Deep Learning Based a New Approach for Power Quality Disturbances Classification in Power Transmission System

Abstract Power quality is one of the most important research eras for energy sector. Suddenly dropped voltages or suddenly rising and harmonics in should be identified. All these distortions are called power disturbances (PQDs). Deep learning based convolutional artificial neural networks with an attention model approach has been carried out. The main idea to develop a new network (CNN) which classifies particular signal into its respective condition. on that best solution will taken from newly produced data pool obtained by rescaling available according total number pixels before average created then deep CNN processes continue. In approach, all multiplied elements epoch time sixty-six tensors. dataset used here contains signals belong 9 classes. This means each characterized 622 points 5600 parameters. provided domain. (PQ) directly depending disturbances’ absence scarcity. accuracy error values developed were both epochs iterations.