期刊
IEEE ACCESS
卷 6, 期 -, 页码 26194-26214出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2018.2832181
关键词
Evolutionary computation; experimental comparison; HV; IGD; multi-objective optimization
资金
- National Natural Science Foundation of China [61403404, 61773390, 71571187, 71371181]
- Distinguished Natural Science Foundation of Hunan Province [2017JJ1001]
With the increasing attention paid to many-objective optimization in the evolutionary multi-objective optimization community, various approaches have been proposed to solve many-objective problems. However, existing experimental comparative studies are usually restricted to a few methods. Few studies have encompassed most of the recently proposed state-of-the-art approaches and made an experimental comparison. To this end, this paper offers a systematic comparison of 13 algorithms covering various categories to solve many-objective problems. The experimental comparison is conducted on three groups of test functions by using two performance metrics and a visual observation in the decision space. The experimental results demonstrate that different approaches have different search abilities. None of the test approaches outperform the others on all types of problems. However, some of the approaches are competitive on a large number of test problems. Moreover, inconsistent results from the hypervolume and the inverted generational distance metrics are revealed in this paper. Based on these comparative results, researchers can obtain useful suggestions for choosing appropriate algorithms for different problems.
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