Paper Title
Prediction of Total Harmonic Distortion in Electric Railway Power Supply Systems By Using LSTM

Abstract
In this paper, a Long Short-Term Memory (LSTM) network and its architecture to forecastTotal Harmonic Distortion of current (THDI) patterns within a context of harmonic analysis in electric railway power systems were introduced. This LSTM-based approach enabledthe prediction up to 19 minutes into the future. When compared with the 1-hour dataset (7199 samples), the model exhibitedgood performances by achieving a root-mean-square error (RMSE) and mean absolute error (MAE)for benchmarking. Keywords - LSTM, THDI, RMSE, MAE.