Methodology to Determine Relationships between Performance Factors in Hadoop Cloud Computing Applications

Cloud Computing is a model for enabling ubiquitous, convenient, on-demand network access to a shared pool of configurable computing resources. Cloud Computing users prefer not to own physical infrastructure, but instead rent Cloud infrastructure, a Cloud platform or software, from a third-party provider. Sometimes, anomalies and defects affect a part of the Cloud platform, resulting in degradation of the Cloud performance. One of the challenges in identifying the source of such degradation is how to determine the type of relationship that exists between the various performance metrics which affect the quality of the Cloud and more specifically Cloud applications. This work uses the Taguchi method for the design of experiments to propose a methodology for identifying the relationships between the various configuration parameters that affect the quality of Cloud Computing performance in Hadoop environments. This paper is based on a proposed performance measurement framework for Cloud Computing systems, which integrates software quality concepts from ISO 25010 and other international standards.