An Ensemble Method for Non-Intrusive Load Monitoring (NILM) Applied to Deep Learning Approaches
Energies · 11.09.2024 · 17 (18) · 4548
DOI: 10.3390/en17184548 ↗Kurz gefasst
Fachartikel in der Zeitschrift Energies, online erschienen am 11.09.2024. Verfasst von Silvia Moreno und 8 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 20 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Colombian Ministry of Science, MINCIENCIAS.
Abstract (Originalsprache)
Climate change, primarily driven by human activities such as burning fossil fuels, is causing significant long-term changes in temperature and weather patterns. To mitigate these impacts, there is an increased focus on renewable energy sources. However, optimizing power consumption through effective usage control and waste recycling also offers substantial potential for reducing energy demands. This study explores non-intrusive load monitoring (NILM) to estimate disaggregated energy consumption from a single household meter, leveraging advancements in deep learning such as convolutional neural networks. The study uses the UK-DALE dataset to extract and plot power consumption data from the main meter and identify five household appliances. Convolutional neural networks (CNNs) are trained with transfer learning using VGG16 and MobileNet. The models are validated, tested on split datasets, and combined using ensemble methods for improved performance. A new voting scheme for ensembles is proposed, named weighted average confidence voting (WeCV), and it is used to create combinations of the best 3 and 5 models and applied to NILM. The base models achieve up to 97% accuracy. The ensemble methods applying WeCV show an increased accuracy of 98%, surpassing previous state-of-the-art results. This study shows that CNNs with transfer learning effectively disaggregate household energy use, achieving high accuracy. Ensemble methods further improve performance, offering a promising approach for optimizing energy use and mitigating climate change.
Förderung
- Colombian Ministry of Science, MINCIENCIAS
Zitieren
APA
Moreno, S., Teran, H., Villarreal, R., Vega-Sampayo, Y., Paez, J., Ochoa, C., Espejo, C. A., Chamorro-Solano, S., & Montoya, C. (2024). An Ensemble Method for Non-Intrusive Load Monitoring (NILM) Applied to Deep Learning Approaches. Energies, 17(18), 4548. https://doi.org/10.3390/en17184548
Vancouver
Moreno S, Teran H, Villarreal R, Vega-Sampayo Y, Paez J, Ochoa C, et al. An Ensemble Method for Non-Intrusive Load Monitoring (NILM) Applied to Deep Learning Approaches. Energies. 2024;17(18):4548. doi:10.3390/en17184548
BibTeX
@article{Moreno2024,
author = {Moreno, Silvia and Teran, Hector and Villarreal, Reynaldo and Vega-Sampayo, Yolanda and Paez, Jheifer and Ochoa, Carlos and Espejo, Carlos Alejandro and Chamorro-Solano, Sindy and Montoya, Camilo},
title = {An Ensemble Method for Non-Intrusive Load Monitoring (NILM) Applied to Deep Learning Approaches},
journal = {Energies},
year = {2024},
volume = {17},
number = {18},
pages = {4548},
doi = {10.3390/en17184548}
}
EUVIMED