On Multi-Label Classification for Non-Intrusive Load Identification using Low Sampling Frequency Datasets

Titre	On Multi-Label Classification for Non-Intrusive Load Identification using Low Sampling Frequency Datasets
Publication Type	Conference Paper
Year of Publication	2021
Authors	Ahajjam, MA, Essayeh, C, Ghogho, M, Kobbane, A
Conference Name	Conference Record - IEEE Instrumentation and Measurement Technology Conference
Mots-clés	Aggregate consumption, Classification (of information), Electric consumption, Load identification, Machine learning models, Measurement, Multi label classification, Non-intrusive, Nonintrusive load monitoring, Sampling frequencies
Abstract	Non-intrusive load monitoring (NILM) aims to infer information about the electric consumption of individual loads using the premises' aggregate consumption. In this work, we target supervised multi-label classification for non-intrusive load identification. We describe how we have created a new dataset from Moroccan households using a low sampling frequency. Then, we analyze the performance of three machine learning models for NILM, and investigate the impact of signal input length on performance. © 2021 IEEE.
URL	https://www.scopus.com/inward/record.uri?eid=2-s2.0-85113709883&doi=10.1109%2fI2MTC50364.2021.9460059&partnerID=40&md5=2f6ca1a0b8790dce2a085d0e0ff10cf4
DOI	10.1109/I2MTC50364.2021.9460059