Abstract
The Aquila Optimizer (AO) is a novel and efficient optimization algorithm inspired by the hunting and searching behavior of Aquila. However, the AO faces limitations when tackling high-dimensional and complex optimization problems due to insufficient search capabilities and a tendency to prematurely converge to local optima, which restricts its overall performance. To address these challenges, this study proposes the Multi-Strategy Aquila Optimizer (MSAO) by integrating multiple enhancement techniques. Firstly, the MSAO introduces a random sub-dimension update mechanism, significantly enhancing its exploration capacity in high-dimensional spaces. Secondly, it incorporates memory strategy and dream-sharing strategy from the Dream Optimization Algorithm (DOA), thereby achieving a balance between global exploration and local exploitation. Additionally, the MSAO employs adaptive parameter and dynamic opposition-based learning to further refine the AO's original update rules, making them more suitable for a multi-strategy collaborative framework. In the experiment, the MSAO outperform eight state-of-the-art algorithms, including CEC-winning and enhanced AO variants, achieving the best optimization results on 55%, 69%, 69%, and 72% of the benchmark functions, respectively, which demonstrates its outstanding performance. Furthermore, ablation experiments validate the independent contributions of each proposed strategy, and the application of MSAO to five engineering problems confirms its strong practical value and potential for broader adoption.