Chaotic Spider Monkey Optimization Algorithm with Enhanced Learning

Spider monkey Optimization (SMO) algorithm is a category of swarm intelligence-based algorithms, which mimics the fission–fusion social system (FFSS) comportment of spider monkeys. Although, SMO is proven to be a balanced algorithm, i.e., it balances the exploration and exploitation phenomena, sometimes the performance of SMO is degraded due to slow convergence in the search process. This article presents an efficient modified SMO algorithm which is capable of suppressing these inadequacies and is named as chaotic spider monkey optimization with enhanced learning (CSMO) algorithm. In this proposed algorithm, a chaotic factor is introduced in the Global Leader stage for providing appropriate stochastic nature and enhanced learning methods are commenced over the Local Leader stage and the Local Leader Learning stage in the form of learning method and exploring method, respectively. These changes help to enhance the exploration and exploitation proficiencies of SMO algorithm. Moreover, this proposed strategy is analysed on 12 different benchmark functions, and the results are being contrasted with original SMO and two of its recent variants, namely power law-based local search in SMO (PLSMO) and Levy flight SMO (LFSMO).