An ensemble method for non-intrusive load monitoring (NILM) applied to deep learning approaches
| datacite.rights | http://purl.org/coar/access_right/c_abf2 | |
| dc.contributor.advisor | Moreno Trillos, Silvia | |
| dc.contributor.advisor | Villarreal, Reynaldo | |
| dc.contributor.author | Terán Torres, Héctor Rafael | |
| dc.date.accessioned | 2024-08-27T13:55:15Z | |
| dc.date.available | 2024-08-27T13:55:15Z | |
| dc.date.issued | 2024 | |
| dc.description.abstract | 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. | eng |
| dc.description.abstract | El cambio climático, impulsado principalmente por actividades humanas como la quema de combustibles fósiles, está causando cambios significativos a largo plazo en la temperatura y los patrones climáticos. Para mitigar estos impactos, hay un enfoque creciente en las fuentes de energía renovable. Sin embargo, la optimización del consumo de energía a través del control efectivo del uso y el reciclaje de desechos también ofrece un potencial sustancial para reducir la demanda de energía. Este estudio explora la monitorización no intrusiva de cargas (NILM) para estimar el consumo de energía desagregado a partir de un solo medidor doméstico, aprovechando los avances en aprendizaje profundo, como las redes neuronales convolucionales. El estudio utiliza el conjunto de datos UK-DALE para extraer y graficar datos de consumo de energía del medidor principal e identificar cinco electrodomésticos. Las redes neuronales convolucionales (CNN) se entrenan con aprendizaje por transferencia utilizando VGG16 y MobileNet. Los modelos se validan, prueban en conjuntos de datos divididos y se combinan mediante métodos de Ensemble para mejorar el rendimiento. Se propone un nuevo esquema de votación para Ensemble, llamado votación de confianza de promedio ponderado (WeCV), que se utiliza para crear combinaciones de los 3 y 5 mejores modelos y aplicarlas a NILM. Los modelos base logran hasta un 97% de precisión. Los métodos de Ensemble aplicando WeCV muestran un aumento de la precisión al 98%, superando los resultados anteriores más avanzados. Este estudio demuestra que las CNN con aprendizaje por transferencia desagregan eficazmente el uso de energía doméstica, logrando una alta precisión. Los métodos de Ensemble mejoran aún más el rendimiento, ofreciendo un enfoque prometedor para optimizar el uso de energía y mitigar el cambio climático. | spa |
| dc.format.mimetype | ||
| dc.identifier.doi | https://doi.org/10.3390/en17184548 | |
| dc.identifier.issn | 19961073 | |
| dc.identifier.uri | https://hdl.handle.net/20.500.12442/15423 | |
| dc.identifier.url | https://www.mdpi.com/1996-1073/17/18/4548 | |
| dc.language.iso | eng | |
| dc.publisher | Ediciones Universidad Simón Bolívar | spa |
| dc.publisher | Facultad de Ingenierías | spa |
| dc.publisher | MDPI | eng |
| dc.rights | Attribution-NonCommercial-NoDerivs 3.0 United States | eng |
| dc.rights.accessrights | info:eu-repo/semantics/openAccess | |
| dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/3.0/us/ | |
| dc.source | Energies | eng |
| dc.source | Vol.17 No.18 Año 2024 | spa |
| dc.source.bibliographicCitation | Moreno, S.; Teran, H.; Villarreal, R.; Vega-Sampayo, Y.; Paez, J.; Ochoa, C.; Espejo, C.A.; Chamorro-Solano, S.; Montoya, C. An Ensemble Method for Non-Intrusive Load Monitoring (NILM) Applied to Deep Learning Approaches. Energies 2024, 17, 4548. https://doi.org/10.3390/en17184548 | eng |
| dc.subject.keywords | NILM | eng |
| dc.subject.keywords | Convolutional neural networks | eng |
| dc.subject.keywords | Climate change | eng |
| dc.subject.keywords | Energy consumption optimization | eng |
| dc.title | An ensemble method for non-intrusive load monitoring (NILM) applied to deep learning approaches | eng |
| dc.type.driver | info:eu-repo/semantics/masterThesis | |
| dc.type.spa | Trabajo de grado máster | |
| dcterms.references | United Nations What Is Climate Change? Available online: https://www.un.org/es/climatechange/what-is-climate-change (ac- cessed on 18 May 2022). | eng |
| dcterms.references | Edmonds, J.; Abdallah, Z.S. IMG-NILM: A Deep Learning NILM Approach Using Energy Heatmaps. In Proceedings of the Proceedings of the 38th ACM/SIGAPP Symposium on Applied Computing, Tallinn, Estonia, 27–31 March 2023; Association for Computing Machinery: New York, NY, USA, 2023; pp. 1151–1153. | eng |
| dcterms.references | Hart, G.W. Nonintrusive Appliance Load Monitoring. Proc. IEEE 1992, 80, 1870–1891. https://doi.org/10.1109/5.192069. | eng |
| dcterms.references | Chavat, J.; Nesmachnow, S.; Graneri, J. Non-Intrusive Energy Disaggregation by Detecting Similarities in Consumption Pat- terns. Rev. Fac. Ing. Univ. Antioq. 2021, 98, 27–46. https://doi.org/10.17533/udea.redin.20200370. | eng |
