{"ID":6267018,"CreatedAt":"2026-07-10T01:11:38.759438437Z","UpdatedAt":"2026-07-12T03:12:04.745660124Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.08079","arxiv_id":"2607.08079","title":"PARA-PV: Physics-Aware Retrieval-Augmented PV Prediction Based on Frozen Foundation Model and Distribution Shift Correction","abstract":"Accurate photovoltaic (PV) power forecasting is essential for reliable grid dispatch and renewable energy integration, yet it remains challenging because PV generation is jointly shaped by weather variability, day-night transitions, regime-dependent dynamics, and strict physical constraints. We propose PARA-PV, a Physics-Aware Retrieval-Augmented framework that embeds physical knowledge throughout the forecasting process. The framework first encodes multivariate PV observations into patch-level representations and, through a physics-aware retrieval-augmented learner, retrieves historical patches and analog trajectories that are consistent with the current window in temporal shape, power level, PV operating state, and intra-day period; this yields a physically grounded base forecast. To supplement local memory with broader temporal knowledge, the base forecast is then calibrated against a frozen Chronos time-series foundation-model prior through a lightweight residual adapter, so that general temporal regularities are adapted to PV-specific dynamics without overriding the physically grounded prediction. Because residual conditional distribution shifts persist when weather and diurnal regimes change, a physics-aware distribution shift correction module subsequently adjusts the preliminary forecast using power, weather, timestamp, and day/night conditions, applying gated mean-shift and scale corrections selectively. Finally, a physics-constrained loss function partitions the samples into peak, ramping, night-time, and regular regimes and adaptively reweights their error contributions, preventing the dominant regular regime from suppressing learning of operationally critical states. Our code is available at https://github.com/weican1103/PARA-PV.","short_abstract":"Accurate photovoltaic (PV) power forecasting is essential for reliable grid dispatch and renewable energy integration, yet it remains challenging because PV generation is jointly shaped by weather variability, day-night transitions, regime-dependent dynamics, and strict physical constraints. We propose PARA-PV, a Physi...","url_abs":"https://arxiv.org/abs/2607.08079","url_pdf":"https://arxiv.org/pdf/2607.08079v1","authors":"[\"Hang Fan\",\"Weican Liu\",\"Ying Lu\",\"Dunnan Liu\",\"Long Cheng\",\"Wei Wei\"]","published":"2026-07-09T03:15:42Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[]","has_code":false,"code_links":[{"ID":614069,"CreatedAt":"2026-07-10T01:11:38.759438437Z","UpdatedAt":"2026-07-10T01:11:38.759438437Z","DeletedAt":null,"paper_id":6267018,"paper_url":"https://arxiv.org/abs/2607.08079","paper_title":"PARA-PV: Physics-Aware Retrieval-Augmented PV Prediction Based on Frozen Foundation Model and Distribution Shift Correction","repo_url":"https://github.com/weican1103/PARA-PV","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}