Enhanced offshore wind resource assessment using hybrid data fusion and numerical models

Abstract

Wind resource assessments are crucial for pre-construction planning of wind farms, especially offshore. This study proposes a novel hybrid model integrating Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) and Empirical Wavelet Transform (EWT) for enhanced wind speed forecasting. This secondary decomposition reduces forecasting complexity by processing high-frequency signals. A Bidirectional Long Short-Term Memory (BiLSTM) neural network optimized with the Grey Wolf Optimizer (GWO) is then employed for forecasting. The model’s accuracy is evaluated using simulated wind speeds along the coast of Denmark, combined with lidar measurements through data fusion. This approach demonstrates significant improvements in prediction accuracy, highlighting its potential for offshore wind resource assessment. • A novel algorithm is proposed to predict offshore wind speed using continuous simulation data. • A secondary signal decomposition algorithm is used to pre-process a time series and further reduce the complexity of the signal. • A Gaussian regression is constructed for the fusion of data with multiple fidelities where high-fidelity data is considered as a function of low fidelity data. • The data fusion method using gappy empirical measurement results in more accurate wind resource assessment with 40% improvement, significantly outperforming models that are trained only on a single source of data.