TimesFM-Based Photovoltaic Power Forecasting with Few-Shot Residual Adaptation Under Data Scarcity
Energies · 02.11.2026 · 19 (21) · 5210
DOI: 10.3390/en19215210 ↗Kurz gefasst
Fachartikel in der Zeitschrift Energies, online erschienen am 02.11.2026. Verfasst von Ping Zhou und 6 weiteren Autor:innen. Die Arbeit nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Sichuan Rangtang Huadian New Energy Co., Ltd..
Abstract (Originalsprache)
Accurate photovoltaic (PV) power forecasting is becoming increasingly important for the secure and economical operation of renewable-rich power systems. However, conventional data-driven forecasting methods generally rely on sufficient site-specific historical observations, limiting their applicability to newly commissioned PV stations with severe data scarcity; meanwhile, forecasting performance is still predominantly evaluated using statistical error metrics, which cannot fully reflect its practical value in power system operation. To address these issues, this study develops a PV forecasting framework based on the pretrained time-series foundation model TimesFM, which exploits transferable temporal representations to enable zero-shot forecasting with limited target-site data. A lightweight residual quantile few-shot adaptation scheme is further introduced to learn station-specific forecasting deviations from limited historical observations while keeping the pretrained forecasting backbone fixed, thereby improving target-site adaptation and forecasting capability. In addition, a multi-dimensional power-system-operation-oriented evaluation framework is established to assess forecasting performance from economic, flexibility, regulation, and network-operation perspectives, together with different PV integration locations and installed capacities. Experimental results demonstrate that for the investigated CYT Station 1 case, the proposed method improves deterministic and probabilistic forecasting performance relative to zero-shot TimesFM and achieves substantial adaptation gains using limited target-site observations. The improved forecasts also reduce forecasting-induced operating costs and reserve requirements and yield system responses closer to those obtained with actual PV generation, confirming that forecasting improvements can be translated into measurable operational benefits.
Förderung
- Sichuan Rangtang Huadian New Energy Co., Ltd.
Zitieren
APA
Zhou, P., Cai, F., Jiang, W., Deng, X., Wu, Y., Wu, W., & Ruan, J. (2026). TimesFM-Based Photovoltaic Power Forecasting with Few-Shot Residual Adaptation Under Data Scarcity. Energies, 19(21), 5210. https://doi.org/10.3390/en19215210
Vancouver
Zhou P, Cai F, Jiang W, Deng X, Wu Y, Wu W, et al. TimesFM-Based Photovoltaic Power Forecasting with Few-Shot Residual Adaptation Under Data Scarcity. Energies. 2026;19(21):5210. doi:10.3390/en19215210
BibTeX
@article{Zhou2026,
author = {Zhou, Ping and Cai, Fujie and Jiang, Weize and Deng, Xin and Wu, Yahu and Wu, Weiyao and Ruan, Jiaqi},
title = {TimesFM-Based Photovoltaic Power Forecasting with Few-Shot Residual Adaptation Under Data Scarcity},
journal = {Energies},
year = {2026},
volume = {19},
number = {21},
pages = {5210},
doi = {10.3390/en19215210}
}
EUVIMED