Enhancing Global Optimization Performance of Arithmetic Optimization Algorithm with a Modified Population Initialization Scheme

Abstract

Arithmetic Optimization Algorithm (AOA) is widely used to solve global optimization problems. However, it often faces premature convergence challenges in complex optimization scenarios. A key factor affecting AOA's performance is the solution quality of the initial population. The conventional initialization scheme, despite its prevalence, lacks reliability in ensuring high-quality solutions due to inherent stochastic processes. To address this issue, we propose a modified initialization scheme that improves initial population quality by integrating chaotic maps and oppositional-based learning. Through extensive simulation studies, we demonstrate that the enhanced AOA, equipped with this new initialization scheme, exhibits superior performance in solving a range of benchmark functions with improved accuracy.