Advanced Harmonic Forecasting in Offshore Wind Farms with Permanent Magnet Synchronous Generators Using a Hybrid Deep and Machine Learning Architecture

Wind energy is crucial for reducing fossil fuel dependence and promoting sustainability. Offshore wind farms (OWFs) benefit from higher, stable wind speeds but pose challenges such as harmonic distortion and voltage fluctuations when integrated into power grids. This study develops an advanced model for accurate harmonic forecasting in OWFs using permanent magnet synchronous generators (PMSG). Real meteorological data from Zonguldak and Sinop in the Black Sea region of Turkey were used to simulate power output, voltage, and current waveforms. Harmonic components, including total harmonic distortion for voltage (THDV) and current (THDI), were extracted and predicted. Various machine learning (ML) and deep learning (DL) algorithms were applied, including Linear Regression, Decision Tree, Random Forest, Gradient Boosting, XGBoost, KNeighbors, LSTM, GRU, and CNN. Additionally, hybrid ML-DL models were explored to enhance forecasting accuracy. A comparative analysis of these models demonstrated their effectiveness in improving harmonic prediction. Results indicate that hybrid models, particularly LSTM+GB and GRU+GB, improve harmonic forecasting accuracy by reducing RMSE by approximately 15% compared to traditional ML methods. This enhancement contributes to better power quality management and grid stability, making offshore wind farms more viable for large-scale renewable energy integration. The findings of this research provide a fundamental basis for future investigations into offshore wind harmonic forecasting.