摘要
研究粒子群算法惯性权重与种群规模大小、空间维度以及惯性权重递减率的关系,对多个具有代表性的函数进行实验研究。结果表明,适当改变惯性权重可以快速收敛、提高搜索效率以及避免陷入局部最优。
The relationship between Inertial weight parameters with population size, space dimension and decreasing rate of the inertia weight are studied for particle swarm algorithm. Experiments are made based on some typical functions. The results show that inertia weight variation can let the algorithm quickly converged, searching efficiently and local optimization avoided.
作者
王泽儒
李芬田
王红梅
WANG Zeru LI Fentian WANG Hongmei(School of Computer Science ＆ Engineering, Changchun University of Technology, Changchun 130012, China)
出处
《长春工业大学学报》
CAS
2017年第4期354-360,共7页
Journal of Changchun University of Technology
基金
吉林省科技厅发展计划基金资助项目(20160415013JH)
关键词
粒子群
种群
空间维度
惯性权重
递减率
particle swarm
population size
space dimensions
inertia weight
decreasing rate.
