[1]汪慎文,张佳星,褚晓凯,等.两阶段搜索的多模态多目标差分进化算法[J].郑州大学学报(工学版),2021,42(01):9-14.[doi:10.13705/j.issn.1671-6833.2021.01.002]
 Wang Shenwen,Zhang Jiaxing,Chu Xiaokai,et al.Multimodal Multi-ob<x>jective Differential Evolution Algorithm ba<x>sed On Two-stage Search[J].Journal of Zhengzhou University (Engineering Science),2021,42(01):9-14.[doi:10.13705/j.issn.1671-6833.2021.01.002]
点击复制

两阶段搜索的多模态多目标差分进化算法()
分享到:

《郑州大学学报(工学版)》[ISSN:1671-6833/CN:41-1339/T]

卷:
42卷
期数:
2021年01期
页码:
9-14
栏目:
出版日期:
2021-03-14

文章信息/Info

Title:
Multimodal Multi-ob<x>jective Differential Evolution Algorithm ba<x>sed On Two-stage Search
作者:
汪慎文张佳星褚晓凯刘䫺王晖
河北地质大学信息工程学院;河北地质大学人工智能与机器学习研究室;中国信息通信研究院泰尔终端实验室;南昌工程学院信息工程学院;

Author(s):
Wang Shenwen; Zhang Jiaxing; Chu Xiaokai; Liu Yefeng; Wang Hui;
Institute of Information Engineering, Hebei University of Geosciences; Artificial Intelligence and Machine Learning Laboratory of Hebei University of Geology; Terr Terminal Laboratory of the China Institute of Information and Communication; School of Information Engineering, Nanchang Institute of Engineering;

关键词:
Keywords:
DOI:
10.13705/j.issn.1671-6833.2021.01.002
文献标志码:
A
摘要:
在多模态多目标优化问题中,决策空间的多个Pareto最优解往往对应目标空间中Pareto前沿的同一位置。针对这种问题提出了一种两阶段搜索的多模态多目标差分进化算法,该算法将优化过程分为了精英搜索和分区搜索两个阶段。在精英搜索阶段通过精英变异策略生成高质量个体来保障种群的搜索精度和效率;在分区搜索阶段将决策空间分为若干子空间,利用已探测到的种群对各个子空间进行深度探索,降低问题复杂度的同时提高种群在决策空间的扩展性和均匀性。该算法在18个多模态多目标优化测试函数上与常见的5种算法进行了性能比较。实验结果证明了该算法的有效性。
Abstract:
In the multi-modal multi-ob<x>jective optimization problem, the more decision-making space Pareto optimal solutions often correspond to the target space in the same location Pareto frontier. In response to this problem, a two-stage search multi-modal multi-ob<x>jective differential evolution algorithm is proposed. The algorithm divides the optimization process into elite search and partition search. In the elite search stage, high-quality population are generated through elite mutation strategies to ensure the search accuracy and efficiency of the population In the partition search stage, the decision space is divided into several subspaces, use the detected population to conduct deep exploration of each subspace, reduce the complexity of the problem while improving the scalability and uniformity of the population in the decision space. The algorithm is compared with the common five algorithms on 18 multi-modal multi-ob<x>jective optimization test functions. Experimental results prove the effectiveness of the algorithm

相似文献/References:

[1]吴擎,张春江,高亮.经济负荷分配问题中的约束处理方法研究[J].郑州大学学报(工学版),2019,40(03):36.[doi:10.13705/j.issn.1671-6833.2018.06.003]
 Wu Qing,Zhang Chunjiang,Gao Liang.Study of Constraint Handling methods in Economic Load Dispatch Problem[J].Journal of Zhengzhou University (Engineering Science),2019,40(01):36.[doi:10.13705/j.issn.1671-6833.2018.06.003]
[2]张勇,高光辉,郭一楠,等.融合差分进化和Taylor级数的超宽带定位解算方法[J].郑州大学学报(工学版),2020,41(01):70.[doi:10.13705/j.issn.1671-6833.2019.04.013]
 Zhang Yong,high brilliance,Guo Yinan,et al..:2013Ultra-wideband Positioning Memetic Solution Method Based on Differential Evolution and Taylor Series[J].Journal of Zhengzhou University (Engineering Science),2020,41(01):70.[doi:10.13705/j.issn.1671-6833.2019.04.013]
[3]梁静,周钦亚,瞿博阳,等.基于混合策略的差分进化算法[J].郑州大学学报(工学版),2013,34(05):59.[doi:10.3969/j.issn.1671-6833.2013.05.013]

更新日期/Last Update: 2021-03-15