Membrane-based models for service selection in cloud

Abstract

Cloud service selection is one of the prime areas of research within the ambit of cloud computing, which has gained wide attention in the recent past. The service selection algorithm primarily involves selecting the best service from a set of available services, based on Quality of Service (QoS) attributes. The QoS attributes are the parameters which allow the users to ascertain the actual quality of the service, often quantitatively. Over the years, there have been several methods designed for service selection in the cloud that are primarily sequential, with many being sensitive to changes. Thus, the aim is to propose multiple robust and parallel models for cloud service selection. The proposed models are designed using Membrane Computing paradigm, which is an inherently parallel computing model, combined with the Improved Technique for Order of Preference by Similarity to Ideal Solution (ITOPSIS), a popular Multi-Criteria Decision Making Method. Two methods based on a tactical amalgamation of ITOPSIS and Enzymatic Numerical P System (A membrane computing device variant) structure are proposed here. The proposed parallel models are implemented, tested, and the obtained results are analyzed. The results indicate one model to be robust (less sensitive) and the other to be moderately sensitive. © 2020 Elsevier Inc.