Research Based on The Improved Grey Wolf Optimization Algorithm

Abstract

With the continuous progress of machine learning methods, more and more methods are widely used in various fields. Grey Wolf Optimization Algorithm (GWO), as a kind of population algorithm, has become a research hotspot in recent years because of its good optimization ability. Similar to other population algorithms, gray wolf optimization algorithm itself has the problem of imbalance between global search and local search capabilities. In order to solve this problem, the following improvements are proposed to the standard gray wolf optimization algorithm: First, change the decrement method of the convergence factor and adopt a non-linear decrement method to meet the actual search process; At the same time, a weighting strategy is introduced to dynamically assign weights to the guide wolves. It can ensure that the population jumps out of the local optimal solution. In order to verify the effectiveness of the improved algorithm, an international general test function is selected for simulation. The simulation results show that the improved gray wolf optimization algorithm has faster convergence speed, higher solution accuracy and better stability.