An Enhanced Cloud Computing Architecture focussed at Optimising VM Migration through an efficient Placement Algorithm

Abstract

Generally, the architecture of a cloud computing system contains several layers, which includes hardware layer, infrastructure layer, Platform layer, and the Services layer. Each layer performs different kinds of operations and provides different types of services. VM Migration is undertaken by a scheduler installed within computing nodes with the main aim of balancing the Load on Physical servers. The Migration is undertaken based on the internal design of a cloud computing system. The response time agreed with the user and contained within an SLA gets compromised due to the heavy processing required for deciding on the migration and actually effecting the Migration. Unlike a traditional Virtual Machine (VM), a container is an emerging lightweight virtualization technology that operates at the operating system level to encapsulate a task and its library dependencies for execution. In this paper, a modified layered architecture is presented which considers the addition of another layer (Optimised Migration Layer) that is responsible for optimising the process of migration focusing on reduction of delay time caused due effecting the migration. The additional layer uses the concept of containerisation for optimising and reduction in delay time caused due to effecting the Migration. An efficient placement algorithm has been implemented in the OML layer. OML includes certain components, such as validation, business, transformation, and the deployment phase. The component that is responsible for effecting the Migration is quarantined by making changes to the configuration files. OML is designed using four phases that include Validation, Business phase, Transformation phase. The scheduling algorithm calls the software situated in OML layer which checks the validity of the request and the actual migration is effected in the Business phase in which an efficient Migration/Placement algorithm is implemented. Here, the placement algorithm, named Squirrel Whale Optimization Algorithm (S-WOA) is implemented. The migration is done based on five conditions, which include VM to Physical Machine (PM), container to VM under same PM, and the container to VM under different PM, tasks in VM to container, and container tasks to VM. A fitness function is designed and implemented to find, best migration method. The fitness function is designed using several parameters that include bandwidth, resource utilization and load. In the transformation phase the transformation from VM to container and vice versa is undertaken. The performance of the migration strategy in cloud based on S-WOA is evaluated in terms of number of instantiated VMs, CPU utilization, memory utilization, number of activated PMs, and time. The proposed S-WOA method achieves the maximal CPU utilization of 0.483, maximal memory of 0.523, and minimal time of 4.99sec. ©2020, World Academy of Research in Science and Engineering. All rights reserved.