Fuzzy logic and MCDA in IoT resources classification

Abstract

Internet of Things is characterized by a lot of resources connected to the Internet, many simultaneously requesting and providing services. The adequate selection of resources that best meets the demands of users with a broad range of options has been a relevant and current research challenge. Based on the non-functional parameters of QoS, it plays a significant role in the ranking of these resources according to the services they offer. This work presents a proposal to classify and select the most appropriate resource to the client's request, using fuzzy logic to treat uncertainties in the definition of ideal weights for QoS attributes. It also proposes to add fuzzy logic in the pre-classification of resources, to reduce the computational cost generated by MCDA algorithms. The accuracy of the proposed model in the pre-classification of the best resources is presented, and the results obtained are promising and indicate the continuity of the research.