Statistical Modelling for Performance Evaluation of Cloud Based System

Abstract

Virtualization reduces the operational cost by increasing the resource utilization level newlineintegrating heterogeneous environments to provide resources to users and applications. A vast newlineimprovement in system security, reliability and availability of resources at reduced cost can be newlineachieved through this technology. The major issues to be considered while performing such newlineactivity are optimizing resources, fault tolerance, load balancing, power management, system newlinemaintenance, etc. Live migration is a prerequisite feature of virtualization that allows transfer of newlinea working virtual machine from one data center to another. It is a useful tool for optimization of newlineresources and is one of the issues of research. In this study, we are exploring and implementing newlinean analytical model based approach for quality evaluation of cloud by considering rejection newlineprobability of jobs. The work has been done in two phases by applying M/M/1/K queueing newlinemodel first phase of the work in order to find the rejection probability of jobs. To study the newlineimpact of changing buffer sizes on the rejection probability of the jobs is the main point of newlineconcern here. We have proposed application of M/G/1/and#8734;, M/G/1/K models to it. It is observed newlinethat in case of M/M/1/K, with an increase in the request arrival rate, the rejection probability of newlinejobs increases, but if we change the model to M/G/1/and#8734;, the rejection probability of jobs newlinedecreases. We can say that general distribution queueing model is more effective in migration as newlinecompared to exponential distribution model. newlineMathematical analysis and the performance evaluation of the cloud services has always newlinebeen a challenging and complicated task. The analytical models-based evaluation helps in newlinedetermining the performance of the system whenever the input parameters are changed. Most newlinemodels based on queuing theory assumed either Markovian distribution or proposes complex newlinemathematics to evaluate the parameters of interest. To simplify the computing process, the newlinecurrent research utilizes the GEM