Analysis of Workloads for Cloud Services

Capturing best quality datasets for a study is the first evidence for better outcomes of research. If the analysis are based on such datasets, then the metrics, the characteristics and few factors determines proof point for well proven theories. Hence it is obvious that we rely on the best possible ways to arrive at such data acquiring sources. It can be either based on historical techniques or from the innovations in application of it to industry. This paper introduces a mapping framework for analyzing, and characterizing data previously used by research community and how they are made to fit for Cloud systems, i.e. using “workloads” and “datasets” as the “refined definitions”. It was contributed in the past two decades within the scientific community setting their own workflow analysis mechanisms. The framework thus is validated by acquiring a sample workload per layer of cloud. The sources are form the literature that are available from existing scientific theories. These workloads are then experimented against the three tiers of the cloud computing ie., IaaS(Infrastructure as a Service), PaaS(Platform as a Service), & SaaS(Software as a Service). The selected data is analyzed by the authors for an offline model presented here based on the Machine Learning tool-kits. There are future studies planned for and to be experimented in a cloud auto scaled environment with online model as well.