Paper Info
Title
Integrating a Feature Selection Algorithm for Classification of Voltage Sags Originated in Transmission and Distribution Networks
Abstract
As a global problem in the power quality area, voltage sags are matter of high interest for both utilities and customers. With a view to resolving the problem of sag source location in the power network, this paper introduces a new method based on dimension reduction capability of Multiway Principal Component Analysis (MPCA). MPCA models are developed using three dimensional databases of voltage and current Root Mean Square (RMS) values. Computed scores are then used for training commonly used classifiers for putting sags in two classes. A feature selection algorithm is successfully applied for determining the optimal subsets of scores for training classifiers and also the number of principal components in the MPCA models. The proposed method is tested with success using some real voltage sags recorded in some substations. Also, through some experiments we demonstrate that satisfactorily high classification rates must be attributed to the applied feature selection algorithm.
Year
Venue
Keywords
2007
CCIA
high interest,real voltage,feature selection algorithm,power network,mpca model,new method,applied feature selection algorithm,global problem,distribution networks,high classification rate,voltage sag,feature selection
Field
DocType
Volume
Data mining,Dimensionality reduction,Feature selection,Computer science,Distribution networks,Power network,Artificial intelligence,Voltage sag,Pattern recognition,Voltage,Algorithm,Root mean square,Principal component analysis
Conference
163
ISSN
Citations 
PageRank 
0922-6389
1
0.46
References 
Authors
2
5
Name
Order
Citations
PageRank
Abbas Khosravi150160.11
Toni Martinez210.46
Joaquim Melendez372.97
Joan Colomer4135.21
Jorge Sanchez510.46