Context-Aware Asymmetric Conformal Calibration of Renewable-Power Prediction Intervals for Day-Ahead Operational Risk Assessment
Abstract
High renewable penetration makes day-ahead operation sensitive to the directional effects of wind and photovoltaic forecast errors. Conventional prediction intervals mainly evaluate coverage and sharpness, but lower- and upper-boundary violations correspond to different operational risks: shortage-side supply-adequacy pressure and accommodation-side curtailment pressure. This paper proposes context-aware asymmetric conformal quantile regression (CA-ACQR) to construct directional renewable-power risk intervals. The method builds separate conformal scores for the two interval sides, estimates context-dependent boundary corrections, and reallocates the tail-risk budget under supply-priority, balanced, and accommodation-priority profiles. Case studies use regional wind and photovoltaic power data, with contextual groups defined by renewable type, lead-time block, forecast difficulty, weather-risk regime, and output level. CA-ACQR increases the prediction interval coverage probability (PICP) from 91.11% to 94.07% and reduces the accommodation-side violation rate from 4.37% to 1.44%. The results demonstrate selectable directional risk postures and quantify trade-offs among interval width, directional violations, normalized stress cost, and the 95% conditional value-at-risk stress cost.