计算机工程与应用 ›› 2011, Vol. 47 ›› Issue (6): 49-51.
• 研究、探讨 • 上一篇 下一篇
顾大为,凌 君
收稿日期:
修回日期:
出版日期:
发布日期:
GU Dawei,LING Jun
Received:
Revised:
Online:
Published:
摘要: 针对PSO在寻优过程容易出现“早熟”现象,提出了一种基于Sobol序列的自适应变异PSO算法(SAPSO)。该算法以积分控制粒子群算法(ICPSO)为基础,使用准随机Sobol序列初始化种群个体,并在算法过程中引入基于多样性反馈的Beta分布自适应变异来保持种群的多样性,避免陷入局部最优。仿真结果表明,SAPSO算法在求解复杂优化问题时优势明显,可以有效地避免算法陷入局部最优,在保证收敛速度的同时增强了算法的全局搜索能力。
关键词: 粒子群优化算法, Sobol序列, Beta分布, 自适应变异, 多样性反馈
Abstract: To solve the premature problem of PSO,an improved PSO algorithm with adaptive mutation based on Sobol sequence(SAPSO) is proposed.Based on ICPSO,quasi-random Sobol sequence is introduced to the initialization of the swarm and the adaptive mutation with Beta distribution based on diversity feedback is used to keep the diversity of the population and to avoid the local optimum.The results show the effectiveness of SAPSO solving complicated optimization problems and avoiding the local optimum.The global searching ability is enhanced as well as the convergent speed is guaranteed.
Key words: Particle Swarm Optimization(PSO), Sobol sequence, Beta distribution, adaptive mutation, diversity feedback
顾大为,凌 君. 一种改进的新颖的粒子群优化算法[J]. 计算机工程与应用, 2011, 47(6): 49-51.
GU Dawei,LING Jun. Improved novel Particle Swarm Optimization algorithm[J]. Computer Engineering and Applications, 2011, 47(6): 49-51.
0 / 推荐
导出引用管理器 EndNote|Ris|BibTeX
链接本文: http://cea.ceaj.org/CN/
http://cea.ceaj.org/CN/Y2011/V47/I6/49