期刊
INFORMATION SCIENCES
卷 509, 期 -, 页码 457-469出版社
ELSEVIER SCIENCE INC
DOI: 10.1016/j.ins.2018.10.007
关键词
Evolutionary algorithm; CMA-ES; Large-scale multi-objective optimization; Many-objective optimization; Scalable populations
资金
- National Science Foundation of China [41571397, 41501442, 51678077]
- Natural Science Foundation of Hunan Province [2016E3144, 2016E2006]
- Fundamental Research Funds for the Central Universities [21618329]
- Science and Technology Innovation Committee Foundation of Shenzhen grant [ZDSYS201703031748284]
- Shenzhen Peacock Plan [KQTD2016112514355531]
Despite the recent development in evolutionary multi- and many-objective optimization, the problems with large-scale decision variables still remain challenging. In this work, we propose a scalable small subpopulations based covariance matrix adaptation evolution strategy, namely S-3-CMA-ES, for solving many-objective optimization problems with large-scale decision variables. The proposed S-3-CMA-ES attempts to approximate the set of Pareto-optimal solutions using a series of small subpopulations instead of a whole population, where each subpopulation converges to only one solution. In the proposed S-3-CMA-ES, a diversity improvement strategy is designed to generate and select new solutions. The performance of S-3-CMA-ES is compared with five representative algorithms on 36 test instances with 5-15 objectives and 500-1500 decision variables. The empirical results demonstrate the superiority of the proposed S-3-CMA-ES. (C) 2018 Elsevier Inc. All rights reserved.
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