Support vector regression and rule based classifier comparison for power quality diagnosis

This paper presents a comparative study for performing automated power quality diagnosis using rule base classifier (RBC) and support vector regression (SVR) to identify the causes of short duration voltage disturbances such as voltage sag and swell. In the proposed power quality diagnosis method, a time frequency analysis technique called as the S-transform was used to analyse and extract features of voltage disturbances recorded from the power quality monitoring system. The RBC and SVR which are intelligent techniques were then used to identify whether the voltage disturbances were caused by permanent, non-permanent transient or incipient faults. Test results proved that the RBC performed better than the SVR in diagnosing the causes of short duration voltage disturbances.

[1]  E. L. Harder,et al.  The Institute of Electrical and Electronics Engineers, Inc. , 2019, 2019 IEEE International Conference on Software Architecture Companion (ICSA-C).

[2]  C. Robert Pinnegar,et al.  The S-transform with windows of arbitrary and varying shape , 2003 .

[3]  D. G. Ece,et al.  Covariance analysis of voltage waveform signature for power-quality event classification , 2006, IEEE Transactions on Power Delivery.

[4]  Il-Yop Chung,et al.  Development of a network-based power quality diagnosis system , 2007 .

[5]  Edward J. Powers,et al.  Characterization of distribution power quality events with Fourier and wavelet transforms , 2000 .

[6]  Irene Y. H. Gu,et al.  Classification of Underlying Causes of Power Quality Disturbances: Deterministic versus Statistical Methods , 2007, EURASIP J. Adv. Signal Process..

[7]  Zuhaina Zakaria,et al.  Investigation on the effectiveness of classifying the voltage sag using support vector machine , 2010, 2010 4th International Power Engineering and Optimization Conference (PEOCO).

[8]  Azah Mohamed,et al.  Power quality diagnosis using time frequency analysis and rule based techniques , 2011, Expert Syst. Appl..

[9]  W. Weeks,et al.  Instrumentation for the Detection and Locatiion of Incipient Faults on Power Cables , 1982, IEEE Transactions on Power Apparatus and Systems.

[10]  L. Fickert,et al.  Automated power system event detector and classifier , 2004, 2004 11th International Conference on Harmonics and Quality of Power (IEEE Cat. No.04EX951).

[11]  M.H.J. Bollen,et al.  Automatic classification of power system events using RMS voltage measurements , 2002, IEEE Power Engineering Society Summer Meeting,.