Intelligence-Driven Solar Power Prediction: The Impact of Feature Selection and Seasonal Training Approaches on Model Performance
ADCAIJ: Advances in Distributed Computing and Artificial Intelligence Journal · 17.11.2026 · 15 · e34834
DOI: 10.14201/adcaij.34834 ↗Kurz gefasst
Fachartikel in der Zeitschrift ADCAIJ: Advances in Distributed Computing and Artificial Intelligence Journal, online erschienen am 17.11.2026. Verfasst von Beatriz Teixeira und 5 weiteren Autor:innen. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-SA 4.0).
Abstract (Originalsprache)
This study evaluates machine learning paradigms for photovoltaic power generation forecasting, focusing on the impact of architectural structures and feature selection on predictive stability. Using data from Portugal, we tested multiple combinations of meteorological variables and seasonal training approaches. Results demonstrate that ensemble tree-based methods, particularly Random Forest, offer superior robustness and generalization compared to kernel based and connectionist architectures when handling non-linear environmental transitions. A critical finding reveals that models relying exclusively on historical lags often function as naive predictors, emphasizing the necessity of integrating exogenous meteorological features for effective forecasting. Overall, this research highlights the importance of feature engineering and strategic training in enhancing model performance for intelligent energy management within smart grid contexts.
Zitieren
APA
Teixeira, B., Pinto, T., Catarino, P., Vasco, P., Reis, A., & Barroso, J. (2026). Intelligence-Driven Solar Power Prediction: The Impact of Feature Selection and Seasonal Training Approaches on Model Performance. ADCAIJ: Advances in Distributed Computing and Artificial Intelligence Journal, 15, e34834. https://doi.org/10.14201/adcaij.34834
Vancouver
Teixeira B, Pinto T, Catarino P, Vasco P, Reis A, Barroso J. Intelligence-Driven Solar Power Prediction: The Impact of Feature Selection and Seasonal Training Approaches on Model Performance. ADCAIJ: Advances in Distributed Computing and Artificial Intelligence Journal. 2026;15:e34834. doi:10.14201/adcaij.34834
BibTeX
@article{Teixeira2026,
author = {Teixeira, Beatriz and Pinto, Tiago and Catarino, Paula and Vasco, Paulo and Reis, Arsénio and Barroso, João},
title = {Intelligence-Driven Solar Power Prediction: The Impact of Feature Selection and Seasonal Training Approaches on Model Performance},
journal = {ADCAIJ: Advances in Distributed Computing and Artificial Intelligence Journal},
year = {2026},
volume = {15},
pages = {e34834},
doi = {10.14201/adcaij.34834}
}
EUVIMED