计算机工程与应用 ›› 2011, Vol. 47 ›› Issue (9): 51-53.

• 研究、探讨 • 上一篇    下一篇

结合局部优化算法的改进粒子群算法研究

殷 脂1,2,叶春明1,温 蜜2   

  1. 1.上海理工大学 管理学院,上海 200093
    2.上海电力学院 计算机与信息工程学院,上海 200090
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2011-03-21 发布日期:2011-03-21

Research on combination algorithm of particle swarm optimization and local optimization

YIN Zhi1,2,YE Chunming1,WEN Mi2   

  1. 1.Business School,University of Shanghai for Science and Technology,Shanghai 200093,China
    2.School of Computer and Information Engineering,Shanghai University of Electric Power,Shanghai 200090,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2011-03-21 Published:2011-03-21

摘要: 提出了结合局部优化算法的改进粒子群算法(Combination Particle Swarm Optimization,CPSO),粒子群算法虽然通过群体规模来规避早熟,但缺乏局部快速搜索能力,因此将局部优化算法与改进粒子群算法相结合,并尝试不同的局部优化算法,例如牛顿法、最速下降法,通过典型函数优化实验表明,与其他改进粒子群算法相比,CPSO具有较强的寻优能力,鲁棒性和较快的收敛速度;实验也表明不同的局部优化算法在不同的特征函数上体现出不同的优势。

关键词: 粒子群优化算法, 牛顿法, 最速下降法, 优化效率

Abstract: This paper proposes an algorithm which is a combination algorithm of particle swarm optimization and local optimization named CPSO.CPSO incorporates the advantages of the local optimization and PSO.Different local optimization algorithms are tried.Finally several experiments are performed on typical functions.Compared with other PSO algorithms,CPSO shows excellent global searching,robustness and rapid constringency;several numerical examples also show that different local optimization algorithms own their different advantages of different types of target functions.

Key words: particle swarm optimization, Newton algorithm, steepest-descent algorithm, optimization efficiency