An improved moth-flame optimization algorithm based on fusion mechanism
Luchao Jiang, Kuangrong Hao, Xue‐song Tang, Tong Wang, Xiaoyan Liu · 2021
Moth-flame optimization algorithms are widely employed to solve optimization problems and achieve good performance. However, the algorithms suffer the shortcoming of prematurity because of the early gathering of flames. To solve this problem, the flame fusion mechanism is integrated to improve the exploratory behavior of the moth-flame optimization algorithm. The flame fusion mechanism provides a new way to evaluate the state of flame aggregation based on the distribution of flames and moths. When the concentration of flames is higher than the fusion threshold, the better flame will fuse other flames. And the fused flames will be regenerated to enhance the exploration behavior of the algorithm. At the same time, the fusion rate that determines the probability of flame fusion is introduced. The fusion rate changes during iteration to balance the exploration and exploitation behaviors of the algorithm. The improved moth-flame optimization is validated by ten benchmark functions. The results show that the optimization ability of the improved moth-flame optimization algorithm is improved, and the stability is higher than compared algorithms as well.