Power quality events recognition using a SVM-based method

• Published in: Electric power systems research Vol. 78; no. 9; pp. 1546 - 1552
• Main Authors: Cerqueira, Augusto Santiago, Ferreira, Danton Diego, Ribeiro, Moisés Vidal, Duque, Carlos Augusto
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier B.V 01-09-2008; Elsevier
• Subjects: Applied sciences; Disturbances. Regulation. Protection; Electrical engineering. Electrical power engineering; Electrical power engineering; Event classification; Exact sciences and technology; Operation. Load control. Reliability; Pattern recognition; Power electronics, power supplies; Power networks and lines; Power quality; Signal processing; Support vector machine; Signal processing; Pattern recognition; Support vector machine; Power quality; Event classification; Performance evaluation; Power distribution faults; Power system stability; Power electronics; Vector method; Computational complexity; Power system faults; Classification; Feature extraction; System simulation; Energy quality; Service quality; Comparative study
• ISSN: 0378-7796; 1873-2046
• DOI: 10.1016/j.epsr.2008.01.016

In this paper, a novel SVM-based method for power quality event classification is proposed. A simple approach for feature extraction is introduced, based on the subtraction of the fundamental component from the acquired voltage signal. The resulting signal is presented to a support vector machine for event classification. Results from simulation are presented and compared with two other methods, the OTFR and the LCEC. The proposed method shown an improved performance followed by a reasonable computational cost.