Skip to Main content Skip to Navigation
Journal articles

Comparative Evaluation of Non-Intrusive Load Monitoring Methods Using Relevant Features and Transfer Learning

Abstract : Non-Intrusive Load Monitoring (NILM) refers to the analysis of the aggregated current and voltage measurements of Home Electrical Appliances (HEAs) recorded by the house electrical panel. Such methods aim to identify each HEA for a better control of the energy consumption and for future smart grid applications. Here, we are interested in an event-based NILM pipeline, and particularly in the HEAs’ recognition step. This paper focuses on the selection of relevant and understandable features for efficiently discriminating distinct HEAs. Our contributions are manifold. First, we introduce a new publicly available annotated dataset of individual HEAs described by a large set of electrical features computed from current and voltage measurements in steady-state conditions. Second, we investigate through a comparative evaluation a large number of new methods resulting from the combination of different feature selection techniques with several classification algorithms. To this end, we also investigate an original feature selection method based on a deep neural network architecture. Then, through a machine learning framework, we study the benefits of these methods for improving Home Electrical Appliance (HEA) identification in a supervised classification scenario. Finally, we introduce new transfer learning results, which confirm the relevance and the robustness of the selected features learned from our proposed dataset when they are transferred to a larger dataset. As a result, the best investigated methods outperform the previous state-of-the-art results and reach a maximum recognition accuracy above 99% on the PLAID evaluation dataset.
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03223322
Contributor : Dominique Fourer Connect in order to contact the contributor
Submitted on : Monday, May 10, 2021 - 6:58:09 PM
Last modification on : Friday, September 24, 2021 - 6:24:02 PM
Long-term archiving on: : Wednesday, August 11, 2021 - 8:11:46 PM

File

energies-Houidi21_final.pdf
Publisher files allowed on an open archive

Identifiers

Citation

Sarra Houidi, Dominique Fourer, François Auger, Houda Ben Attia Sethom, Laurence Miègeville. Comparative Evaluation of Non-Intrusive Load Monitoring Methods Using Relevant Features and Transfer Learning. Energies, MDPI, 2021, 14 (9), pp.2726. ⟨10.3390/en14092726⟩. ⟨hal-03223322⟩

Share

Metrics

Record views

140

Files downloads

132