Energy Modelisation Accuracy to Allow Efficient Datacenter Optimizations. 16th International Symposium on Cluster, Cloud and Grid Computing, May 2016, Cartagena, Italy. 2016, IEEE/ACM 16th International Symposium on Cluster, Cloud and Grid Computing. 〈https://ccgrid2016.uniandes.edu.co/〉. 〈10.1109/CCGrid.2016.67〉. 〈hal-01356099〉

Partager

Métriques

Consultations de
la notice

643

Téléchargements du document

137