Machine Learning-Based Power Quality Prediction in a Microgrid for Community Energy Systems

To mitigate environmental impact, specifically the CO2 emissions associated with conventional thermal and nuclear facilities, renewable energy sources are increasingly being adopted as primary alternatives. However, integrating these renewable sources into the utility grid poses a significant challenge, primarily due to the stochastic and nonlinear nature of weather. Consequently, it is imperative that power systems operate under an intelligent control model to ensure energy output meets strict power quality standards. In this context, accurate forecasting is a cornerstone of smart power management, particularly in off-grid architectures, where predicting Power Quality Parameters (PQPs) is fundamental for system optimization and error correction. This study conducts a comprehensive comparative evaluation of nine different predictive architectures for estimating PQPs. The algorithms analyzed include LSTM, GRU, DNN, CNN1D-LSTM, BiLSTM, attention mechanisms, DT, SVM, and XGBoost. The central objective is to develop a reliable basis for the automated regulation and enhancement of electrical quality in isolated systems. The specific parameters investigated are power voltage (U), Voltage Total Harmonic Distortion (THDu), Current Total Harmonic Distortion (THDi), and short-term flicker severity (Pst). Data for this investigation were acquired from an experimental off-grid setup at VSB-Technical University of Ostrava (VSB-TUO), Czech Republic. To assess model performance, we utilized root mean square error (RMSE) as the primary accuracy metric, while simultaneously evaluating computational efficiency in terms of processing speed and memory consumption during testing.