摘要
元启发式群集智能优化算法通过模拟自然现象或生物行为来寻找问题的最优解,是一类成功且具有竞争力的全局优化方法。本文概述了近几年典型的元启发式群集智能优化算法及其设计原理;详细介绍了其中4类典型改进方法:种群初始化、增添新策略、迭代公式调整、算法混合;对元启发式群集智能优化算法未来的改进和发展进行了展望。
Meta-heuristic swarm intelligent optimization algorithms are successful and competitive global optimization methods.They find globally optimal solutions by simulating natural phenomena or biological behaviors.In this paper,the typical meta-heuristic swarm intelligent optimization algorithms and their design principle are introduced.Secondly,four typical improvement methods of this kind of optimization algorithm are summarized in detail.There are population initialization,adding new strategies,iterative formula adjustment,and algorithm mixing.Finally,the future improvement and development of meta-heuristic swarm intelligent optimization algorithms are prospected.
作者
张文雅
赵健
ZHANG Wenya;ZHAO Jian(School of Science,University of Science and Technology Liaoning,Anshan 114051,China)
出处
《辽宁科技大学学报》
CAS
2024年第2期129-137,共9页
Journal of University of Science and Technology Liaoning
基金
国家自然科学基金资助项目(U1731128)
辽宁省自然科学基金资助项目(2019-MS-174)
辽宁省教育厅项目(LJKZ0279)。
关键词
元启发式
群集智能优化算法
优化性能
改进方法
meta-heuristic
swarm intelligent optimization algorithm
optimize performance
improvement
