期刊
SWARM AND EVOLUTIONARY COMPUTATION
卷 48, 期 -, 页码 274-287出版社
ELSEVIER
DOI: 10.1016/j.swevo.2019.03.009
关键词
Evolutionary algorithm; Multi-objective optimization; Many-objective optimization; Reference vector adaptation; Diversity
资金
- National Natural Science Foundation of China [61440049, 61866025, 61866026]
- Natural Science Foundation of Jiangxi Province [20181BAB202025]
- Superiority Science and Technology Innovation Team Program of Jiangxi Province [20181BCB24008]
In recent years, a variety of multi-objective evolutionary algorithms (MOEAs) have been proposed in the literature. As pointed out in some recent studies, the performance of most existing MOEAs is sensitive to the Pareto front (PF) shapes of the problem to be solved, and it is difficult for these algorithms to manage diversity on various types of Pareto fronts (PFs) effectively. To address these issues, this paper proposes an evolutionary algorithm based on diversity ranking method for multi-objective and many-objective optimization. The proposed evolutionary algorithm introduces reference vector adaptation method to solve different shapes of Pareto fronts, and proposes the diversity ranking method to manage diversity. The extensive experimental results demonstrate that the proposed algorithm can solve various types of Pareto fronts, surpassing several state-of-the-art evolutionary algorithms for multi-objective and many-objective optimization.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据