Real Implementation and Testing of Short-Term Building Load Forecasting: A Comparison of SVR and NARX

Juan José Hernández, Irati Zapirain, Haritza Camblong (), Nora Barroso and Octavian Curea
Additional contact information
Juan José Hernández: Department of Systems Engineering and Control, Faculty of Engineering of Gipuzkoa, University of the Basque Country (UPV/EHU), Plaza de Europa 1, 20018 Donostia-San Sebastian, Spain
Irati Zapirain: Department of Systems Engineering and Control, Faculty of Engineering of Gipuzkoa, University of the Basque Country (UPV/EHU), Plaza de Europa 1, 20018 Donostia-San Sebastian, Spain
Haritza Camblong: Department of Systems Engineering and Control, Faculty of Engineering of Gipuzkoa, University of the Basque Country (UPV/EHU), Plaza de Europa 1, 20018 Donostia-San Sebastian, Spain
Nora Barroso: Department of Systems Engineering and Control, Faculty of Engineering of Gipuzkoa, University of the Basque Country (UPV/EHU), Plaza de Europa 1, 20018 Donostia-San Sebastian, Spain
Octavian Curea: Estia Institute of Technology, Technopole Izarbel, University of Bordeaux, F-64210 Bidart, France

Energies, 2025, vol. 18, issue 7, 1-17

Abstract: In self-consumption (SC) configurations, energy management systems (EMSs) are increasingly being implemented to maximise the self-consumption ratio (SCR). Recent studies have demonstrated that prediction-based EMSs significantly enhance decision-making capabilities compared to non-predictive EMSs. This paper presents the design, implementation, and testing on a real system of two machine learning (ML)-type predictive models capable of forecasting the electricity consumption of an individual building using a small dataset. A nonlinear autoregressive with exogenous input (NARX) neural network model and a support vector regression (SVR) model were designed and compared. These models predict day-ahead hourly electricity consumption using forecasted meteorological data from Meteo Galicia (MG) and building occupancy data, both automatically obtained and pre-processed. In order to compensate for the lack of recurrence of the SVR model, the effect of introducing an additional input, a time vector, was analysed. It is proved that both ML models trained with a small dataset are able to predict the next day’s average hourly power with a mean MAPE below 13.96% and a determination coefficient (R 2 ) greater than 0.78. The model that most accurately predicts the hourly average power of a week is the SVR, which achieves a mean MAPE and R 2 of 10.73% and 0.85, respectively.

Keywords: short-term load forecasting; machine learning; nonlinear autoregressive exogenous; support vector regression; automatic pre-processing; small dataset (search for similar items in EconPapers)
JEL-codes: Q Q0 Q4 Q40 Q41 Q42 Q43 Q47 Q48 Q49 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1996-1073/18/7/1775/pdf (application/pdf)
https://www.mdpi.com/1996-1073/18/7/1775/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jeners:v:18:y:2025:i:7:p:1775-:d:1626361

Access Statistics for this article

Energies is currently edited by Ms. Agatha Cao

More articles in Energies from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().