Two-stage random search–Bayesian optimization for CNN-based short-term load forecasting
Bulletin of Electrical Engineering and Informatics · 01.06.2026 · 15 (3) · 2734-2746
DOI: 10.11591/eei.v15i3.11030 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bulletin of Electrical Engineering and Informatics, online erschienen am 01.06.2026. Verfasst von Tuan Anh Nguyen und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).
Abstract (Originalsprache)
This study proposes a two-stage hyperparameter optimization pipeline for convolutional neural network (CNN)–based short-term electricity load forecasting. In the first stage, random search is used to broadly explore candidate configurations, including the number of filters in each convolutional layer, batch size, training epochs, and the loss function. In the second stage, Bayesian optimization based on the tree-structured Parzen estimator (TPE), implemented in Optuna, refines promising regions of the hyperparameter space to obtain a better-performing model. The optimized CNN is evaluated using half-hourly (30-minute) electricity demand data from New South Wales (NSW), Victoria (VIC), and Queensland (QLD), and is benchmarked against a baseline CNN, a multilayer perceptron (MLP), an extended short-term memory network, and single-stage optimization variants. Across the three regions, the proposed approach achieves mean absolute percentage error (MAPE) values between 1.05% and 1.14%, representing an improvement of approximately 58% over the baseline CNN. Statistical robustness is examined using paired Wilcoxon signed-rank tests with Holm–Bonferroni correction on per-timestamp errors. Overall, the results indicate that combining random search with Bayesian optimization improves CNN forecasting accuracy across the three studied regions and provides a transparent tuning framework for future replication.
Zitieren
APA
Nguyen, T. A., & Tran, T. N. (2026). Two-stage random search–Bayesian optimization for CNN-based short-term load forecasting. Bulletin of Electrical Engineering and Informatics, 15(3), 2734-2746. https://doi.org/10.11591/eei.v15i3.11030
Vancouver
Nguyen TA, Tran TN. Two-stage random search–Bayesian optimization for CNN-based short-term load forecasting. Bulletin of Electrical Engineering and Informatics. 2026;15(3):2734-2746. doi:10.11591/eei.v15i3.11030
BibTeX
@article{Nguyen2026,
author = {Nguyen, Tuan Anh and Tran, Thanh Ngoc},
title = {Two-stage random search–Bayesian optimization for CNN-based short-term load forecasting},
journal = {Bulletin of Electrical Engineering and Informatics},
year = {2026},
volume = {15},
number = {3},
pages = {2734--2746},
doi = {10.11591/eei.v15i3.11030}
}
EUVIMED