Home // International Journal On Advances in Telecommunications, volume 14, numbers 1 and 2, 2021 // View article

Cloud Cost Optimization Based on Shifted N-policy M/M/M/K Queue Model

Authors:
Zsolt Saffer

Keywords: optimization; cloud model; queueing model; N-policy.

Abstract:
Cloud cost optimization is an important issue having also impact on the economy of the Cloud service, since it enables the Cloud service provider the service provisioning at minimum cost. This paper provides the performance analysis and cost optimization of an Infrastructure-as-a-Service Cloud model with a capacity control policy. The Virtual Machines are modelled as parallel resources, which can be either in active or in standby state. The capacity of the cloud is controlled by changing the number of active Virtual Machines. The cost model, which the cloud provider encounters, takes into account both energy consumption and performance measures. The major objective of the work is to provide a tractable analytic model, which is suitable for practical use. For this purpose, we model the Cloud services by an M/M/M/K queue. We propose a simple control policy, in which a predefined portion of Virtual Machines are always active. The remaining ones are activated simultaneously when the number of requests reaches a threshold and deactivated when the number of requests falls below the predefined portion of active Virtual Machines. We call this policy as shifted N-policy. We provide the stationary analysis of the model and derive closed form results for the distribution of the number of requests as well as for several performance measures. The cost model leads to a discrete optimization task, which we approximate by a nonlinear continuous optimization task. After applying numerous approximations, we provide, in form of solution formulas, approximate solutions of the optimization task in the two most relevant traffic ranges. We give illustrating examples for the most important approximations and properties of the model as well as validate the approximate solution formulas by numeric optimization. The major results of the work are the closed form approximate solution formulas, which give the optimal threshold under the most relevant ranges of parameters and provide insight into the dependency of the optimum on the model and cost parameters.

Pages: 70 to 99

Copyright: Copyright (c) to authors, 2021. Used with permission.

Publication date: December 31, 2021

Published in: journal

ISSN: 1942-2601