Rank-based multimodal immune algorithm for many-objective optimization problems

The immune algorithm (IA) is a prestigious heuristic algorithm based on a model of an artificial immune system, and the IA has shown promising results in the multi -objective optimization field. However, the algorithm's low search ability in high -dimensional space and the clone assignment metric problem must be addressed. Thus, to solve these problems, we propose a rank -based multimodal immune algorithm (RMIA) for many -objective optimization problems. To alleviate the clone assignment metric problem, we design a novel vaccine selection mechanism, which is a rank -based clone selection method. We also propose a dynamic age -based elimination mechanism and a multimodal mutation strategy to address the poor searching ability of the IA in high -dimensional space, where the former is eliminated randomly via roulette in terms of the survival time and the advantages of antibodies in the population, and the latter adopts different mutation strategies based on the different states of antibodies. The proposed algorithm was evaluated and compared to multiple advanced multi -objective optimization immune algorithms (MOIAs) and many -objective optimization evolutionary algorithms (MaOEAs) to demonstrate its superiority. The code is available at https://github.com/AizhEngHN/RMIA.