arXiv：cs.AI· Phil Aupke, Muhammad Hassan, Khalid Ali, Seema, Andreas Kassler, Andreas Theocharis·· 18 小时前
PowerMamba：物理信息状态空间模型用于日前光伏功率预测
Physics-Informed State Space Models for Day-Ahead Photovoltaic Power Forecasting
AI 导读
研究者提出物理信息状态空间框架，将可微光伏转换模型与选择性状态空间骨干 PowerMamba 结合，按物理残差分解预测日前光伏功率。在一年公用事业规模光伏数据上，该方法较纯物理基线 RMSE 降低 38.5%、MAE 降低 45.8%，并优于纯数据驱动模型。系统级物理约束带来最大性能增益，同时使预测更符合物理可行性。
正文
Abstract:Accurate day-ahead photovoltaic (PV) power forecasting requires both strong temporal modeling and adherence to physical PV system constraints. Purely data-driven models often ignore the underlying PV conversion process and may produce predictions that are outside the operational range of a PV system. In this paper, we propose a physics-informed state space framework that combines a differentiable PV conversion model with a selective state space backbone (PowerMamba). Our approach follows a physics-residual decomposition. The physics module provides a structured baseline based on solar geometry, irradiance, temperature effects, and inverter limits, while the state space model learns residual corrections from numerical weather prediction (NWP) inputs over a 24-hour horizon. Experiments on one year of utility-scale PV data show that the proposed method significantly improves forecasting accuracy, reducing RMSE by 38.5% and MAE by 45.8% compared to a physics-only baseline, and outperforming a purely data-driven model. Results further show that incorporating system-level physics provides the largest performance gains, while additional refinements offer only marginal improvements. Beyond accuracy, the model improves robustness by constraining predictions toward physical feasibility, reducing unrealistic predictions under corrupted measurements.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.14014 [cs.LG] |
| (or arXiv:2610.14014v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.14014 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Andreas Kassler [view email]
[v1]
Tue, 29 Sep 2026 09:09:02 UTC (970 KB)
来源：arXiv：cs.AI · arxiv.org