As a representative uncertain renewable energy source, photovoltaic (PV) power generation is highly sensitive to meteorological conditions, posing significant challenges for microgrid operation and scheduling. To address the limitations of traditional forecasting methods in simultaneously achieving high prediction accuracy and robust uncertainty quantification, this study proposes a multi-quantile forecasting model integrating a Bidirectional Temporal Convolutional Network (BiTCN), Efficient Channel Attention (ECA), and Quantile Regression (QR). The model unifies point and interval forecasting...
