Federated learning-enhanced generative models for non-intrusive load monitoring in smart homes
Abstract Non-Intrusive Load Monitoring (NILM) estimates load-specific power by disaggregating household-level power data, enabling smart grids to provide more accurate power estimations and thus prevent energy waste and casualties. Some existing NILM methods employ federated learning (FL) with gener...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-07-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-11403-1 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849235397131894784 |
|---|---|
| author | Yuefeng Lu Shijin Xu Yadong Liu Xiuchen Jiang |
| author_facet | Yuefeng Lu Shijin Xu Yadong Liu Xiuchen Jiang |
| author_sort | Yuefeng Lu |
| collection | DOAJ |
| description | Abstract Non-Intrusive Load Monitoring (NILM) estimates load-specific power by disaggregating household-level power data, enabling smart grids to provide more accurate power estimations and thus prevent energy waste and casualties. Some existing NILM methods employ federated learning (FL) with generative models to estimate load power; however, their accuracy often suffers within an FL architecture. This is because the generators tend to learn the most common load patterns while neglecting the less frequent ones. To address this, we propose an FL architecture with a Wasserstein generative adversarial network (FL-WGAN) to enhance accuracy. In our method, each client trains its own generative neural network to estimate load power, while a discriminator network evaluates these estimates. Each client employs a Wasserstein distance-based guidance mechanism to ensure the generative model learns the full distribution of all states rather than being confined to a subset. Additionally, an attention mechanism is integrated into the generative model to further improve its representational capability. We evaluate FL-WGAN using the UA-DALE and REDD datasets, and the results demonstrate that our method outperforms existing methods. |
| format | Article |
| id | doaj-art-b95dd5a4e56b45f3af956a09ff1c8cf4 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-b95dd5a4e56b45f3af956a09ff1c8cf42025-08-20T04:02:46ZengNature PortfolioScientific Reports2045-23222025-07-0115111310.1038/s41598-025-11403-1Federated learning-enhanced generative models for non-intrusive load monitoring in smart homesYuefeng Lu0Shijin Xu1Yadong Liu2Xiuchen Jiang3Smart Grid Center, Shanghai Jiao Tong UniversitySouthern Power Grid Company, China Southern Power GridSmart Grid Center, Shanghai Jiao Tong UniversitySmart Grid Center, Shanghai Jiao Tong UniversityAbstract Non-Intrusive Load Monitoring (NILM) estimates load-specific power by disaggregating household-level power data, enabling smart grids to provide more accurate power estimations and thus prevent energy waste and casualties. Some existing NILM methods employ federated learning (FL) with generative models to estimate load power; however, their accuracy often suffers within an FL architecture. This is because the generators tend to learn the most common load patterns while neglecting the less frequent ones. To address this, we propose an FL architecture with a Wasserstein generative adversarial network (FL-WGAN) to enhance accuracy. In our method, each client trains its own generative neural network to estimate load power, while a discriminator network evaluates these estimates. Each client employs a Wasserstein distance-based guidance mechanism to ensure the generative model learns the full distribution of all states rather than being confined to a subset. Additionally, an attention mechanism is integrated into the generative model to further improve its representational capability. We evaluate FL-WGAN using the UA-DALE and REDD datasets, and the results demonstrate that our method outperforms existing methods.https://doi.org/10.1038/s41598-025-11403-1Smart GridNon-Intrusive Load Monitoring (NILM)Federated Learning (FL)Wasserstein Generative Adversarial Network (WGAN) |
| spellingShingle | Yuefeng Lu Shijin Xu Yadong Liu Xiuchen Jiang Federated learning-enhanced generative models for non-intrusive load monitoring in smart homes Scientific Reports Smart Grid Non-Intrusive Load Monitoring (NILM) Federated Learning (FL) Wasserstein Generative Adversarial Network (WGAN) |
| title | Federated learning-enhanced generative models for non-intrusive load monitoring in smart homes |
| title_full | Federated learning-enhanced generative models for non-intrusive load monitoring in smart homes |
| title_fullStr | Federated learning-enhanced generative models for non-intrusive load monitoring in smart homes |
| title_full_unstemmed | Federated learning-enhanced generative models for non-intrusive load monitoring in smart homes |
| title_short | Federated learning-enhanced generative models for non-intrusive load monitoring in smart homes |
| title_sort | federated learning enhanced generative models for non intrusive load monitoring in smart homes |
| topic | Smart Grid Non-Intrusive Load Monitoring (NILM) Federated Learning (FL) Wasserstein Generative Adversarial Network (WGAN) |
| url | https://doi.org/10.1038/s41598-025-11403-1 |
| work_keys_str_mv | AT yuefenglu federatedlearningenhancedgenerativemodelsfornonintrusiveloadmonitoringinsmarthomes AT shijinxu federatedlearningenhancedgenerativemodelsfornonintrusiveloadmonitoringinsmarthomes AT yadongliu federatedlearningenhancedgenerativemodelsfornonintrusiveloadmonitoringinsmarthomes AT xiuchenjiang federatedlearningenhancedgenerativemodelsfornonintrusiveloadmonitoringinsmarthomes |