EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Multi-Level Distributed Photovoltaic Power Forecasting Method Based on Knowledge Transfer

Fei Luo, Lei Gao, Qiangsheng Bu, Ye Guo, Sicong Zhang

Energies · 29.10.2026 · 19 (21) · 5149

DOI: 10.3390/en19215149 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Energies, online erschienen am 29.10.2026. Verfasst von Fei Luo und 4 weiteren Autor:innen. Die Arbeit nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: State Grid Jiangsu Electric Power Company Ltd. Science and Technology Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Conventional independently trained models for distributed photovoltaic (DPV) power forecasting at the feeder, main-transformer, and regional-grid levels do not explicitly reuse spatiotemporal representations across the distribution-network hierarchy. This paper proposes a knowledge-transfer-based multilevel method for short-term DPV power forecasting. First, a T-GCN encoding block integrating a temporal convolutional network and an adaptive graph convolutional network is developed at the distribution-transformer-area–feeder level to capture multiscale temporal dependencies and implicit spatial correlations. Second, the pretrained feeder-level encoder is transferred to the main-transformer task and frozen, while a Transformer-based cross-feeder aggregation network and a decoder are trained for the target task. At the grid level, a meteorology-driven weighting network fuses the representations of individual main transformers. In a regional case study using real-world operating data, the proposed method achieves equal-weighted mean relative reductions of approximately 20.0% in NRMSE and 17.5% in NMAE over an independently trained T-GCN baseline across the three forecasting levels. Identical-architecture comparisons at the main-transformer level further show that fine-tuning a pretrained encoder improves forecasting accuracy relative to training from random initialization, while freezing the pretrained encoder yields additional error reductions. These findings support the proposed pretraining-and-freezing strategy under the evaluated conditions.

Förderung

  • State Grid Jiangsu Electric Power Company Ltd. Science and Technology Project

Zitieren

APA

Luo, F., Gao, L., Bu, Q., Guo, Y., & Zhang, S. (2026). A Multi-Level Distributed Photovoltaic Power Forecasting Method Based on Knowledge Transfer. Energies, 19(21), 5149. https://doi.org/10.3390/en19215149

Vancouver

Luo F, Gao L, Bu Q, Guo Y, Zhang S. A Multi-Level Distributed Photovoltaic Power Forecasting Method Based on Knowledge Transfer. Energies. 2026;19(21):5149. doi:10.3390/en19215149

BibTeX
@article{Luo2026,
  author = {Luo, Fei and Gao, Lei and Bu, Qiangsheng and Guo, Ye and Zhang, Sicong},
  title = {A Multi-Level Distributed Photovoltaic Power Forecasting Method Based on Knowledge Transfer},
  journal = {Energies},
  year = {2026},
  volume = {19},
  number = {21},
  pages = {5149},
  doi = {10.3390/en19215149}
}
Kostenlos starten →