A Comprehensive Survey of Manta Ray Foraging Optimization: Theory, Variants, Hybridization, and Applications

Abstract

The Manta Ray Foraging Optimization (MRFO) algorithm is a recent Swarm-based meta-heuristic optimization algorithm inspired by the foraging behavior of manta rays in catching and hunting their prey, utilizing three main techniques (i.e.: chain foraging, somersault foraging, and cyclone foraging). Since its development by Zhao et al. (Neural Comput Appl 32:9777–9808, 2020; Eng Appl Artif Intell 87:103300, 2020), the MRFO algorithm has garnered significant attention among researchers and has been applied across various fields to solve real-world optimization problems. This is due to its simple structure, flexibility, ease of implementation, and reasonable convergence rate. This paper provides an extensive and in-depth survey of the MRFO algorithm including modification, multi-objective, and hybridized versions. It also examines the various applications of the MRFO algorithm in several domains of problems such as classification, feature selection, scheduling, robotics, photovoltaic power systems, optimal parameter control, and clustering. Furthermore, the results of the MRFO algorithm are compared with some well-regarded optimization meta-heuristics such as Differential Evolution (DE), Harmony Search (HS), Bat Algorithm (BA), Multi-Verse Optimizer (MVO), Grey Wolf Optimization (GWO), Sine Cosine Algorithm (SCA), Moth Flame Optimization (MFO), Henry Gas Solubility Optimization (HGSO), and White Shark Optimizer (WSO). Finally, the paper proposes some potential future research directions to further advance the MRFO’s capability and applicability