Evolutionary Computing Techniques for Load Balancing in Cloud Network

Abstract

Due to increasing of numerous data and computing, it impossible to purchase and maintain computing capacity with more expensive. Therefore, it is essential to share the resources for economical purpose It is also necessary to process those data and computing within a specified span of time which is not possible to compute through cluster computing and grid computing in parallel and distributed manner. This idea brings the concept of sharing computing resources and enhance the computing facility through internet by integrating the distributed and parallel computing strategy and the concept is known as cloud computing. When the computing services are stored and accesses over internet instead of through physical hard drives. The services offer by cloud computing as servers, databases, software, networks resources (hardware, and software applications) and other computing functions that can be operated through the cloud. The cloud computing is an Internet- based computing model that share resources (e.g., networks, servers, storage, applications, and services), software, and information to various devices of the user on demand. In cloud computing, the user(Client) request the service provider(CSP) through internet for computing facilities and CSP manage users request through the scheduling algorithm and assign the task to the Physical machine for processing. Each physical machine consists of several virtual machines(VMs) where actual computing is carried out and assign the tasks for execution into VMs may lead to overload of tasks in a particular VMs. Therefore, it is essential to equally distribute the requested user tasks among the VMs which is objective of this thesis. Load balancing, in Cloud Computing (CC) environment, is defined as the method of splitting workloads and computing properties. It enables the enterprises to manage workload demands or application demands by distributing the resources among computers, networks or servers. . The aim of the thesis narrowed to different load balancing algor