Modified Spider Monkey Optimization Algorithm Based on Self-Adaptive Inertia Weight

Abstract

Spider monkey optimization (SMO) algorithm is a new swarm intelligence optimization algorithm proposed in recent years. It simulates the foraging behavior of spider monkeys which have fission-fusion social structure (FFSS). In this paper, a modified spider monkey optimization algorithm is proposed. The self-adaptive inertia weight is introduced in the local leader phase to enhance the self-learning ability of the spider monkey. According to the function value of an individual, the distance from the optimal value is determined, so the inertia weight related the individual function value is added to strength the global search ability or local search ability. The proposed algorithm is tested on 20 benchmark problems and compared with the original SMO and the hybrid algorithm SMOGA and GASMO. The numerical results show that the proposed algorithm has a certain degree of improvement in convergence accuracy and convergence speed. The performance of the proposed algorithm is also inspected by two classical engineering design problems.