Authors: David Guyon; Anne-Cécile Orgerie; Christine Morin; Deb Agarwal
Addresses: University of Rennes, Inria, CNRS, IRISA, France ' University of Rennes, Inria, CNRS, IRISA, France ' University of Rennes, Inria, CNRS, IRISA, France ' Lawrence Berkeley National Lab., Berkeley, USA
Abstract: Services offered by cloud computing are convenient to users for reasons such as their ease of use, flexibility, and financial model. Yet data centres used for their execution are known to consume massive amounts of energy. The growing resource utilisation following the cloud success highlights the importance of the reduction of its energy consumption. This paper investigates a way to reduce the footprint of HPC cloud users by varying the size of the virtual resources they request. We analyse the influence of concurrent applications with different resources sizes on the system energy consumption. Simulation results show that resources with larger size are more energy consuming regardless of faster completion of applications. Although smaller-sized resources offer energy savings, it is not always favourable in terms of energy to reduce too much the size. High energy savings depend on the user profiles' distribution.
Keywords: cloud computing; green computing; HPC applications; high performance computing; energy savings; users involvement.
International Journal of Grid and Utility Computing, 2019 Vol.10 No.3, pp.272 - 282
Received: 26 Jul 2017
Accepted: 05 Jan 2018
Published online: 15 May 2019 *