From Symmetric Persistence to Asymmetric Gating: A Regime-Aware Network for Ultra-Short-Term Wind Power Forecasting

Ultra-short-term wind-power forecasting must handle both stable conditions and rapid ramp events, yet many architectures do not explicitly distinguish positive from negative ramp evidence. We evaluate whether that distinction improves multi-step predictions under a chronological wind-power forecasting protocol. RAA-Net combines a persistence-anchored baseline with a causal GRU and separate mappings for upward and downward ramps. A calibration-set blending rule substitutes persistence for selected low-volatility cases. We evaluated two turbines from the public SDWPF dataset at 40–160 min horizons, using chronological train, validation, calibration, and test partitions and three-seed neural-model comparisons against eight baselines. RAA-Net records the lowest reported RMSE at every horizon for both turbines. On the primary turbine, it also records the best reported MAE, R2, nRMSE, and nMAE at each horizon. Component ablations quantify the effects of the directional module, anchor, and blending rule. These findings support direction-specific ramp representations for the evaluated turbines and protocol.