Deep Learning for Residential Electrical Energy Consumption Forecasting: A Hybrid Framework with Multiscale Temporal Analysis and Weather Integration

Bruno Knevitz Hammerschmitt (), Marcos Vinicio Haas Rambo (), Andre de Souza Leone, Luciana Michelotto Iantorno, Handy Borges Schiavon, Dayanne Peretti Corrêa, Paulo Lissa, Marcus Keane and Rodrigo Jardim Riella
Additional contact information
Bruno Knevitz Hammerschmitt: Future Grid, Lactec, Curitiba 80215-090, PR, Brazil
Marcos Vinicio Haas Rambo: Future Grid, Lactec, Curitiba 80215-090, PR, Brazil
Andre de Souza Leone: Future Grid, Lactec, Curitiba 80215-090, PR, Brazil
Luciana Michelotto Iantorno: Future Grid, Lactec, Curitiba 80215-090, PR, Brazil
Handy Borges Schiavon: College of Science and Engineering, University of Galway, H91 TK33 Galway, Ireland
Dayanne Peretti Corrêa: College of Science and Engineering, University of Galway, H91 TK33 Galway, Ireland
Paulo Lissa: College of Science and Engineering, University of Galway, H91 TK33 Galway, Ireland
Marcus Keane: College of Science and Engineering, University of Galway, H91 TK33 Galway, Ireland
Rodrigo Jardim Riella: Future Grid, Lactec, Curitiba 80215-090, PR, Brazil

Energies, 2025, vol. 18, issue 22, 1-29

Abstract: This paper presents an evaluation of the use of deep learning architectures for forecasting electrical energy consumption in residential environments. The main contribution of this study lies in the development and assessment of a hybrid forecasting framework that integrates multiscale temporal analysis and weather data, enabling evaluation of predictive performance across different temporal granularities, forecast horizons, and aggregation levels. Single and hybrid models were compared, trained with high-resolution data from a single residence, both considering only endogenous variables and including exogenous variables (weather data). The results showed that, among all models tested in this study, the hybrid LSTM + GRU model achieved the highest predictive performance, with R 2 values of 94.62% using energy data and 95.25% when weather variables were included. Intermediary granularities, particularly the 6 steps, offered the best balance between temporal detail and predictive robustness for the tests performed. Furthermore, short-time windows aggregation (1 to 5 min) showed better accuracy, while the inclusion of weather data in scenarios with larger aggregation windows and longer horizons provided additional gains. The results reinforce the potential of hybrid deep learning models as effective tools for forecasting residential electricity consumption, with possible practical applications in energy management, automation, and integration of distributed energy resources.

Keywords: electrical energy consumption forecasting; residential electricity consumption; deep learning; hybrid models; temporal granularity; multiscale; weather variables (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/1996-1073/18/22/5885/pdf (application/pdf)
https://www.mdpi.com/1996-1073/18/22/5885/ (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:22:p:5885-:d:1790457

Access Statistics for this article

Energies is currently edited by Ms. Cassie Shen

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