Online power quality disturbance classification based on Hoeffding Tree

被引：0
|
作者：
机构：
[1] Key Laboratory of Control of Power Transmission and Conversion, Department of Electrical Engineering, Shanghai Jiao Tong University, Shanghai
来源：
Ding, Jianguang | 1600年 / Electric Power Automation Equipment Press卷 / 34期
关键词：
Adaptive sliding window; Data mining; Data stream; Disturbance; Hoeffding Tree; Noises; Power quality; Wavelet transforms;
D O I：
10.3969/j.issn.1006-6047.2014.09.014
中图分类号：
学科分类号：
摘要：
An online classification method based on Hoeffding Tree is proposed for the online classification of PQD (Power Quality Disturbance). The key technologies used in the online PQD classification based on power quality data stream are researched and a PQD detection method combining the wavelet transform and the DFT (Discrete Fourier Transform) is proposed, which adopts an adaptive sliding window to extract a complete PQD event according to its duration. The characteristic vector is composed of the wavelet energy and the fundamental RMS and the Hoeffding Tree algorithm is applied to build the incremental classification training model. Simulative results show that, the accuracy and efficiency of the proposed method meet the requirements of online PQD detection and classification.
引用
收藏
页码：84 / 89
页数：5
相关论文
共 18 条
  • [1] Zhang X., Xu Y., Xiao X., Power quality disturbance detection and identification based on dq conversion and wavelet transform, Electric Power Automation Equipment, 25, 7, pp. 1-5, (2005)
  • [2] Li T., Chen X., Zhao W., Et al., Double wavelets measurements and classification of short duration power quality disturbances, Automation of Electric Power Systems, 27, 22, pp. 26-30, (2003)
  • [3] Li T., Guo Y., Wang J., Et al., Power quality disturbance detection based on mathematical morphology and power algorithm of short data window, Electric Power Automation Equipment, 28, 7, pp. 37-40, (2008)
  • [4] Zhang Q., Liu H., Lan Q., Consunmer importance classification based on VOLL, Electric Power Automation Equipment, 28, 8, (2008)
  • [5] Ouyang S., Song Z., Chen D., Et al., Application of wavelet soft-threshold de-noising technique to power quality detection, Automation of Electric Power Systems, 26, 19, pp. 56-60, (2002)
  • [6] Kong Y., Che L., Yuan J., Et al., A power quality disturbance identification method based on wavelet decomposition and decision tree algotithm in data mining, Power System Technology, 31, 23, pp. 78-82, (2007)
  • [7] Tang L., Yang X., A de-noising method of power quality based on triangle module operator, Transactions of China Electrotechnical Society, 22, 9, pp. 154-158, (2007)
  • [8] Huang S., Qu Y., Survey on data stream classification technologies, Application Research of Computers, 26, 10, pp. 3604-3609, (2009)
  • [9] Babcock B., Babu S., Datar M., Et al., Models and issues in data stream system, pp. 1-30, (2002)
  • [10] Zhao J., Yang G., Mu L., Et al., Research on the application of the data stream technology in grid automation, Power System Technology, 35, 8, pp. 6-11, (2011)
12