Optimal Cloud-Path Selection in Mobile Cloud Offloading Systems Based on QoS Criteria

Literature Review

Cloud service selection is a highly significant research issue but it has not been fully investigated and little literature has been published in this area since cloud computing itself is still in its early stages. In this section, we give a brief overview of the related framework in cloud service selection.

The diversity in cloud computing offering makes it difficult to compare one cloud service against others. To help cloud users in selecting a cloud provider, CloudCmp (Li, Yang, Kandula & Zhang, 2010a, 2010b) has been proposed to compare the performance of public cloud services such as Amazon EC2, Windows Azure and Google AppEngine. A set of benchmarking tools are used in CloudCmp to compare the common services (such as elastic computing cluster, persistent storage, intra-cloud and wide area network) and the benchmarking results are then used to predict the performance and costs of application when deployed on a cloud provider.

CloudRank (Zheng, Zhang & Lyu, 2010) is a collaborative QoS-driven ranking framework for cloud components to predict the quality ranking of cloud components without requiring additional real-world component invocations from the intended user. By taking advantage of the past component usage experiences of different component users, it identifies and aggregates the preferences between pair of components to produce a ranking of the components through a proposed greed method.

Multi-Criteria Comparison Method for Cloud Computing ((MC²)²) (Menzel, Schönherr & Tai, 2011) offers a multi-criteria-based decision framework that can be applied to cloud computing scenarios. (MC2)² framework aims to choose the most suitable one when filtering out all infeasible alternatives by evaluating and ranking candidate cloud services using multiple criteria derived from a comprehensive criteria catalog. As a recommendation multi-criteria decision making process, the analytic network process (ANP) employs pair-wise comparisons and normalization to assign values to quantitative and qualitative criteria on a ratio scale.