HAL will be down for maintenance from Friday, June 10 at 4pm through Monday, June 13 at 9am. More information
Skip to Main content Skip to Navigation
Conference papers

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.
Document type :
Conference papers
Complete list of metadata

Cited literature [8 references]  Display  Hide  Download

Contributor : Olivier Barais Connect in order to contact the contributor
Submitted on : Wednesday, August 24, 2016 - 6:07:19 PM
Last modification on : Wednesday, November 3, 2021 - 4:34:49 AM
Long-term archiving on: : Friday, November 25, 2016 - 1:52:41 PM


Files produced by the author(s)



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. ⟨10.1109/CCGrid.2016.67⟩. ⟨hal-01356099⟩



Record views


Files downloads