EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Regional Short-Term PV Power Forecasting Based on Graph Convolution and Transformer Networks

Qinggui Chen, Ziqi Liu, Zhao Zhen

Electronics · 24.04.2026 · 15 (9) · 1817

DOI: 10.3390/electronics15091817 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 24.04.2026. Verfasst von Qinggui Chen und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: S&T Program of Hebei.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate short-term photovoltaic (PV) power forecasting is essential for power system scheduling and market operations. Existing studies have shown the value of numerical weather prediction (NWP), graph-based spatial modeling, and temporal sequence learning, but the boundary of their contributions remains fragmented across many practical forecasting frameworks. In particular, adjacent multi-point NWP information is often not explicitly organized according to its spatial relationships, while historical similar-day power is rarely integrated with graph-structured meteorological features in a unified model. To address this gap, this study develops a short-term PV power forecasting framework that combines multi-point NWP graph construction with similar-day-guided Transformer fusion. First, predicted irradiance from the target site and neighboring NWP points is organized as a graph, and a Graph Convolutional Network (GCN) is used to extract local spatial meteorological features. Second, similar days are identified through a two-stage selection strategy based on Euclidean distance and Pearson correlation, and the corresponding historical power sequences are aggregated as temporal guidance. Finally, the graph-extracted NWP features, similar-day power, and predicted humidity are fused by a Transformer-based temporal modeling module to generate day-ahead PV power forecasts. Experimental results show that the proposed framework outperforms TCN-Transformer, Transformer, GCN, LSTM, and BP on the studied dataset, and maintains favorable performance on additional PV stations. These results indicate that the joint integration of graph-structured multi-point NWP information and historical similar-day power is effective for short-term PV power forecasting.

Förderung

  • S&T Program of Hebei

Zitieren

APA

Chen, Q., Liu, Z., & Zhen, Z. (2026). Regional Short-Term PV Power Forecasting Based on Graph Convolution and Transformer Networks. Electronics, 15(9), 1817. https://doi.org/10.3390/electronics15091817

Vancouver

Chen Q, Liu Z, Zhen Z. Regional Short-Term PV Power Forecasting Based on Graph Convolution and Transformer Networks. Electronics. 2026;15(9):1817. doi:10.3390/electronics15091817

BibTeX
@article{Chen2026,
  author = {Chen, Qinggui and Liu, Ziqi and Zhen, Zhao},
  title = {Regional Short-Term PV Power Forecasting Based on Graph Convolution and Transformer Networks},
  journal = {Electronics},
  year = {2026},
  volume = {15},
  number = {9},
  pages = {1817},
  doi = {10.3390/electronics15091817}
}
Kostenlos starten →