Energy Efficient Virtual Machine Placement using Flower Pollination Algorithm

The cloud data center hardware is emitting immense amounts of hazardous gases to provide Virtual machine services to users. In cloud datacentres, Virtual Machines (VMs) have to be allocated on Physical machine s(PMs) to provide services. The optimal allocation of VM refers to minimal allocation time...

Full description

Saved in:
Bibliographic Details
Published in:2022 International Conference on Electronics and Renewable Systems (ICEARS) pp. 1341 - 1345
Main Authors: Darshini, Ch. Gayathri Priya, Tejasri, T., Raj, D. Jacob, Phani Kumar, V V N V
Format: Conference Proceeding
Language:English
Published: IEEE 16-03-2022
Subjects:
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The cloud data center hardware is emitting immense amounts of hazardous gases to provide Virtual machine services to users. In cloud datacentres, Virtual Machines (VMs) have to be allocated on Physical machine s(PMs) to provide services. The optimal allocation of VM refers to minimal allocation time and effective utilization of energy. This results in the allocation as an NP hard problem. Within this proposed strategy, a Bio inspired approach is discussed to deal with the problem. The proposed strategy adopts Flower Pollination Algorithm (FPA) for VM allocation and uses Multi-objective optimization techniques. The main objectives are to reduce execution time and minimize energy consumption. The FPA algorithm employs two phases Global pollination which explores global search space and Local pollination that explores local search space. The Dynamic Switching Probability determines the FPA allocation phase therefore it regulates global search space and local search space. The parameters of PMs that are considered for energy-efficient allocation of VM are CPU utilization and RAM. Therefore, Energy efficient virtual machine placement using Flower Pollination Algorithm can reduce greenhouse gases emissions by reducing the utilization of hardware resources
DOI:10.1109/ICEARS53579.2022.9752166