A Novel Approach of Virtual Machine Consolidation for Energy Efficiency and Reducing Sla Violation in Data Centers
Pardeep Singh1, Jyotsna Sengupta2, P.K. Suri3

1Pardeep Singh, Department of Computer Science, Punjabi University, Patiala (Punjab), India.
2Jyotsna Sengupta, Department of Computer Science, Punjabi University, Patiala (Punjab), India.
3P.K. Suri, Department of Computer Science and Applications, Kurukshetra University, Kurukshetra (Haryana), India.
Manuscript received on 07 March 2019 | Revised Manuscript received on 20 March 2019 | Manuscript published on 30 March 2019 | PP: 547-555 | Volume-8 Issue-5, March 2019 | Retrieval Number: D3210028419/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Infrastructure as a Service (IaaS) virtually divides the hardware resources of datacenter and produces several Virtual Machine (VM) objects on one or more physical machines (PM). These VMs are further allocated to the different clients as per their requirements. So, virtualization has a significant role to enhance the utilization of PM. And, this is managed by optimally constructing and destructing VMs over PMs. In this work,VM consolidation algorithm is the center of research that includes the procedures of initial VM allocation, detecting overloaded hosts, selecting appropriate VMs for migration, then placing the migrated VMs overs PMs and finally detecting the idle or under-loaded hosts. Main issues discussed are dynamically placement of VMs and finding the idle or under-loaded hosts. VM Placement problem is solved by introducing a novel Utility Aware Best Fit Decreasing (UABFD) algorithm that increases the utility of the servers. By increasing the utility, servers can finish the assigned load in a shorter makespan, which leads to less energy consumption. Another problem of detecting underloaded hostsis also modified by applying some heuristics. Both the Proposed algorithms are then replaced with the existing algorithms inVM consolidation scheme, to designa Modified VM Consolidation (MVMC) scheme. Cloudsim is used for evaluating various performance parameters of cloud environment with the proposed scheme.Resultsare compared and analyzed with the existing VM consolidation scheme. That has proved thatMVMC has significant improvement for various parameters over the existing scheme.
Keyword: Energy Consumption, Vm Selection, Vm Consolidation, Vm Placement, Sla Violation, Cloud Computing, Data Center Management.
Scope of the Article: Cloud Computing