Business-driven capacity planning of a cloud-based it infrastructure for the execution of Web applications

With the emergence of the cloud computing paradigm and the continuous search to reduce the cost of running Information Technology (IT) infrastructures, we are currently experiencing an important change in the way these infrastructures are assembled, configured and managed. In this research we consider the problem of managing a computing infrastructure whose processing elements are acquired from infrastructure-as-a-service (IaaS) providers, and used to support the execution of long-lived on-line transactions processing applications, whose workloads experience huge fluctuations over time, such as Web applications. Resources can be acquired from IaaS providers in different ways, each with its own pricing scheme and associated quality of service. One acquisition model allows resources to be reserved for long periods of usage at a reduced usage price, while others allow dedicated resources to be instantiated on demand at any time, subject to the availability of resources, with a usage price that is usually larger than that paid for reserved resources. In this context, the problem that we address in this paper is how the provider of a Web application should plan the long-term reservation contracts with an IaaS provider, in such a way that its profitability is increased. We propose a model that can be used for guiding this capacity planning activity. We use the model to evaluate the gains that can be achieved with the judicious planning of the infrastructure capacity in a number of scenarios. We show that the gains can be substantial, specially when the load variation between normal operational periods and surge periods is large.