An Improved Beluga Whale Optimization Algorithm Based on Chaotic Opposition-Based Learning and Adaptive Weighting Factor

Beluga Whale Optimization (BWO) algorithm faces challenges such as slower convergence, lower accuracy, and instability for dealing with unimodal functions. To tackle these problems, we propose an enhanced version of Beluga Whale Optimization Algorithm (ABWO). ABWO algorithm incorporates chaotic Opposition-Based Learning (OBL) and adaptive weighting factor. We fuse Logistic and Tent chaotic mappings with OBL to ensure an even distribution of individuals in the initial solution space during initialization. Consequently, the population diversity is increased and the quality of the initial solution is better. The adaptive weighting factor $F$ is introduced in the exploitation phase. It increases and then decreases with each iteration. This adjustment enhances the guiding effect of the global optimal position on individual position updates in the early stage of BWO. It also enables the algorithm to execute more effective global searches in the middle stage. Meanwhile, the algorithm converges more quickly in the late stage. Overall, the solution accuracy and convergence stability of the algorithm are improved. On nine unimodal test functions, ABWO has better optimization and convergence performance compared with six basic algorithms. It also outperforms three improved beluga whale optimization algorithms proposed by other scholars.