计算机应用 ›› 2019, Vol. 39 ›› Issue (2): 330-335.DOI: 10.11772/j.issn.1001-9081.2018061201

• 人工智能 • 上一篇    下一篇

基于定期竞争学习的多目标粒子群优化算法

刘明1, 董明刚1,2, 敬超1,2   

  1. 1. 桂林理工大学 信息科学与工程学院, 广西 桂林 541004;
    2. 广西嵌入式技术与智能系统重点实验室(桂林理工大学), 广西 桂林 541004
  • 收稿日期:2018-06-12 修回日期:2018-08-23 出版日期:2019-02-10 发布日期:2019-02-15
  • 通讯作者: 董明刚
  • 作者简介:刘明(1996-),男,湖南衡阳人,硕士研究生,主要研究方向:智能计算、机器学习;董明刚(1977-),男,湖北孝感人,教授,博士,CCF会员,主要研究方向:智能计算、机器学习;敬超(1983-)男,河南长葛人,讲师,博士,CCF会员,主要研究方向:数据中心管理。
  • 基金资助:
    国家自然科学基金资助项目(61563012,61203109,61802085);广西自然科学基金资助项目(2014GXNSFAA118371,2015GXNSFBA139260)。

Scheduled competition learning based multi-objective particle swarm optimization algorithm

LIU Ming1, DONG Minggang1,2, JING Chao1,2   

  1. 1. College of Information Science and Engineering, Guilin University of Technology, Guilin Guangxi 541004, China;
    2. Guangxi Key Laboratory of Embedded Technology and Intelligent System(Guilin University of Technology), Guilin Guangxi 541004, China
  • Received:2018-06-12 Revised:2018-08-23 Online:2019-02-10 Published:2019-02-15
  • Supported by:
    This work is partially supported by the National Natural Science Foundation of China (61563012, 61203109, 61802085), the Guangxi Natural Science Foundation (2014GXNSFAA118371, 2015GXNSFBA139260).

摘要: 为提高种群的多样性和算法的收敛性,提出一种基于定期竞争学习机制的多目标粒子群算法。该算法将多目标粒子群算法和竞争学习机制相结合,即每隔一定迭代代数便使用一次竞争学习机制,很好地保持了种群的多样性;同时,该算法不需要全局最优粒子的外部存档,而是从当前代种群中选取一部分优秀的粒子,再从这些优秀的粒子中随机选取一个作为全局最优粒子,能够有效提升算法的收敛性。将提出的算法与基于分解的多目标粒子群算法(MPSOD)、基于竞争机制且快速收敛的多目标粒子群(CMOPSO)算法、参考向量引导的多目标进化算法(RVEA)等8个算法在21个标准测试函数上进行了比较,结果表明,所提算法的帕累托(Pareto)前沿更加均匀,在世代距离(IGD)上会更加小。

关键词: 多目标优化, 粒子群优化, 定期竞争, 竞争学习机制, 全局最优选取策略

Abstract: In order to improve the diversity of population and the convergence performance of algorithm, a Scheduled competition learning based Multi-Objective Particle Swarm Optimization (SMOPSO) algorithm was proposed. The multi-objective particle swarm optimization algorithm and the competition learning mechanism were combined and the competition learning mechanism was used in every certain iterations to maintain the diversity of the population. Meanwhile, to improve the convergence of algorithm without using the global best external archive, the elite particles were selected from the current swarm, and then a global best particle was randomly selected from these elite particles. The performance of the proposed algorithm was verified on 21 benchmarks and compared with 8 algorithms, such as Multi-objective Particle Swarm Optimization algorithm based on Decomposition (MPSOD), Competitive Mechanism based multi-Objective Particle Swarm Optimizer (CMOPSO) and Reference Vector guided Evolutionary Algorithm (RVEA). The experimental results prove that the proposed algorithm can get a more uniform Pareto front and a smaller Inverted Generational Distance (IGD).

Key words: multi-objective optimization, Particle Swarm Optimization (PSO), scheduled competition, competitive learning mechanism, global best selection strategy

中图分类号: