A New Interval Type-2 Fuzzy Logic Variant of the Multiverse Optimizer Algorithm

This paper presents a new variant of the Multiverse Optimizer Algorithm (MVO) that can use the advantages of fuzzy logic, by implementing an interval type-2 fuzzy inference system. In this new variant of Fuzzy Multi Verse Optimizer (FMVO), we are testing over 13 benchmark mathematical functions used in MVO tests, this to compare between the original MVO algorithm and the type-1 variant of the same algorithm, where fuzzy logic was used to adjust two main parameters responsible for exploration and exploitation in the algorithm, that were previously adapted in type-1 variants and resulted beneficial to the algorithm, improving convergence and diversity in the obtained solutions of the cases where the algorithm is used. The change to an interval type-2 fuzzy inference system, adjusts the algorithm to perform better in more complex problems, resulting in a more competitive variant of the MVO algorithm. In addition to benchmark mathematical functions, we compare the algorithm with the shower fuzzy controller optimization case. The objective of this work is to introduce a new variant of the algorithm, that takes advantage of type-2 fuzzy logic for both simple and more complex cases of study, to compare the improvement of the algorithm, and then scale to other cases in fuzzy controller design.