A multi-layered gravitational search algorithm for function optimization and real-world problems

被引：144

作者：

Wang, Yirui ^{[1
]}

Gao, Shangce ^{[1
]}

Zhou, Mengchu ^{[2
]}

Yu, Yang ^{[1
]}

机构：

[1] Univ Toyama, Fac Engn, Toyama 9308555, Japan

[2] New Jersey Inst Technol, Dept Elect & Comp Engn, Newark, NJ 07102 USA

来源：

IEEE-CAA JOURNAL OF AUTOMATICA SINICA | 2021年 / 8卷 / 01期

基金：

中国国家自然科学基金;

关键词：

Artificial intelligence; exploration and exploitation; gravitational search algorithm; hierarchical interaction; hierarchy; machine learning; population structure; PARTICLE SWARM OPTIMIZATION; DIFFERENTIAL EVOLUTION; POPULATION INTERACTION; HYBRID ALGORITHM; NEURAL-NETWORKS; FUZZY-LOGIC; SCALE-FREE; GSA; DESIGN; TOPOLOGIES;

D O I：

10.1109/JAS.2020.1003462

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

A gravitational search algorithm (GSA) uses gravitational force among individuals to evolve population. Though GSA is an effective population-based algorithm, it exhibits low search performance and premature convergence. To ameliorate these issues, this work proposes a multi-layered GSA called MLGSA. Inspired by the two-layered structure of GSA, four layers consisting of population, iteration-best, personal-best and global-best layers are constructed. Hierarchical interactions among four layers are dynamically implemented in different search stages to greatly improve both exploration and exploitation abilities of population. Performance comparison between MLGSA and nine existing GSA variants on twenty-nine CEC2017 test functions with low, medium and high dimensions demonstrates that MLGSA is the most competitive one. It is also compared with four particle swarm optimization variants to verify its excellent performance. Moreover, the analysis of hierarchical interactions is discussed to illustrate the influence of a complete hierarchy on its performance. The relationship between its population diversity and fitness diversity is analyzed to clarify its search performance. Its computational complexity is given to show its efficiency. Finally, it is applied to twenty-two CEC2011 real-world optimization problems to show its practicality.

引用

页码：94 / 109

页数：16