arXiv cs.AI· Anushka Katiyar, Cong Feng, Jing Wang, Tristan Liu, Simon Julien, Zachary Jacobs·· 5 小时前AI 评分27
IMPACT：逆变器信息驱动的多模态学习用于光伏发电预测
IMPACT: Inverter-Informed Multimodal Learning for Photovoltaic Generation Forecasting
AI 导读
IMPACT 是一个面向 10 至 110 分钟前瞻概率光伏功率预测的物理信息多模态深度学习框架。模型采用四分支架构，分别编码电站级时间历史、经图注意力编码器处理的逆变器级空间云动态、太阳几何与气象状态，并通过门控交叉注意力融合，预测锚定于 smart persistence 基线并经自适应共形校准。
正文 · 原文
Abstract:This work develops a physics-informed multimodal deep learning framework for 10- to 110-minute-ahead probabilistic photovoltaic power forecasting. The forecasting model is built on a four-branch architecture that separately encodes plant-level temporal history and inverter-level spatial cloud dynamics through a graph attention encoder with a learned adjacency, known-future solar geometry, and the current meteorological state, fused through gated cross-attention. The geometry branch adds two forward-looking physical signals, spatial cloud heterogeneity and inverter ramp-down activity, each empirically weighted toward the horizon where it is most predictive. The decoder anchors its prediction to a smart persistence baseline, learning a horizon-conditioned correction, and the resulting quantile forecasts are calibrated online through a kernel-weighted adaptive conformal calibration step. The proposed model outperforms all 14 baselines, achieving a forecast skill score (FSS) of 0.2950, 0.099 above the next-best model. A branch-composition ablation shows that every branch contributes positively and the model retains substantial skill in challenging overcast and variable sky conditions (FSS 0.198 and 0.255).
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.40418 [cs.LG] |
| (or arXiv:2610.40418v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.40418 arXiv-issued DOI via DataCite |
Submission history
From: Cong Feng [view email]
[v1]
Thu, 29 Oct 2026 16:44:20 UTC (4,897 KB)
来源：arXiv cs.AI · arxiv.org