EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Attention-Enhanced CNN-LSTM with Spatial Downscaling for Day-Ahead Photovoltaic Power Forecasting

Feiyu Peng, Xiafei Tang, Maner Xiao

Sensors · 15.01.2026 · 26 (2) · 593

DOI: 10.3390/s26020593 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 15.01.2026. Verfasst von Feiyu Peng und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Electrical and Information Engineering, Changsha University of Science and Technology, Changsha 410114, China. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate day-ahead photovoltaic (PV) power forecasting is essential for secure operation and scheduling in power systems with high PV penetration, yet its performance is often constrained by the coarse spatial resolution of operational numerical weather prediction (NWP) products at the plant scale. To address this issue, this paper proposes an attention-enhanced CNN–LSTM forecasting framework integrated with a spatial downscaling strategy. First, seasonal and diurnal characteristics of PV generation are analyzed based on theoretical irradiance and historical power measurements. A CNN–LSTM network with a channel-wise attention mechanism is then employed to capture temporal dependencies, while a composite loss function is adopted to improve robustness. We fuse multi-source meteorological variables from NWP outputs with an attention-based module. We also introduce a multi-site XGBoost downscaling model. This model refines plant-level meteorological inputs. We evaluate the framework on multi-site PV data from representative seasons. The results show lower RMSE and higher correlation than the benchmark models. The gains are larger in medium power ranges. These findings suggest that spatially refined NWP inputs improve day-ahead PV forecasting. They also show that attention-enhanced deep learning makes the forecasts more reliable. Quantitatively, the downscaled meteorological variables consistently achieve lower normalized MAE and normalized RMSE than the raw NWP fields, with irradiance-related errors reduced by about 40% to 55%. For day-ahead PV forecasting, using downscaled NWP inputs reduces RMSE from 0.0328 to 0.0184 and MAE from 0.0194 to 0.0112, while increasing the Pearson correlation to 0.995 and the CR to 98.1%.

Schlagwörter

Stichwörter der Autor:innen

CNN-LSTMattention mechanismdeep learningmulti-source data fusionnumerical weather predictionphotovoltaic power forecastingspatial downscaling

Autor:innen und Institutionen

  • School of Electrical and Information Engineering, Changsha University of Science and Technology, Changsha 410114, China.

Zitieren

APA

Peng, F., Tang, X., & Xiao, M. (2026). Attention-Enhanced CNN-LSTM with Spatial Downscaling for Day-Ahead Photovoltaic Power Forecasting. Sensors, 26(2), 593. https://doi.org/10.3390/s26020593

Vancouver

Peng F, Tang X, Xiao M. Attention-Enhanced CNN-LSTM with Spatial Downscaling for Day-Ahead Photovoltaic Power Forecasting. Sensors. 2026;26(2):593. doi:10.3390/s26020593

BibTeX
@article{Peng2026,
  author = {Peng, Feiyu and Tang, Xiafei and Xiao, Maner},
  title = {Attention-Enhanced CNN-LSTM with Spatial Downscaling for Day-Ahead Photovoltaic Power Forecasting},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {2},
  pages = {593},
  doi = {10.3390/s26020593}
}
Kostenlos starten →