Improved Research Based On Grey Wolf Optimizer Algorithm And Its Application

As an important branch of meta-heuristic intelligent optimization algorithm,swarm intelligence algorithm is favored by many scholars because of its strong adaptability and can be used to solve the complex optimization problems that traditional deterministic optimization algorithms can not solve.As an emerging population intelligent optimization algorithm proposed in2014,grey wolf optimizer algorithm has some merits,such as less parameters,easy to implement and strong local search ability.However,there still exist some problems such as easy to fall into local optimum and convergence accuracy in the face of complex problems is not high,the convergence rate is not fast enough,and other shortcomings,and its scope of application is currently narrow.In view of this,this article made improvements to the standard grey wolf optimizer algorithm,and applies the improved grey wolf optimizer algorithm to the design field of FIR digital filters and array antennas.The main research results include:1.Studied the standard grey wolf optimizer algorithm from the basic principle and mathematical model of the algorithm,analyzed the convergence of the algorithm,and compared with the two typical intelligent optimization algorithms,Particle Swarm Optimization and Differential Evolution Algorithm.Points out the shortcomings of the algorithm and provides ideas for subsequent improvement.2.In order to further improve the optimization ability and convergence speed of the grey wolf optimizer algorithm,the main improvements made in this paper are as follows: Firstly,the initial population is initialized by using the good point set theory to ensure the initial uniformity.Secondly,a new adaptive mutation method and extrapolation strategy are proposed by integrating differential evolution algorithm to improve global optimization ability.Then,after analyzing the location updating mechanism of the standard grey wolf optimizer algorithm,a strategy of segment updating step is proposed to keep the diversity of the population.In addition,the original search space of the algorithm is mapped to a hypersphere to make a disturbance strategy to avoid premature convergence of the algorithm.Finally,the global optimum location adopts the dimension-by-dimension updating strategy to improve the optimization efficiency and global optimization ability of the algorithm.The validity of the improved algorithm is verified by using standard test functions.3.The improved grey wolf optimizer algorithm is applied to the FIR digital filter coefficients optimization;4.The improved grey wolf optimizer algorithm is applied to the field of array antennas.Experimental tests show that the improved algorithm has obvious advantages over the traditionalanalytical methods and the standard grey wolf optimizer algorithm.