EUVIMEDEUVIMED entdecken
Crossref

Multilevel Stacking with Domain-Adversarial Neural Network and Enriched Metadata for Improved Renewable Energy Output Forecasting

Daniel Dankwah, Prince Clement Addo, Joshua Caleb Dagadu, Samuel Kofi Akpatsa, Oliver Kufour Boansi, William Asiedu, George Asante, Enoch Adjei Frimpong, Dong Miao, William Adjei Atuahene

Journal of Technology Education and Applied Sciences · 21.07.2026 · 1 (1) · 32-45

DOI: 10.64922/jteas.v1i1.86 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Technology Education and Applied Sciences, online erschienen am 21.07.2026. Verfasst von Daniel Dankwah und 9 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study proposes a multilevel stacking approach that extends Wolpert's (1992) stacked generalisation, aiming to minimise forecasting error, reduce systematic bias, and enforce temporal domain invariance. It incorporates walk-forward out-of-fold and step-based walk-forward validation, enriched metadata, and a domain adversarial neural network (DANN). The base learners XGB and LSTM function as residual and latent encoders for the Random Forest with DANN meta-learner. DANN is integrated in meta-learning to minimise task regression loss and maximize domain discrimination loss through a gradient reversal layer. This fusion improves domain transition stability, as the model’s high explanatory power with ^2 values exceed 0.98 across validation and test regimes. The MASE values below 0.07 on both regimes indicate strong predictive performance relative to a naïve benchmark, and NRMSE values around 0.025 confirm that the proposed stacking framework effectively captures temporal dependencies. Moreover, the model achieves a near-symmetric residual distribution, with a skewness of 0.37 on the validation set and -0.01 on the test set, suggesting that adversarial feature learning helps reduce asymmetric prediction errors and stabilise meta-learning. This proposed framework demonstrates empirically that stacking should not be evaluated solely on MAE/RMSE but on residual distribution behaviour under domain transition. Furthermore, SHAP analysis provides empirical evidence that enriched metadata significantly enhances the learning capacity, allowing the meta-learner to capture complex dependencies.

Zitieren

APA

Dankwah, D., Addo, P. C., Dagadu, J. C., Akpatsa, S. K., Boansi, O. K., Asiedu, W., Asante, G., Frimpong, E. A., Miao, D., & Atuahene, W. A. (2026). Multilevel Stacking with Domain-Adversarial Neural Network and Enriched Metadata for Improved Renewable Energy Output Forecasting. Journal of Technology Education and Applied Sciences, 1(1), 32-45. https://doi.org/10.64922/jteas.v1i1.86

Vancouver

Dankwah D, Addo PC, Dagadu JC, Akpatsa SK, Boansi OK, Asiedu W, et al. Multilevel Stacking with Domain-Adversarial Neural Network and Enriched Metadata for Improved Renewable Energy Output Forecasting. Journal of Technology Education and Applied Sciences. 2026;1(1):32-45. doi:10.64922/jteas.v1i1.86

BibTeX
@article{Dankwah2026,
  author = {Dankwah, Daniel and Addo, Prince Clement and Dagadu, Joshua Caleb and Akpatsa, Samuel Kofi and Boansi, Oliver Kufour and Asiedu, William and Asante, George and Frimpong, Enoch Adjei and Miao, Dong and Atuahene, William Adjei},
  title = {Multilevel Stacking with Domain-Adversarial Neural Network and Enriched Metadata for Improved Renewable Energy Output Forecasting},
  journal = {Journal of Technology Education and Applied Sciences},
  year = {2026},
  volume = {1},
  number = {1},
  pages = {32--45},
  doi = {10.64922/jteas.v1i1.86}
}
Kostenlos starten →