An artificial neural-net based method for predicting distribution transformer's total harmonic distortions

This paper presents a new method for predicting distribution transformerpsilas total current and total voltage harmonic distortion with artificial neural network. The method is based on the backpropagation learning technique. This paper shows the proposed method is promising in total harmonic distortion prediction. For better system planning it is necessary to analyze and predict the behavior of harmonics. By predicted values system planners take an appropriate strategy to decrease significant harmonics in distribution systems.