Neural Network-Aided NILM (NNAN) disaggregation: Revealing appliance consumption patterns with iterative subtraction
Non-Intrusive Load Monitoring (NILM) is a method to decompose overall electricity consumption into individual appliance-level data, utilizing the primary meter’s readings without additional sensors on each device. This article introduces a novel approach which is a Neural Network-Aided NILM (NNAN),...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-06-01
|
| Series: | Machine Learning with Applications |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2666827025000507 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850222471643398144 |
|---|---|
| author | Yacine Belguermi Patrice Wira Gilles Hermann |
| author_facet | Yacine Belguermi Patrice Wira Gilles Hermann |
| author_sort | Yacine Belguermi |
| collection | DOAJ |
| description | Non-Intrusive Load Monitoring (NILM) is a method to decompose overall electricity consumption into individual appliance-level data, utilizing the primary meter’s readings without additional sensors on each device. This article introduces a novel approach which is a Neural Network-Aided NILM (NNAN), focusing on revealing appliance consumption patterns by following a sequential subtraction method. Our goal is to tackle the issue where high-power and highly-used appliances make it difficult for neural networks to accurately separate the usage of lower-power and less-used appliances. We mainly employ Long Short-Term Memory (LSTM) and Convolutional Neural Networks (CNN) using inception blocks as key components. Our proposed architecture is validated on three public datasets that are AMPds2, ECO and UK-DALE. The NNAN model showed promising results, achieving disaggregation accuracy improvements of up to 5.13% on AMPds2, 3.79% on ECO, and 9.55% on UK-DALE compared to the reference methods. Additionally, NNAN reduces model complexity, requiring up to 74% fewer parameters than traditional deep learning approaches, leading to improved computational efficiency. Finally, NNAN demonstrated a reduced correlation between appliance usage rates and disaggregation accuracies. |
| format | Article |
| id | doaj-art-b373bb9d911f4a9da9594ffe2017f8ec |
| institution | OA Journals |
| issn | 2666-8270 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Machine Learning with Applications |
| spelling | doaj-art-b373bb9d911f4a9da9594ffe2017f8ec2025-08-20T02:06:20ZengElsevierMachine Learning with Applications2666-82702025-06-012010066710.1016/j.mlwa.2025.100667Neural Network-Aided NILM (NNAN) disaggregation: Revealing appliance consumption patterns with iterative subtractionYacine Belguermi0Patrice Wira1Gilles Hermann2Institut de Recherche en Informatique, Mathématiques, Automatique et Signal, Université de Haute Alsace, Mulhouse, FranceCorresponding author.; Institut de Recherche en Informatique, Mathématiques, Automatique et Signal, Université de Haute Alsace, Mulhouse, FranceInstitut de Recherche en Informatique, Mathématiques, Automatique et Signal, Université de Haute Alsace, Mulhouse, FranceNon-Intrusive Load Monitoring (NILM) is a method to decompose overall electricity consumption into individual appliance-level data, utilizing the primary meter’s readings without additional sensors on each device. This article introduces a novel approach which is a Neural Network-Aided NILM (NNAN), focusing on revealing appliance consumption patterns by following a sequential subtraction method. Our goal is to tackle the issue where high-power and highly-used appliances make it difficult for neural networks to accurately separate the usage of lower-power and less-used appliances. We mainly employ Long Short-Term Memory (LSTM) and Convolutional Neural Networks (CNN) using inception blocks as key components. Our proposed architecture is validated on three public datasets that are AMPds2, ECO and UK-DALE. The NNAN model showed promising results, achieving disaggregation accuracy improvements of up to 5.13% on AMPds2, 3.79% on ECO, and 9.55% on UK-DALE compared to the reference methods. Additionally, NNAN reduces model complexity, requiring up to 74% fewer parameters than traditional deep learning approaches, leading to improved computational efficiency. Finally, NNAN demonstrated a reduced correlation between appliance usage rates and disaggregation accuracies.http://www.sciencedirect.com/science/article/pii/S2666827025000507NILMNeural networksEnergy disaggregationInception CNNLSTM |
| spellingShingle | Yacine Belguermi Patrice Wira Gilles Hermann Neural Network-Aided NILM (NNAN) disaggregation: Revealing appliance consumption patterns with iterative subtraction Machine Learning with Applications NILM Neural networks Energy disaggregation Inception CNN LSTM |
| title | Neural Network-Aided NILM (NNAN) disaggregation: Revealing appliance consumption patterns with iterative subtraction |
| title_full | Neural Network-Aided NILM (NNAN) disaggregation: Revealing appliance consumption patterns with iterative subtraction |
| title_fullStr | Neural Network-Aided NILM (NNAN) disaggregation: Revealing appliance consumption patterns with iterative subtraction |
| title_full_unstemmed | Neural Network-Aided NILM (NNAN) disaggregation: Revealing appliance consumption patterns with iterative subtraction |
| title_short | Neural Network-Aided NILM (NNAN) disaggregation: Revealing appliance consumption patterns with iterative subtraction |
| title_sort | neural network aided nilm nnan disaggregation revealing appliance consumption patterns with iterative subtraction |
| topic | NILM Neural networks Energy disaggregation Inception CNN LSTM |
| url | http://www.sciencedirect.com/science/article/pii/S2666827025000507 |
| work_keys_str_mv | AT yacinebelguermi neuralnetworkaidednilmnnandisaggregationrevealingapplianceconsumptionpatternswithiterativesubtraction AT patricewira neuralnetworkaidednilmnnandisaggregationrevealingapplianceconsumptionpatternswithiterativesubtraction AT gilleshermann neuralnetworkaidednilmnnandisaggregationrevealingapplianceconsumptionpatternswithiterativesubtraction |