DOI: 10.1049/cp.2009.1123 ISBN: 978 1 84919 126 5 Location: Prague, Czech Republic Conference date: 8-11 June 2009 Format: PDF This paper considers two important classification algorithms for to classify several power quality disturbances. Artificial Neural Network (ANN) and support vector machine (SVM). The last one is a novel algorithm that has shown good performance in general patterns classification. Nevertheless, Multilayer Perceptron Artificial Neural Network (MLPANN) is the most popular and most widely used models in various applications. Both are used for classify some disturbances under survey as: low frequency disturbances (such as flicker and harmonics) and high frequency disturbances (such as transient and sags). Biorthogonal Wavelet Function is used as a base function for extract features of PQ disturbances. In addition, RMS value is used to characterize the magnitude of disturbances. (4 pages) Inspec keywords: multilayer perceptrons; support vector machines; power engineering computing; wavelet transforms; power supply quality Subjects: Integral transforms; Neural computing techniques; Power supply quality and harmonics; Power engineering computing; Integral transforms; Knowledge engineering techniques