A Secure and Multi-objective Virtual Machine Placement Framework for Cloud Data Centre

TL;DR

This paper introduces a secure, energy-efficient, multi-objective VM placement framework for cloud data centers, utilizing a novel whale-inspired genetic algorithm to optimize resource allocation, reduce costs, and enhance security.

Contribution

It proposes a novel SM-VMP framework with WOGA, improving resource utilization, security, and reducing power consumption and inter-communication costs.

Findings

Up to 28.81% reduction in shared servers.

Up to 25.7% decrease in inter-communication cost.

Up to 35.9% reduction in power consumption.

Abstract

To facilitate cost-effective and elastic computing benefits to the cloud users, the energy-efficient and secure allocation of virtual machines (VMs) plays a significant role at the data centre. The inefficient VM Placement (VMP) and sharing of common physical machines among multiple users leads to resource wastage, excessive power consumption, increased inter-communication cost and security breaches. To address the aforementioned challenges, a novel secure and multi-objective virtual machine placement (SM-VMP) framework is proposed with an efficient VM migration. The proposed framework ensures an energy-efficient distribution of physical resources among VMs that emphasizes secure and timely execution of user application by reducing inter-communication delay. The VMP is carried out by applying the proposed Whale Optimization Genetic Algorithm (WOGA), inspired by whale evolutionary optimization and non-dominated sorting based genetic algorithms. The performance evaluation for static and dynamic VMP and comparison with recent state-of-the-arts observed a notable reduction in shared servers, inter-communication cost, power consumption and execution time up to 28.81%, 25.7%, 35.9% and 82.21%, respectively and increased resource utilization up to 30.21%.