The evolution of the smart grid ecosystem is accelerating, driven by climate challenges and rising energy demand. Distributed renewable resources play a strategic role in enhancing grid stability and reducing greenhouse emissions. Industrial plants, as major energy consumers, are particularly well-positioned to benefit from these distributed resources. NonIntrusive Load Monitoring (NILM) has emerged as a valuable technique for optimizing the use of renewable energy through the insights extracted from smart meters. However, its application in industrial environments remains partially underexplored. This research addresses this gap by presenting the first comparative study of seven state-of-the-art NILM methods in the literature. We evaluate their performance at different signal resolutions using two publicly available datasets from different industrial contexts, one of which includes energy production signals. Given the complexity of industrial systems, this study highlights the need to account for the distinct characteristics of industrial electrical loads and to carefully adapt NILM methods to these unique conditions.
Industrial Non-Intrusive Power Monitoring to Unlock the Usability of Renewable Energy Sources: A Comparative Study / Tanoni, G., Khan, M.A., Xhani, E., Principi, E.. - (2025), pp. 919-924. (14th International Conference on Renewable Energy Research and Applications, ICRERA 2025 Vienna 27 - 30 October 2025) [10.1109/ICRERA66237.2025.11283653].
Industrial Non-Intrusive Power Monitoring to Unlock the Usability of Renewable Energy Sources: A Comparative Study
Tanoni, Giulia
Primo
;Xhani, Enrik;Principi, EmanueleUltimo
2025-01-01
Abstract
The evolution of the smart grid ecosystem is accelerating, driven by climate challenges and rising energy demand. Distributed renewable resources play a strategic role in enhancing grid stability and reducing greenhouse emissions. Industrial plants, as major energy consumers, are particularly well-positioned to benefit from these distributed resources. NonIntrusive Load Monitoring (NILM) has emerged as a valuable technique for optimizing the use of renewable energy through the insights extracted from smart meters. However, its application in industrial environments remains partially underexplored. This research addresses this gap by presenting the first comparative study of seven state-of-the-art NILM methods in the literature. We evaluate their performance at different signal resolutions using two publicly available datasets from different industrial contexts, one of which includes energy production signals. Given the complexity of industrial systems, this study highlights the need to account for the distinct characteristics of industrial electrical loads and to carefully adapt NILM methods to these unique conditions.| File | Dimensione | Formato | |
|---|---|---|---|
|
Tanoni_Industrial-Non-Intrusive-Power-Monitoring_2025.pdf
Solo gestori archivio
Tipologia:
Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza d'uso:
Tutti i diritti riservati
Dimensione
424.3 kB
Formato
Adobe PDF
|
424.3 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.


