A Novel Approach for Accurate Wind Speed Time Series Forecasting Using ICEEMDAN Decomposition and Sample Entropy through Integration of Deep Learning Models

This study proposes a novel hybrid model for wind speed forecasting (WSF) based on a three-stage framework comprising decomposition, feature selection, and forecasting. The proposed approach employs Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (ICEEMDAN) to decompose wind speed time series into Intrinsic Mode Functions (IMFs). A distinctive contribution of this study is the use of sample entropy as a feature selection mechanism to identify the most relevant Intrinsic Mode Functions (IMFs). The selected IMFs are then integrated through a classification-based fusion technique, significantly enhancing forecasting accuracy and distinguishing this approach from conventional methods. Two distinct forecasting approaches are evaluated using multiple performance metrics, including RMSE, MAE, MAPE, and R². The first approach applies the fusion technique directly to the original wind speed time series, while the second incorporates ICEEMDAN to decompose the time series. Experimental validation using two real-world datasets from Algeria demonstrates the superiority of the proposed hybrid model over individual forecasting models, yielding significant improvements in prediction accuracy, robustness, and stability. These findings underscore the effectiveness of the three-stage framework, offering a reliable and efficient solution for short-term wind speed forecasting, with potential applications in renewable energy management and grid optimization.