Processes, Journal Year: 2022, Volume and Issue: 10(12), P. 2703 - 2703

Published: Dec. 14, 2022

Aquila Optimizer (AO) and Artificial Rabbits Optimization (ARO) are two recently developed meta-heuristic optimization algorithms. Although AO has powerful exploration capability, it still suffers from poor solution accuracy premature convergence when addressing some complex cases due to the insufficient exploitation phase. In contrast, ARO possesses very competitive potential, but its ability needs be more satisfactory. To ameliorate above-mentioned limitations in a single algorithm achieve better overall performance, this paper proposes novel chaotic opposition-based learning-driven hybrid called CHAOARO. Firstly, global phase of is combined with local maintain respective valuable search capabilities. Then, an adaptive switching mechanism (ASM) designed balance procedures. Finally, we introduce learning (COBL) strategy avoid fall into optima. comprehensively verify effectiveness superiority proposed work, CHAOARO compared original AO, ARO, several state-of-the-art algorithms on 23 classical benchmark functions IEEE CEC2019 test suite. Systematic comparisons demonstrate that can significantly outperform other competitor methods terms accuracy, speed, robustness. Furthermore, promising prospect real-world applications highlighted by resolving five industrial engineering design problems photovoltaic (PV) model parameter identification problem.

Language: Английский