Conditioned fully convolutional denoising autoencoder for multi-target NILM
Neural Computing and Applications · 2025-06 · 37 (17) · 10491-10505
DOI: 10.1007/s00521-024-10552-0 ↗Kurz gefasst
Fachartikel in der Zeitschrift Neural Computing and Applications, online erschienen am 05.12.2024. Verfasst von Diego García und 6 weiteren Autor:innen. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministerio de Ciencia e Innovación, Universidad de Oviedo.
Abstract (Originalsprache)
Energy management requires reliable tools to support decisions aimed at optimising consumption. Advances in data-driven models provide techniques like Non-Intrusive Load Monitoring (NILM), which estimates the energy demand of appliances from total consumption. Common single-target NILM approaches perform energy disaggregation by using separate learned models for each device. However, the use of single-target systems in real scenarios is computationally expensive and can obscure the interpretation of the resulting feedback. This study assesses a conditioned deep neural network built upon a Fully Convolutional Denoising AutoEncoder (FCNdAE) as multi-target NILM model. The network performs multiple disaggregations using a conditioning input that allows the specification of the target appliance. Experiments compare this approach with several single-target and multi-target models using public residential data from households and non-residential data from a hospital facility. Results show that the multi-target FCNdAE model enhances the disaggregation accuracy compared to previous models, particularly in non-residential data, and improves computational efficiency by reducing the number of trainable weights below 2 million and inference time below 0.25 s for several sequence lengths. Furthermore, the conditioning input helps the user to interpret the model and gain insight into its internal behaviour when predicting the energy demand of different appliances.
Förderung
- Ministerio de Ciencia e Innovación
- Universidad de Oviedo
Zitieren
APA
García, D., Pérez, D., Papapetrou, P., Díaz, I., Cuadrado, A. A., Enguita, J. M., & Domínguez, M. (2025). Conditioned fully convolutional denoising autoencoder for multi-target NILM. Neural Computing and Applications, 37(17), 10491-10505. https://doi.org/10.1007/s00521-024-10552-0
Vancouver
García D, Pérez D, Papapetrou P, Díaz I, Cuadrado AA, Enguita JM, et al. Conditioned fully convolutional denoising autoencoder for multi-target NILM. Neural Computing and Applications. 2025;37(17):10491-10505. doi:10.1007/s00521-024-10552-0
BibTeX
@article{Garca2025,
author = {García, Diego and Pérez, Daniel and Papapetrou, Panagiotis and Díaz, Ignacio and Cuadrado, Abel A. and Enguita, José M. and Domínguez, Manuel},
title = {Conditioned fully convolutional denoising autoencoder for multi-target NILM},
journal = {Neural Computing and Applications},
year = {2025},
volume = {37},
number = {17},
pages = {10491--10505},
doi = {10.1007/s00521-024-10552-0}
}
EUVIMED