White-faced capuchin optimizer: a new bionic metaheuristic algorithm for solving optimization problems

To address the diverse requirements of various optimization problems and the inherent limitations of existing meta-heuristic algorithms, this paper introduces a novel meta-heuristic algorithm, the white-faced capuchin optimizer (WCO). The algorithm is mathematically modeled based on the foraging, social interaction, and defensive behaviors of the white-faced capuchin, incorporating various adaptive and stochastic factors to enhance its global exploration and local exploitation performance. The WCO is rigorously benchmarked against eight high-performance algorithms across four widely recognized test suites: CEC-2005 (30 dimensions and fixed dimensions), CEC-2017 (30 dimensions), CEC-2020 (20 dimensions), and CEC-2022 (20 dimensions). WCO achieves optimal performance on the above four benchmark suites, using the best average value as the standard. The success rates of optimization are 78.3%, 69%, 60%, and 66.7%, respectively. Statistical analysis through the Wilcoxon signed-rank test and Friedman test demonstrated WCO’s superior optimization accuracy and solution quality. Furthermore, WCO is tested on five engineering design problems and two path-planning scenarios, consistently delivering high-quality solutions and outperforming comparison algorithms in real-world challenges. Demonstrating robust convergence and adaptability across diverse tasks, WCO highlights its significant potential for solving real-world optimization challenges.