Computer Engineering and Applications ›› 2021, Vol. 57 ›› Issue (1): 69-76.DOI: 10.3778/j.issn.1002-8331.2003-0152

Previous Articles     Next Articles

Particle Swarm Optimization Algorithm Integrated with Multiple-Strategies

LIAO Weilin, CHENG Shan, SHANG Dongdong, WEI Zhaobin   

  1. Hubei Collaborative Center for Microgrid of New Energy, Three Gorges University, Yichang, Hubei 443002, China
  • Online:2021-01-01 Published:2020-12-31

多策略融合的粒子群优化算法

廖玮霖,程杉,尚冬冬,魏昭彬   

  1. 三峡大学 微电网湖北省协同创新中心,湖北 宜昌 443002

Abstract:

Inspired by astrology and botany, Particle Swarm Optimization algorithm integrated with Multiple-Strategies(MSPSO) is proposed to improve the shortcoming of Particle Swarm Optimization(PSO) algorithm which is prone to local optimization. With the introduction of three-black-hole-system capture strategy and multiple-dimensional random interference strategy, the algorithm has enhanced global exploration ability with local exploitation capacity. And the algorithm transforms from global exploration to local exploitation through coordination coefficient, convergence speed is improved. At the same time, premature disturbance strategy is adopted to reduce the possibility of the algorithm falling into local optimization. Nine benchmark functions are used to compare the performance of the algorithm with other five algorithms. The simulation results show that MSPSO algorithm has the advantages of better optimization ability under the same iteration and faster convergence speed under the given accuracy.

Key words: Particle Swarm Optimization(PSO) algorithm, three-black-hole-system capture, multiple-dimensional random interference, coordination coefficient, premature disturbance

摘要:

受天体学和植物学启发,提出一种多策略融合的粒子群优化算法(MSPSO),以改善粒子群优化算法(PSO)易陷入局部最优的不足。三黑洞系统捕获策略和多维随机干扰策略的引入,使算法增强全局开拓能力的同时兼顾局部搜索能力,并通过协调因子完成从全局寻优向局部搜索的转变,进而提高收敛速度。同时,早熟扰动策略的采用,使算法陷入局部最优的概率降低。采用9个测试函数,将该算法与其他5种算法进行性能对比。仿真结果表明,MSPSO算法具有在相同迭代下更好的寻优能力、在给定精度下更快的收敛速度等优势。

关键词: 粒子群优化算法, 三黑洞系统捕获, 多维随机干扰, 协调因子, 早熟扰动