Metaheuristic Optimization Algorithms: an overview

Abstract

Metaheuristic optimization algorithms are known for their versatility and adaptability, making them effective tools for solving a wide range of complex optimization problems. They don't rely on specific problem types, gradients, and can explore globally while handling multi-objective optimization. They strike a balance between exploration and exploitation, contributing to advancements in optimization. However, it's important to note their limitations, including the lack of a guaranteed global optimum, varying convergence rates, and their somewhat opaque functioning. In contrast, metaphor-based optimization algorithms, while intuitively appealing, have faced controversy due to potential oversimplification and unrealistic expectations. Despite these considerations, metaheuristic algorithms continue to be widely used for tackling complex problems. This research paper aims to explore the fundamental components and concepts that underlie optimization algorithms, focusing on the use of search references and the delicate balance between exploration and exploitation. Visual representations of the search behavior of selected metaheuristic algorithms will also be provided.