摘要
提出一种改进的粒子群优化(particle swarm optimization,PSO)算法,将随机(random)概念与调整(regula-tion)机制导入PSO算法中,既可避免族群搜寻过程中陷入局部最优解,又可提高算法在最优区域局部搜寻的能力。最后用2种复杂程度不同的函数为例,比较了本算法与广被采用的PSO-CF算法的最优化能力。结果显示,算法在搜寻成功率、平均收敛时间及平均收敛代数方面的性能皆优于PSO-CF算法。
An improved particle swarm optimization (PSO) algorithm based on random concept and regulation mechanism was proposed. This method can prevent the population from trapping into the local optimum and promote the ability of local search simultaneously. Then, the performance of the proposed algorithm was compared with that of PSO-CF algorithm. The comparative results show that the performance of the proposed algorithm is better than that of PSO-CF on search success rate, average convergence times and average convergence generations.
出处
《重庆邮电大学学报(自然科学版)》
北大核心
2010年第1期99-102,共4页
Journal of Chongqing University of Posts and Telecommunications(Natural Science Edition)
基金
重庆市自然科学基金项目(CSTC
2006BB2242)
关键词
群体智能
粒子群优化
随机模式
调整机制
swarm intelligence
particle swarm optimization (PSO)
random pattern
regulation mechanism