Cost-Evaluation Of Cloud Portfolios: An Empirical Case Study

Today, Amazon is the Cloud service market leader with the EC2 platform. Three predominant marketspaces exist on this platform: spot marketspace, reservation marketspace, and the well-known on-demand marketspace. Also other providers such as Google, Microsoft and VirtuStream run multiple marketspaces. Consumers can purchase their virtual machines from different providers on different marketspace to form Cloud portfolios: a bundle of virtual machines whereby the virtual machines have different technical characteristics and pricing mechanisms. An industry-relevant research challenge is to provide best practices and guidelines for creating cost-efficient Cloud portfolios. In this paper, we used Amazon's marketspaces and the dataset from the Bitbrains datacenter to analyze the cost-efficiency of heterogeneous Cloud portfolios - portfolios where the virtual machines are purchased from different marketspaces. We found out that heterogeneous portfolios are more cost-efficient than homogeneous portfolios for almost all analyzed situations. Our analysis further revealed that consumers request virtual machines that are over-sized which forms a significant field of cost-optimization. A second dataset from the Bitbrains datacenter - from another domain of application validates our findings.