Feature Selection of Power Quality Disturbance Signals with an Entropy-Importance-Based Random Forest

Entropy 2016, 18(2), 44; doi:10.3390/e18020044

Author

Nantian Huang ^1,†,* , Guobo Lu ^1,†

, Guowei Cai ^1,†

, Dianguo Xu ^2,†

, Jiafeng Xu ³

, Fuqing Li ¹

 and Liying Zhang ¹

¹

School of Electrical Engineering, Northeast Dianli University, Jilin 132012, China

²

Department of Electrical Engineering, Harbin Institute of Technology, Harbin 150001, China

³

Dongguan Power Supply Bureau, Guangdong Power Grid Corporation, Dongguan 523000, China

^†

These authors contributed equally to this work.

^*

Author to whom correspondence should be addressed. 

Academic Editor: Andreas Holzinger

Received: 4 November 2015 / Revised: 3 January 2016 / Accepted: 18 January 2016 / Published: 28 January 2016

(This article belongs to the Special Issue Machine Learning and Entropy: Discover Unknown Unknowns in Complex Data Sets)

View Full-Text   |     Download PDF [2212 KB, uploaded 28 January 2016]   |    

 Browse Figures

 

Abstract 

Power quality signal feature selection is an effective method to improve the accuracy and efficiency of power quality (PQ) disturbance classification. In this paper, an entropy-importance (EnI)-based random forest (RF) model for PQ feature selection and disturbance classification is proposed. Firstly, 35 kinds of signal features extracted from S-transform (ST) with random noise are used as the original input feature vector of RF classifier to recognize 15 kinds of PQ signals with six kinds of complex disturbance. During the RF training process, the classification ability of different features is quantified by EnI. Secondly, without considering the features with zero EnI, the optimal perturbation feature subset is obtained by applying the sequential forward search (SFS) method which considers the classification accuracy and feature dimension. Then, the reconstructed RF classifier is applied to identify disturbances. According to the simulation results, the classification accuracy is higher than that of other classifiers, and the feature selection effect of the new approach is better than SFS and sequential backward search (SBS) without EnI. With the same feature subset, the new method can maintain a classification accuracy above 99.7% under the condition of 30 dB or above, and the accuracy under 20 dB is 96.8%. View Full-Text

Keywords: power quality;  power quality disturbances;  random forest;  S-transform;  feature selection;  entropy-importance; sequential forward search

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. (CC BY 4.0).

For further details log on website :
http://www.mdpi.com/1099-4300/18/2/44