EUVIMEDOpdag EUVIMED
Video/Audio

Cross-Site Physics-Informed Transfer Learning for One-Hour-Ahead Photovoltaic Power Forecasting

Zhongjun Yang, Yuchen Wang, Huaici Zhao, Feng Guo, He Li

Journal of Visualized Experiments · 2026

DOI: 10.3791/72532 ↗

At a glance

Video/Audio in Journal of Visualized Experiments, 2026. Written by Zhongjun Yang and 4 co-authors. Institution: College of Information Engineering, Shenyang University of Chemical Technology. Major MEDLINE topics: Solar Energy, Power Plants.

AbstractSubjectsBibliografiske oplysningerCiteRelated studies

Abstract (original language)

Accurate short-term photovoltaic power forecasting is essential for grid scheduling, reserve allocation, and the reliable integration of renewable energy into power systems. However, many data-driven forecasting models are trained and evaluated at a single photovoltaic plant, which limits their transferability to plants operating under different climatic, geographic, and engineering conditions. This study evaluated a cross-site physics-informed transfer-learning framework for one-hour-ahead photovoltaic power forecasting across six heterogeneous solar plants. The framework integrated a hybrid temporal model with plant-level static descriptors and a physics-based power prior derived from irradiance, module temperature, installed capacity, and grid export limits. The primary experiment used six leave-one-site-out target folds: for each held-out target plant, the other five plants were pooled as the source domain for pretraining. A separate, ordered single-source-to-single-target analysis (30 routes) was used solely to examine pairwise source-target distances and route-dependent transfer behavior. Source-domain and target-domain validation data were kept separate during checkpoint selection. Compared with direct transfer and conventional fine-tuning in the primary held-out-target analysis, the full physics-informed transfer model reduced forecasting error across the evaluated target sites. The study provides a structured framework for cross-site photovoltaic forecasting under heterogeneous environmental and operational conditions. Because inferential comparisons were based on six held-out target sites, they were interpreted as site-level evidence rather than evidence of broad population-level statistical generalizability.

Subjects

MeSH terms (MEDLINE)

Solar EnergyPower PlantsForecasting

Authors and institutions

  • College of Information Engineering, Shenyang University of Chemical Technology.
  • College of Information Engineering, Shenyang University of Chemical Technology; 337005498@qq.com.

Cite

APA

Yang, Z., Wang, Y., Zhao, H., Guo, F., & Li, H. (2026). Cross-Site Physics-Informed Transfer Learning for One-Hour-Ahead Photovoltaic Power Forecasting. Journal of Visualized Experiments. https://doi.org/10.3791/72532

Vancouver

Yang Z, Wang Y, Zhao H, Guo F, Li H. Cross-Site Physics-Informed Transfer Learning for One-Hour-Ahead Photovoltaic Power Forecasting. Journal of Visualized Experiments. 2026. doi:10.3791/72532

BibTeX
@article{Yang2026,
  author = {Yang, Zhongjun and Wang, Yuchen and Zhao, Huaici and Guo, Feng and Li, He},
  title = {Cross-Site Physics-Informed Transfer Learning for One-Hour-Ahead Photovoltaic Power Forecasting},
  journal = {Journal of Visualized Experiments},
  year = {2026},
  doi = {10.3791/72532}
}
Start for free →