Opportunistic Two Virtual Machines Placements in Distributed Cloud Environment

Opportunistic Two Virtual Machines Placements in Distributed Cloud Environment

Kamal Kumar (National Institute of Technology, Uttarakhand, Srinagar (Garhwal), India) and Jyoti Thaman (Researcher, Chandigarh, India)
Copyright: © 2020 |Pages: 22
DOI: 10.4018/IJGHPC.2020100102

Abstract

Cloud computing is a potentially tremendous platform and its presence is experienced in day to day life. Most infrastructure and technology enterprises have migrated to a cloud-based infrastructure and storage. With so much dependence on the cloud as a distributed and reliable platform, but a few issues remain as a challenge and provide food for the ever-active research entity. Considering a very basic aspect of VM migration followed by VM placement, one VM at a time is a prominent approach. This article presents a novel idea of placing two VMs at a time. This proposal is a draft of solution for the Two VM Placement problem. The experimental validation was done against a well-known placement algorithm, the power aware best fit decreasing (PABFD). PABFD and TVMP were applied on a given context and results were obtained for three important parameters, which include the number of VM migrations, reallocation means, and energy efficiency. Improvements on these parameters may prove beneficial.
Article Preview
Top

1. Introduction

With widespread usage and ever evolving spirit of computing technologies, distributed computing has emerged as most clear form as Cloud Computing environment. This evolution has seen milestones like cluster computing, grid computing and finally, cloud computing. Going by the volume of infrastructure, communication and development attributed to cloud environment, cloud has achieved irreplaceable importance. With so much prevalence of this technology, internal intricacies and their improvement should be a continuous process.

Cloud environment utilizes the concept of housing data centre as collection of hosts as hardware resource and VM as executable units/instances. VMs are hosted inside the hosts and consume resources as per VM’s capacity. Each host in general can support a predetermined or adaptively determined utilization levels. To ensure load balanced state, improved utilization of under-utilized hosts and improved energy efficiency, live migration is most commonly used. Migrated VMs must be placed on most suitable hosts at the moment. Several proposals in recent times have considered VM placement problems. It is very basic aspect but can be expressed as multidimensional problem in terms of Performance Tuning (Kusic et al., 2009), scalability (Piao & Yan 2010), availability (Bin et al., 2011), network (Wang et al., 2011; Jiang et al., 2012), cost (Sharma et al., 2011), etc. Existing proposals (Li et al., 2013) establish the importance of the VMP problem and energy saving policy. Moreover, we can differentiate approaches as mono objective optimization (Caron et al., 2013; Chaisiri et al., 2009; Chang et al., 2013; Biran et al., 2012; Dang & Hermenier 2013; Dias & Costa 2012) and multi-objective optimization (Adamuthe et al., 2013; Anand et al., 2013; Dong & Herbert, 2013; Dong et al., 2013; Dong et al., 2013; Fang et al., 2013; Fang et al., 2013; Ferreto et al., 2011; Gao et al., 2013). Further, several important aspects like load balancing, utilization ratio, energy efficiency, migration and placement has emerged as challenges in current scenario.

This paper is a proposal of recently researched idea of implementing two VM placement (TVMP) instance and provides a buildup on what is prevailing in research and commercial enterprises. This paper has been organized in 6 sections. Section 1 presents introduction to VMP and relevant constraints. Section 2 presents related works in this field. Section 3 discusses problem statement for this proposal. Section 4 presents TVMP approach and realizing algorithms. Section 5 establishes the simulation setup and experimentations. Section 6 presents discussion and performance. Section 7 is the conclusion.

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 13: 4 Issues (2021): Forthcoming, Available for Pre-Order
Volume 12: 4 Issues (2020)
Volume 11: 4 Issues (2019)
Volume 10: 4 Issues (2018)
Volume 9: 4 Issues (2017)
Volume 8: 4 Issues (2016)
Volume 7: 4 Issues (2015)
Volume 6: 4 Issues (2014)
Volume 5: 4 Issues (2013)
Volume 4: 4 Issues (2012)
Volume 3: 4 Issues (2011)
Volume 2: 4 Issues (2010)
Volume 1: 4 Issues (2009)
View Complete Journal Contents Listing