A transformer-LSTM network enhanced by EEMD for ultra-short-term wind power forecasting

• The AI-driven model integrates signal decomposition with deep learning techniques. • An attention-based Transformer–LSTM network enhances renewable energy forecasting. • Multi-scale feature extraction significantly improves the accuracy of wind power prediction. • Intelligent optimization strategies ensure model robustness under variable grid conditions. • The proposed framework advances AI applications in smart and sustainable energy systems. This study aims to improve the dispatch safety and economic efficiency of grid-connected wind power systems by addressing the limitations of traditional ultra-short-term forecasting methods, particularly their inadequate extraction of multi-scale features and limited…

• NN
  National Natural Science Foundation of China
• DO
  Department of Science and Technology of Inner Mongolia