| dcterms.references | Lazzaretti, A.E.; Renaux, D.P.B.; Lima, C.R.E.; Mulinari, B.M.; Ancelmo, H.C.; Oroski, E.; Pöttker, F.; Linhares, R.R.; da Silva Nolasco, L.; Lima, L.T.; et al. A Multi-Agent NILM Architecture for Event Detection and Load Classification. Energies 2020, 13, 4396. https://doi.org/10.3390/en13174396. | eng |
| dcterms.references | Biansoongnern, S.; Plangklang, B. An Alternative Low-Cost Embedded NILM System for Household Energy Conservation with a Low Sampling Rate. Symmetry 2022, 14, 279. https://doi.org/10.3390/sym14020279. | eng |
| dcterms.references | Li, M.; Tu, Z.; Wang, J.; Xu, P.; Wang, X. Dynamic Time Warping Optimization-Based Non-Intrusive Load Monitoring for Mul- tiple Household Appliances. Int. J. Electr. Power Energy Syst. 2024, 159, 110002. https://doi.org/10.1016/j.ijepes.2024.110002. | eng |
| dcterms.references | Pan, G.; Wang, H.; Tian, T.; Luo, Y.; Xia, S.; Li, Q. Research on Non-Intrusive Load Decomposition Model Based on Parallel Multi-Scale Attention Mechanism and Its Application in Smart Grid. Energy Build. 2024, 312, 114210. https://doi.org/10.1016/j.enbuild.2024.114210. | eng |
| dcterms.references | Li, Z.; Su, S.; Jin, X.; Xia, M.; Chen, Q.; Yamashita, K. Stochastic and Distributed Optimal Energy Management of Active Distri- bution Networks Within Integrated Office Buildings. CSEE J. Power Energy Syst. 2024, 10, 504–517. https://doi.org/10.17775/CSEEJPES.2021.04510. | eng |
| dcterms.references | Ding, B.; Li, Z.; Li, Z.; Xue, Y.; Chang, X.; Su, J.; Jin, X.; Sun, H. A CCP-Based Distributed Cooperative Operation Strategy for Multi-Agent Energy Systems Integrated with Wind, Solar, and Buildings. Appl. Energy 2024, 365, 123275. https://doi.org/10.1016/j.apenergy.2024.123275. | eng |
| dcterms.references | Nolasco, L.D.S.; Lazzaretti, A.E.; Mulinari, B.M. DeepDFML-NILM: A New CNN-Based Architecture for Detection, Feature Extraction and Multi-Label Classification in NILM Signals. IEEE Sens. J. 2022, 22, 501–509. https://doi.org/10.1109/JSEN.2021.3127322. | eng |
| dcterms.references | Machlev, R.; Belikov, J.; Beck, Y.; Levron, Y. MO-NILM: A Multi-Objective Evolutionary Algorithm for NILM Classification. Energy Build. 2019, 199, 134–144. https://doi.org/10.1016/j.enbuild.2019.06.046. | eng |
| dcterms.references | Ma, H.; Jia, J.; Yang, X.; Zhu, W.; Zhang, H. Mc-Nilm: A Multi-Chain Disaggregation Method for Nilm. Energies 2021, 14, 4331. https://doi.org/10.3390/en14144331. | eng |
| dcterms.references | Xu, W.; Jiang, C.; Zhang, Q.; Zheng, J. An Intelligent Non-Intrusive Load Monitoring Model Based on Power Encoding and Convolutional State Modules. Meas. Sci. Technol. 2024, 35, 086210. https://doi.org/10.1088/1361-6501/ad4b55. | eng |
| dcterms.references | Wang, Y.; Zhou, P.; Ye, W.; Qi, W. Non-Intrusive Load Monitoring and Its Privacy-Preserving Scheme Based on Pyramid Net- work. Jisuanji Gongcheng/Comput. Eng. 2024, 50, 182–189. https://doi.org/10.19678/j.issn.1000-3428.0067381. | eng |
| dcterms.references | Moreno, S.; Bonfante, M.; Zurek, E.; Cherezov, D.; Goldgof, D.; Hall, L.; Schabath, M. A Radiogenomics Ensemble to Predict EGFR and KRAS Mutations in NSCLC. Tomography 2021, 7, 154–168. https://doi.org/10.3390/tomography7020014. | eng |
| dcterms.references | Kelly, J.; Knottenbelt, W. The UK-DALE Dataset, Domestic Appliance-Level Electricity Demand and Whole-House Demand from Five UK Homes. Sci. Data 2015, 2, 150007. https://doi.org/10.1038/sdata.2015.7. | eng |
| dcterms.references | Batra, N.; Kelly, J.; Parson, O.; Dutta, H.; Knottenbelt, W.; Rogers, A.; Singh, A.; Srivastava, M. NILMTK: An Open Source Toolkit for Non-Intrusive Load Monitoring. In Proceedings of the 5th International Conference on Future Energy Systems, Cambridge, UK, 11–13 June 2014; Association for Computing Machinery: New York, NY, USA, 2014; pp. 265–276. | eng |
| dcterms.references | Sandler, M.; Howard, A.; Zhu, M.; Zhmoginov, A.; Chen, L.-C. MobileNetV2: Inverted Residuals and Linear Bottlenecks. In Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 18–23 June 2018; pp. 4510–4520. | eng |
| dcterms.references | Simonyan, K.; Zisserman, A. Very Deep Convolutional Networks for Large-Scale Image Recognition. In Proceedings of the 3rd International Conference on Learning Representations, ICLR 2015—Conference Track Proceedings, San Diego, CA, USA, 7–9 May 2015 | eng |
| oaire.version | info:eu-repo/semantics/acceptedVersion | |
| sb.programa | Maestría en Gestión y Emprendimiento Tecnológico | spa |
| sb.sede | Sede Barranquilla | spa |