Power-aware Admission Control and Virtual Machine Allocation for Cloud Applications

Different service providers in the cloud computing environment assume different responsibilities. Software as a Service (SaaS) providers have to respond to users' requests within an acceptable deadline determined in their Service Level Agreement (SLA) contracts, while Infrastructure as a Service (IaaS) providers mostly care about the infrastructural resources. Power and cooling management and pricing of available resources are concerns of IaaS providers. The goal of an SaaS provider is to maximize the revenue from SLAs and minimize the cost of using IaaS resources. An IaaS provider wants to maximize the prices of its own resources that it charges its clients, and at the same time minimize the total power consumption of infrastructural resources. Each provider's decision may affect the other providers' strategies. In this paper, we propose a power-aware algorithm for both IaaS and SaaS providers to jointly and optimally control the admission rate and allocate the resources. We simulate different scenarios to substantiate the viability of our proposed scheme.