EUVIMEDEUVIMED entdecken
Crossref

Short-term forecasting of photovoltaic DC power output using six machine and deep learning algorithms with SHAP-based interpretability analysis

Ahmed Saadoon Algburi, Adem Yılmaz, Hoger K. Omar

at - Automatisierungstechnik · 16.12.2026 · 74 (11) · 936-951

DOI: 10.1515/auto-2026-0079 ↗

Kurz gefasst

Fachartikel in der Zeitschrift at - Automatisierungstechnik, online erschienen am 18.11.2026. Verfasst von Ahmed Saadoon Algburi und 2 weiteren Autor:innen. Die Arbeit nennt 47 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate photovoltaic power forecasting is essential for integrating solar energy into electrical grids, yet most high-accuracy models remain “black boxes” that do not reveal the mechanism of their decisions. This study addresses the short-term forecasting of photovoltaic DC power output at the OEDI station, at a five-minute resolution, through a systematic comparison of six algorithms belonging to three families: linear models (Ridge and SVR), tree-based ensembles (XGBoost and Random Forest), and neural networks (MLP and LSTM). Alongside accuracy evaluation, the SHAP method was applied to interpret each model’s behaviour and reveal the contribution of meteorological and temporal features to its predictions. The results showed that five of the six models achieved normalized errors within the range conventionally regarded as excellent (nRMSE < 10 %), with the LSTM marginally above this threshold at 10.47 %, and with a slight superiority for the MLP. Notably, this relatively simple model surpassed the more time-series-specialized LSTM network, indicating that architectural complexity does not automatically translate into higher accuracy at this short horizon. The SHAP analysis revealed a structural divergence among the model families in their handling of physical relationships: The attributions of the tree-based and neural models exhibited the non-linear pattern expected from thermal efficiency decline, while the linear models reflected their structure in straight relationships. The consistency of the feature ordering across families suggests that the attributions are driven predominantly by the structure of the data rather than by the inductive bias of any individual algorithm. This study contributes to combining predictive accuracy with interpretive transparency, strengthening confidence in deploying machine learning models in energy systems.

Zitieren

APA

Algburi, A. S., Yılmaz, A., & Omar, H. K. (2026). Short-term forecasting of photovoltaic DC power output using six machine and deep learning algorithms with SHAP-based interpretability analysis. at - Automatisierungstechnik, 74(11), 936-951. https://doi.org/10.1515/auto-2026-0079

Vancouver

Algburi AS, Yılmaz A, Omar HK. Short-term forecasting of photovoltaic DC power output using six machine and deep learning algorithms with SHAP-based interpretability analysis. at - Automatisierungstechnik. 2026;74(11):936-951. doi:10.1515/auto-2026-0079

BibTeX
@article{Algburi2026,
  author = {Algburi, Ahmed Saadoon and Yılmaz, Adem and Omar, Hoger K.},
  title = {Short-term forecasting of photovoltaic DC power output using six machine and deep learning algorithms with SHAP-based interpretability analysis},
  journal = {at - Automatisierungstechnik},
  year = {2026},
  volume = {74},
  number = {11},
  pages = {936--951},
  doi = {10.1515/auto-2026-0079}
}
Kostenlos starten →