Cognitive Radio Engine Design for IoT Using Monarch Butterfly Optimization and Fuzzy Decision Making

Abstract

The Internet of Things (IoT) paradigm expands the current Internet and enables communication through machine to machine (M2M), while posing new challenges. Cognitive Radio (CR) Systems have received much attention over the last decade, because of their ability to flexibly adapt their transmission parameters to their changing environment. Current technology trends are shifting to the adaptability of Cognitive Radio Networks (CRNs) into IoT. The determination of the appropriate transmission parameters for a given wireless channel environment is the main feature of a cognitive radio engine. For wireless multicarrier transceivers, the problem becomes high dimensional due to the large number of decision variables required. Evolutionary Algorithms (EAs) are suitable techniques to solve the above-mentioned problem. In this chapter, we propose a new approach for designing a CR engine for wireless multicarrier transceivers using monarch butterfly optimization (MBO). Moreover, we also apply a modified MBO version that includes a Greedy strategy and a self-adaptive Crossover operator, called Greedy Crossover MBO (GCMBO). Additionally, the CR engine also uses a fuzzy decision maker for obtaining the best compromised solution. The simulation results show that the GCMBO driven CR engine can obtain better results than the original MBO and outperform other popular algorithms. Moreover, GCMBO is more efficient when applied to high-dimensional problems in cases of multicarrier system.