Hyperbolic Spider Monkey Optimization Algorithm

Abstract

Background: Spider monkey optimization algorithm is recently developed natureinspired algorithm. It is based on fission-fusion social structure of spider monkeys. Perturbation rate is one of the important parameter of spider monkey optimization algorithm, which affects the convergence behavior of spider monkey optimization algorithm. Generally, perturbation rate is a linearly increasing function. However, due to the availability of non-linearity in different applications, a non-linear function may affect the performance of spider monkey optimization algorithm. Objective: This paper provides a detailed study on various perturbation techniques used in spider monkey optimization algorithm and recommends a novel alternative of hyperbolic spider monkey optimization algorithm. The new approach is named as hyperbolic Spider Monkey Optimization algorithm as the perturbation strategy inspired by hyperbolic growth function. Methods: The proposed algorithm is tested over a set of 23 CEC 2005 benchmark problems. Results: The experimental outcomes illustrate that the hyperbolic spider monkey optimization algorithm effectively increase the reliability of spider monkey optimization algorithm in comparison to the considered approaches. Conclusion: The hyperbolic spider monkey optimization algorithm provides improved perturbation rate, desirable convergence precision, rapid convergence rate, and improved global search capability.