english Icono del idioma   español Icono del idioma  

Please use this identifier to cite or link to this item: https://hdl.handle.net/20.500.12008/27046 How to cite
Title: End-to-end NILM system using high frequency data and neural networks.
Authors: Marchesoni, Franco
Mariño, Camilo
Masquil, Elías
Massaferro Saquieres, Pablo
Fernández, Alicia
Type: Preprint
Keywords: NILM, ANN, Energy disaggregation, Signal Processing
Issue Date: 2020
Abstract: Improving energy efficiency is a necessity in the fight against climate change. Non Intrusive Load Monitoring (NILM) systems give important information about the household consumption that can be used by the electric utility or the end users. In this work the implementation of an end-to-end NILM system is presented, which comprises a custom high frequency meter and neural-network based algorithms. The present article presents a novel way to include high frequency information as input of neural network models by means of multivariate time series that include carefully selected features. Furthermore, it provides a detailed assessment of the generalization error and shows that this class of models generalize well to new instances of seen-in-training appliances. An evaluation database formed of measurements in two Uruguayan homes is collected and discussion on general unsupervised approaches is provided
Publisher: arXiv
IN: Electrical Engineering and Systems Science (eess.SP - Signal Processing), pp. 1--11, apr. 2020, arXiv:2004.13905.
Citation: Marchesoni, F., Mariño, C., Masquil, E. y otros. End-to-end NILM system using high frequency data and neural networks. [Preprint]. EN: Electrical Engineering and Systems Science (eess.SP - Signal Processing), 2020, pp 1–11. arXiv:2004.13905.
Geographic coverage: Uruguay
License: Licencia Creative Commons Atribución - No Comercial - Sin Derivadas (CC - By-NC-ND 4.0)
Appears in Collections:Publicaciones académicas y científicas - Instituto de Ingeniería Eléctrica

Files in This Item:
File Description SizeFormat  
MMMMF20.pdfPreprint1,75 MBAdobe PDFView/Open


This item is licensed under a Creative Commons License Creative Commons