• • The proposed model achieves at least 1.46% RMSE improvement, 2.44% MAE improvement, and 14.67% MAPE improvement over all comparison models across three wind farms, directly reducing grid dispatch pressure and imbalance penalties in electricity markets.
• • The fluctuation continuation scenario identification framework decouples wind power into nonlinear and linear components, enabling quantitative analysis of continuation scales that traditional Hurst exponent methods cannot provide, thus improving scenario classification reliability for downstream forecasting.
• • The sparse neural network (SNN) combining sparse autoencoder (SAE) and self-attention mechanism (SAM) effectively handles high-dimensional sparse features, overcoming the curse of dimensionality that plagues random forest and support vector machine approaches in scenario identification.
• • The LSTM-Transformer hybrid model tailored for each fluctuation continuation scenario demonstrates robust performance across three real wind farms, validating its industrial applicability for station-level ultra-short-term forecasting where existing methods fail to capture multi-scale turbulent coupling.