Design of a cloud brokerage architecture using fuzzy rough set technique

Abstract

Cloud computing offers numerous services to the cloud consumers such as infrastructure, platform, software, etc. Due to the vast diversity in available cloud services from the user point of view, it leads to several challenges to rank and select the potential cloud service. One of the plausible solutions for the problem can be obtained with the use of Rough Set Theory (RST) and available in the literature. Unfortunately, Rough Set Theory cannot deal with numerical values. One of the classical solutions to this problem can be obtained by using Fuzzy Rough Set. To the best of our knowledge, there is no working Fuzzy-Rough Set based brokerage architecture available which is used for minimizing attributes, search space and for ranking the service providers. In this paper, we proposed a Fuzzy Rough Set based Cloud Brokerage (FRSCB) architecture, which is responsible for service selection based on consumers Quality of Service (QoS) request. We propose to use Fuzzy Rough Set Theory (FRST) to minimize the number of attributes and searching space. We also did the QoS attribute categorization to identify functional and non-functional requirements and behavior of the attributes (static/dynamic). Finally, we develop an algorithm that recommends potential cloud services to the cloud consumers.