Recent Advances and Real-World Implementations of the Whale Optimization Algorithm

Abstract

The Whale Optimization Algorithm (WOA) has rapidly evolved as a novel bio-inspired metaheuristic technique, drawing significant attention in the optimization community since its inception in 2016. Inspired by the bubble-net hunting behavior of humpback whales, WOA begins with a simple yet effective mechanism that balances exploration and exploitation in search space. Over the years, numerous enhancements, hybridizations, and applications of WOA have been proposed, addressing complex constrained engineering design problems, renewable energy systems management, feature selection in machine learning, resource allocation in wireless networks, and hyperparameter tuning in deep neural networks. In this review, we provide an in-depth analysis of recent advances in WOA from 2016 to 2024, highlighting algorithmic developments and real-world implementations. We categorize the variants into parameter-controlled, hybridized, binary, and multi-objective forms, and we examine their performance against benchmark functions and practical scenarios in industrial applications. Performance comparisons are supported by convergence studies and transient response analysis from applications such as automatic generation control of modern power systems and photovoltaic system optimization. The review further discusses theoretical aspects such as convergence properties, computational complexity, and stability, while also identifying challenges like premature convergence and scalability issues. Finally, future research directions including self-adaptive strategies, quantum-inspired frameworks, and explainable optimization methods are discussed. The comprehensive overview presented here is intended to inform researchers and practitioners about the recent trends, successes, and remaining challenges of WOA in real-world applications, thereby contributing to further research and development in metaheuristic optimization techniques.