• CSCD核心库收录期刊
  • 中文核心期刊
  • 中国科技核心期刊

ELECTRIC POWER CONSTRUCTION ›› 2015, Vol. 36 ›› Issue (4): 46-51.doi: 10.3969/j.issn.1000-7229.2015.04.008

Previous Articles     Next Articles

Application of Clustering Hierarchy Algorithm Based on Kernel Fuzzy C-Means in Power Load Classification

XU Yanhui, ZHANG Lanyu, SONG Ge   

  1. College of Electrical & Electronic Engineering, North China Electric Power University, Beijing 102206, China
  • Online:2015-04-01
  • Supported by:

    Project Supported by the Fundamental Research Funds for the Central Universities (2014MS05)

Abstract:

To solve the problems that traditional Fuzzy C-means algorithm (FCM) was unsuitable for the clustering of non-normal distribution data set and sensitive to the noise, and its convergence speed for high dimensional dataset treatment was slow, a clustering hierarchy process based on kernel Fuzzy C-means algorithm was proposed for power load classification, which was composed of two modules and a algorithm: improved quick sort module, kernel function module and FCM. Firstly, an improved quick sort module was used to divide the large dataset into several subspaces with significant characteristics, then it could complete the clustering of subspaces combined with kernel function module and FCM algorithm. Based on the investigation data of load in Guangdong, the classification result of clustering hierarchy algorithm based on kernel Fuzzy C-means was compared with that of FCM on MATLAB platform. The results show that: the proposed method can improve the efficiency and accuracy of classification, and has higher convergence rate; moreover, the accuracy controllability of its classification results is benefited to grid engineering planning.

Key words: load classification, improved quick sort, kernel function, Fuzzy C-means

CLC Number: