基于减法聚类的FCM算法在电力负荷分类中的应用
An Improved FCM Algorithm Based on Subtractive Clustering for Power Load Classification
董瑞 1黄民翔1
作者信息
- 1. 浙江大学电气工程学院,杭州 310027
- 折叠
摘要
针对目前在电力负荷分类中应用较多的模糊C均值聚类算法(FCM)的不足之处,提出了一种基于减法聚类改进的算法(SUB-FCM).该算法运用减法聚类来初始化聚类中心矩阵,解决了FCM算法随机初始化的问题,且提高了算法的全局搜索能力,避免陷入局部最优解.由实验算例分析发现,该算法还能加快收敛速度,且收敛效果也较好,能有效应用于电力负荷分类.
Abstract
In view of the weaknesses of Fuzzy C-means Clustering algorithm (FCM) applied in many power load classification currently,this paper proposes an algorithm based on subtractive clustering and improved Fuzzy C-means Clustering (SUB-FCM).This algorithm,using subtractive clustering algorithm to initialize the cluster center matrix,solves the random initialization of FCM algorithm,improves the global search ability,and avoids falling into local optima.Experimental study analysis finds that this algorithm can also accelerate the convergence speed,and have better clustering results.This algorithm can be applied to power load classification effectively.
关键词
负荷分类/减法聚类/模糊C均值聚类算法Key words
power load classification/subtractive clustering/fuzzy C-means algorithm(FCM)引用本文复制引用
出版年
2014
NETL
NSTL
维普
万方数据