Performance Analysis of Algorithms for Virtualized Environments on Cloud Computing

Abstract

Cloud computing emerges as a new dominant paradigm for distributed systems, as a model that allows users to access the network on demand to a shared pool of computing resources that can be configured, e.g., networks, servers, storage, applications and services. In cloud computing the infrastructure can become available as a service through virtualization using hypervisors. Virtualization is a mechanism to abstract hardware resources and system of a given operating system. Therefore, this type of technology is used in cloud environments through a large set of servers using virtual machine monitors that are located between the hardware and the operating system. However there is a wide spread of hypervisors, each with its own advantages and disadvantages. Therefore, this study is one of the proposals, conducting experiments with algorithms among different classes of algorithms available to virtual environments in a cloud. The goal of these experiments is to determine which factors (virtual machines, operating system and hardware) with of its configurations influence the performance of a deterministic algorithm. These experiments were planned and executed with a basic theory of experimental design. The experimental design is a set of tests using pre-established criteria and scientific statistical mostly with the aim of determining the influence of various factors on the results of a system or process, identifying and noting the reasons that led to changes in the expected response. All experiments results will be analyzed and will assist cloud computing users in the discovery of a possible virtual environment configuration that will allow and to avoid programming execution deft, computational resources loss and monthly costs.