Evaluation and Analysis of Heuristic Intelligent Optimization Algorithms for PSO, WDO, GWO and OOBO

Abstract

In order to comprehensively evaluate and analyze the effectiveness of various heuristic intelligent optimization algorithms, this research employed particle swarm optimization, wind driven optimization, grey wolf optimization, and one-to-one-based optimizer as the basis. It applied 22 benchmark test functions to conduct a comparison and analysis of performance for these algorithms, considering descriptive statistics such as convergence speed, accuracy, and stability. Additionally, time and space complexity calculations were employed, alongside the nonparametric Friedman test, to further assess the algorithms. Furthermore, an investigation into the impact of control parameters on the algorithms’ output was conducted to compare and analyze the test results under different algorithms. The experimental findings demonstrate the efficacy of the aforementioned approaches in comprehensively analyzing and comparing the performance on different types of intelligent optimization algorithms. These results illustrate that algorithm performance can vary across different test functions. The one-to-one-based optimizer algorithm exhibited superior accuracy, stability, and relatively lower complexity.