You can view the full text of this article for free using the link below.

Title: Correlation-based heuristics and evaluation of existing greedy heuristics for VM allocations in cloud datacentres

Authors: Viney Sharma; Gur Mauj Saran Srivastava

Addresses: Department of Computer Science and Engineering, Anand Engineering College, Agra, India ' Department of Physics and Computer Science, Dayalbagh Educational Institute, Agra, India

Abstract: Cloud computing has taken the world in its strides. In cloud datacentres, thousands of physical machines run continuously to execute incoming workload. Virtual machines are provisioned to incoming requests and are allocated to physical machines. Efficient mapping of virtual machines to physical machines has potential impact on the efficiency of datacentres. This paper proposes two greedy heuristics for virtual machines to physical machines mapping. We have empirically evaluated proposed heuristics and existing greedy heuristics for comprehensive datasets including PlanetLab datasets. Thereafter we have considered issue of hotspot, and proposed two heuristics for hotspot mitigation. We have evaluated our proposed hotspot mitigation heuristics for wide varieties of cases and case of SLA violation is also taken into consideration. Extensive simulation shows that our proposed heuristics are substantially faster than their counterparts. As clouds have strong business perspective also, our heuristics can be seen as prime alternate options for virtual machines to physical machines mapping.

Keywords: energy efficiency; greedy approaches; computing as a service; VM migrations; multidimensional bin packing; first fit; hotspot mitigation.

DOI: 10.1504/IJITCC.2020.112454

International Journal of Information Technology, Communications and Convergence, 2020 Vol.3 No.4, pp.276 - 318

Received: 25 Jan 2020
Accepted: 17 Sep 2020

Published online: 04 Jan 2021 *

Full-text access for editors Access for subscribers Free access Comment on this article