Improving Golden Eagle Optimization Algorithm Through Using Wavelet Mutation

The Golden Eagle Optimization (GEO) algorithm is another amazing nature inspired optimization algorithm based on the foraging behavior of the Golden Eagles. GEO is an excellent behavioral model of how Golden Eagles interact with one another while searching for prey, consisting of a population of virtual “eagles” that together represent potential solutions to the optimization problem. The “eagles” interact with one another and together communicate and move as a single unit towards something, in this case the optimal solution. In this paper, we expand upon this idea with a new version of the GEO algorithm, called Wavelet Mutation Golden Eagle Optimization (WMGEO). WMGEO introduces a wavelet mutation function into the GEO framework, which will allow the WMGEO algorithm to allow greater exploration and improved overall algorithm performance when solving difficult optimization problems. The WMGEO algorithm ultimately aims to resolve certain constraints exhibited in the GEO algorithm. WMGEO in particular aims to improve the quality of solution, speed of solution convergence, and stability of solution. A variety of benchmark test functions are used to evaluate the efficacy of the proposed method. The benchmark functions are divided into several categories, which provide a variety of challenges for WMGEO. These test functions fall into different types, which means these tests represent a comprehensive and diverse set of challenges for WMGEO. The results of the experiments show a strong impression of the algorithm. There are significant advancements regarding solution quality and convergence speed and consequently solution stability compared to the traditional GEO algorithm. This reinforces the promise and potential for WMGEO as an optimization technique illustrating greater efficacy than its predecessor across multiple options.