arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2610.40418cs.LGcs.AI
收藏

IMPACT:用于光伏发电预测的逆变器信息多模态学习

IMPACT: Inverter-Informed Multimodal Learning for Photovoltaic Generation Forecasting

National Laboratory of the Rockies(落基山国家实验室);Latimer Controls(莱蒂默控制公司)

Anushka Katiyar, Cong Feng, Jing Wang, Tristan Liu, Simon Julien, Zachary Jacobs

AI总结:

本研究提出IMPACT框架,以四分支多模态深度学习结合物理信息,实现10-110分钟光伏概率预测,性能优于14个基准,在复杂天气下仍具良好效果。

摘要:

本研究开发了一种物理信息多模态深度学习框架,用于提前10至110分钟的概率性光伏发电预测。该预测模型基于四分支架构构建,通过带学习邻接的图注意力编码器分别编码电站级时间历史与逆变器级空间云动态、已知未来太阳几何及当前气象状态,经门控交叉注意力融合。几何分支添加两个前瞻性物理信号:空间云异质性与逆变器降载活动,各按经验权重分配至其最具预测性的时间范围。解码器将预测锚定至智能持续基线,学习时间范围相关的修正,所得分位数预测通过核加权自适应共形校准步骤在线校准。所提模型优于全部14个基准模型,预测技能得分(FSS)达0.2950,较次优模型高0.099。分支组合消融实验显示各分支均有正向贡献,且模型在挑战性阴天与多变天空条件下仍保持显著技能(FSS分别为0.198与0.255)。

英文摘要:

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).

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