Research On Improved Spider Monkey Optimization Based On Dynamic Adaptive Inertia Weight

Biology-inspired algorithms are becoming more powerful in modern numerical optimization,especially for NP problems such as traveling salesman problems.Among these biology-derived algorithm,swarm intelligence algorithms such as Particle Swarm Optimization,Ant Colony Optimization,Artificial Bee Colony algorithm and Firefly Algorithm have become hot research topics in optimization and other applications.This paper aims to introduce a new optimization algorithm: Spider Monkey Optimization.The algorithm is a swarm intelligence optimization algorithm inspired by simulating the foraging behavior of spider monkeys.It simulates the fission-fusion mechanism of spider monkey population in real life to find the optimal value of the function.Numerical experiments show that the algorithm has the advantages of simple principle,high efficiency and few control parameters.Firstly,this article provides an overview of existing swarm intelligence algorithms,especially Particle Swarm Optimization.Secondly,this thesis analyzes and studies the Spider Monkey Optimization in detail,and uses the diagram to describe the optimization mechanism of the algorithm in detail.In order to enhance the local search performance of SMO,an algorithm based on dynamic self-adaptive inertia weight is proposed.By introducing the value of the objective function in the inertia weight,the change of inertia weight has directionality,which reduces the blindness of its change,and effectively balances the global exploration ability and local exploitation ability of the algorithm.The improved spider monkey algorithm was tested on function optimization problems.The simulation results show that the new algorithm can effectively improve the function optimization accuracy and the convergence speed,and has a strong stability.