Investigation of Suitable Perturbation Rate Scheme for Spider Monkey Optimization Algorithm

摘要

Spider Monkey Optimization (SMO) is a new metaheuristic whose strengths and limitations are yet to be explored by the research community. In this paper, we make a small but hopefully significant effort in this direction by studying the behaviour of SMO under varying perturbation rate schemes. Four versions of SMO are proposed corresponding to constant, random, linearly increasing and linearly decreasing perturbation rate variation strategies. This paper aims at studying the behaviour of SMO technique by incorporating these different perturbation rate variation schemes and to examine which scheme is preferable to others on the benchmark set of problems considered in this paper. A benchmark set of 15 unconstrained scalable problems of different complexities including unimodal, multimodal, discontinuous, etc., serves the purpose of studying this behaviour. Not only numerical results of four proposed versions have been presented, but also the significance in the difference of their results has been verified by a statistical test.