OATAO - Open Archive Toulouse Archive Ouverte Open Access Week

Effectiveness of neural networks for power modeling for Cloud and HPC: It's worth it!

Da Costa, Georges and Pierson, Jean-Marc and Fontoura Cupertino, Leandro Effectiveness of neural networks for power modeling for Cloud and HPC: It's worth it! (2020) ACM Transactions on Modeling and Performance Evaluation of Computer Systems, 5 (3). 12:1-12:36. ISSN 2376-3639

[img]
Preview
(Document in English)

PDF (Author's version) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
4MB

Official URL: https://doi.org/10.1145/3388322

Abstract

Power consumption of servers and applications are of utmost importance as computers are becoming ubiquitous, from smart phones to IoT and full-fledged computers. To optimize their power consumption, knowledge is necessary during execution at different levels: for the Operating System to take decisions of scheduling, for users to choose between different applications. Several models exist to evaluate the power consumption of computers without relying on actual wattmeters: Indeed, these hardware are costly but also usually have limits on their pooling frequency (usually a one-second frequency is observed) except for dedicated professional hardware. The models link applications behavior with their power consumption, but up to now there is a 5% wall: Most models cannot reduce their error under this threshold and are usually linked to a particular hardware configuration. This article demonstrates how to break the 5% wall of power models. It shows that by using neural networks it is possible to create models with 1% to 2% error. It also quantifies the reachable precision obtainable with other classical methods such as analytical models.

Item Type:Article
Additional Information:Thanks to ACM. The definitive version is available at http://dl.acm.org The original PDF can be found at ACM Transactions on Modeling and Performance Evaluation of Computer Systems website : https://dl.acm.org/doi/10.1145/3388322
HAL Id:hal-02950809
Audience (journal):International peer-reviewed journal
Uncontrolled Keywords:
Institution:Université de Toulouse > Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE)
French research institutions > Centre National de la Recherche Scientifique - CNRS (FRANCE)
Université de Toulouse > Université Toulouse III - Paul Sabatier - UT3 (FRANCE)
Université de Toulouse > Université Toulouse - Jean Jaurès - UT2J (FRANCE)
Université de Toulouse > Université Toulouse 1 Capitole - UT1 (FRANCE)
Laboratory name:
Funders:
ANR : Agence Nationale de la Recherche (France) - European Commission (Europe)
Statistics:download
Deposited On:18 Sep 2020 15:01

Repository Staff Only: item control page