Quantifying the Impact of Shutdown Techniques for Energy-Efficient Data Centers Issam Raïs, Anne-Cécile Orgerie, Martin Quinson, Laurent Lefèvre To cite this version: Issam Raïs, Anne-Cécile Orgerie, Martin Quinson, Laurent Lefèvre. Quantifying the Impact of Shut- down Techniques for Energy-Efficient Data Centers. Concurrency and Computation: Practice and Experience, Wiley, 2018, 30 (17), pp.1-13. 10.1002/cpe.4471. hal-01711812 HAL Id: hal-01711812 https://hal.archives-ouvertes.fr/hal-01711812 Submitted on 19 Feb 2018 HAL is a multi-disciplinary open access L’archive ouverte pluridisciplinaire HAL, est archive for the deposit and dissemination of sci- destinée au dépôt et à la diffusion de documents entific research documents, whether they are pub- scientifiques de niveau recherche, publiés ou non, lished or not. The documents may come from émanant des établissements d’enseignement et de teaching and research institutions in France or recherche français ou étrangers, des laboratoires abroad, or from public or private research centers. publics ou privés. ReceivED 30 September 2017; ReVISED 31 December 2017; Accepted 14 FEBRUARY 2018 DOI: xxx/XXXX CONCURRENCY & COMPUTATION: PRACTICE & EXPERIENCE Quantifying THE Impact OF Shutdown TECHNIQUES FOR Energy-EffiCIENT Data Centers Issam Rais*1,2 | Anne-Cécile Orgerie2 | Martin Quinson2 | Laurent LefèVRE1 1AVALON Team, LIP (Inria, ENS LYon, CNRS, Univ. LYON 1), LYon, FRANCE Summary 2Univ. Rennes, Inria, CNRS, IRISA, Rennes, FRANCE Current large-scale systems, LIKE DATACENTERS AND supercomputers, ARE FACING AN INCREASING elec- TRICITY consumption. These INFRASTRUCTURES ARE OFTEN DIMENSIONED ACCORDING TO THE WORKLOAD Correspondence *Issam Rais. Email:
[email protected] peak. HoweVER, AS THEIR CONSUMPTION IS NOT power-proportional: WHEN THE WORKLOAD IS LOW, THE POWER CONSUMPTION IS STILL high.