Analysis of a pool management scheme for cloud computing centers

Abstract—In this paper, we propose an analytical performance model that addresses the complexity of cloud centers through distinct stochastic sub-models, the results of which are integrated to obtain the overall solution. Our model incorporates the important aspects of cloud centers such as pool management, compound requests (i.e., a set of requests submitted by one user simultaneously), resource virtualization and realistic servicing steps. In this manner we obtain not only a detailed assessment of cloud center performance, but also clear insights into equilibrium arrangement and capacity planning that allows servicing delays, task rejection probability, and power consumption to be kept under control. Index Terms—cloud computing, performance analysis, response time, blocking probability, pool management schema, power consumption, interacting Markov models. F