Adaptive Stacking with Locally Calibrated Exogenous Variables for Short-Term Electricity Demand Forecasting in a Sparsely Populated Region
Electronics · 07.11.2026 · 15 (21) · 5176
DOI: 10.3390/electronics15215176 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics, online erschienen am 07.11.2026. Verfasst von Fatih Durmuş und 3 weiteren Autor:innen. Die Arbeit nennt 79 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
In this study, 20 methods are evaluated for daily electricity-demand forecasting in Giresun, Türkiye, at one-, two-, and three-day horizons. Consumption-only inputs (S1) are compared with calendar, weather, and event inputs (S2). Forecast-origin temperature persistence and training-only degree-day calibration are used in S2, with origin-day observations assumed available at issuance. Common fitting labels, separate tuning and stopping stages, temporal out-of-fold combination, and condition-specific hyperparameter selection are used over three nonoverlapping outer periods comprising 639 test days. Metrics are calculated from daily seed-mean forecasts, with seed dispersion reported separately. Under S2, a T+1 MAPE of 1.924% and an RMSE of 54.32 MWh are obtained with AS-Pair. The lowest T+2 MAPE (2.709%) is obtained with inverse-MSE blending, while the lowest T+3 MAPE (3.027%) is obtained with CNN-GRU. Lower MAPE is obtained under S2 in 48 of 54 non-naive method–horizon comparisons, with an overall mean reduction of 0.625 percentage points. These results support horizon-specific model selection for daily electricity-demand forecasting in Giresun.
Zitieren
APA
Durmuş, F., Özbilgin, F., Çalık, H., & Çeltekligil, U. (2026). Adaptive Stacking with Locally Calibrated Exogenous Variables for Short-Term Electricity Demand Forecasting in a Sparsely Populated Region. Electronics, 15(21), 5176. https://doi.org/10.3390/electronics15215176
Vancouver
Durmuş F, Özbilgin F, Çalık H, Çeltekligil U. Adaptive Stacking with Locally Calibrated Exogenous Variables for Short-Term Electricity Demand Forecasting in a Sparsely Populated Region. Electronics. 2026;15(21):5176. doi:10.3390/electronics15215176
BibTeX
@article{Durmu2026,
author = {Durmuş, Fatih and Özbilgin, Ferdi and Çalık, Hüseyin and Çeltekligil, Uğur},
title = {Adaptive Stacking with Locally Calibrated Exogenous Variables for Short-Term Electricity Demand Forecasting in a Sparsely Populated Region},
journal = {Electronics},
year = {2026},
volume = {15},
number = {21},
pages = {5176},
doi = {10.3390/electronics15215176}
}
EUVIMED