Detection and Identification of Electric Power Quality Problems using Artificial Intelligence Technique LSTM

Detection and identification of the power quality (PQ) problems is a very significant assignment in the electric power system. This book aims to apply a new deep learning technique to detect and identify single and complex PQ problems like interruption, sag, flicker, swell, and surge. The proposed technique, the Long Short-Term Memory (LSTM) network, is a new Artificial Intelligence technique, which is a distinctive pattern of Recurrent Neural Networks. This technique is used to detect and identify PQ problems depending on three main solutions; automatic feature extraction, computations of voltage/current magnitude and PQ problems duration. Simulated PQ problems generated by Matlab environment and many real field data sets are used to confirm the capability of the proposed technique. The real data are real voltage and current waveforms that are measured, recorded and analyzed in HV/MV substation by using data acquisition device. The results demonstrate that the proposed technique has the competence to detect and identify PQ problems accurately comparing with other artificial intelligent techniques.