Training of the Naïve Bayes Classifier for the Detection of the Power Quality Events (Voltage Dip, Voltage Swell and Voltage Interruption)

Abstract

The effect of the Power Quality events can be devastating if not properly managed. To manage such PQ events effective detection and classification techniques must be developed. There are various mathematical models that can be used in the detection and classification of the events which could vary from Dip, Swell, Interruption, and Harmonic distortion. The paper is based on the classification of Voltage Dip, Voltage Swell and Voltage Interruption using the STFT as the method of the detection of the triggering point and using such synthetic signal to train the Naïve Bayes classifier to develop a classifier that is capable of classifying waveform signals that has such disturbances in them.

Power Quality Problems, Signature Method for Voltage Dips and Swells Detection, Classification and Characterization

“…Power Quality problems are defined as any power problems manifested in voltage, current, or frequency deviation that results in failures or malfunctions of customers equipments [1]. Voltage dips and swells are the two recurrent disturbances affecting voltage magnitude.…”

“…The features are used as the training data of the SVM to realize the identification of the voltage dip type. In Adegbite and Okelola [1], a naive Bayes classifier is proposed for the classification of voltage dips and swells.…”