Classification of Power Quality Events Using Deep Learning

Abstract

Power Quality (PQ) can be defined as a clean supply voltage that stays within the prescribed range in a smooth curve waveform. A power quality problem is defined as any problem that causes voltage or frequency deviations in a power supply, and it may result in failure or maloperation of a network. Therefore, continuous monitoring is also required in case of malfunction in these cases. In this paper, we have presented a deep learning-based power quality event classification method. We have used the proprietary electric relay wave-form data from The Turkish Electricity Transmission Corporation (TEIAS), as well as generated wave-form from MATLAB Simulink, to train our model, using Convolutional Neural Networks (CNNs). The results proved to be effective, and can open the path to further research in this direction.