An Adaptive ML Framework for Power Converter Monitoring via Federated Transfer Learning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913806019461120 |
|---|---|
| author | Kakosimos, Panagiotis Saberi, Alireza Nemat Peretti, Luca |
| author_facet | Kakosimos, Panagiotis Saberi, Alireza Nemat Peretti, Luca |
| contents | This study explores alternative framework configurations for adapting thermal machine learning (ML) models for power converters by combining transfer learning (TL) and federated learning (FL) in a piecewise manner. This approach inherently addresses challenges such as varying operating conditions, data sharing limitations, and security implications. The framework starts with a base model that is incrementally adapted by multiple clients via adapting three state-of-the-art domain adaptation techniques: Fine-tuning, Transfer Component Analysis (TCA), and Deep Domain Adaptation (DDA). The Flower framework is employed for FL, using Federated Averaging for aggregation. Validation with field data demonstrates that fine-tuning offers a straightforward TL approach with high accuracy, making it suitable for practical applications. Benchmarking results reveal a comprehensive comparison of these methods, showcasing their respective strengths and weaknesses when applied in different scenarios. Locally hosted FL enhances performance when data aggregation is not feasible, while cloud-based FL becomes more practical with a significant increase in the number of clients, addressing scalability and connectivity challenges. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_16866 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | An Adaptive ML Framework for Power Converter Monitoring via Federated Transfer Learning Kakosimos, Panagiotis Saberi, Alireza Nemat Peretti, Luca Machine Learning This study explores alternative framework configurations for adapting thermal machine learning (ML) models for power converters by combining transfer learning (TL) and federated learning (FL) in a piecewise manner. This approach inherently addresses challenges such as varying operating conditions, data sharing limitations, and security implications. The framework starts with a base model that is incrementally adapted by multiple clients via adapting three state-of-the-art domain adaptation techniques: Fine-tuning, Transfer Component Analysis (TCA), and Deep Domain Adaptation (DDA). The Flower framework is employed for FL, using Federated Averaging for aggregation. Validation with field data demonstrates that fine-tuning offers a straightforward TL approach with high accuracy, making it suitable for practical applications. Benchmarking results reveal a comprehensive comparison of these methods, showcasing their respective strengths and weaknesses when applied in different scenarios. Locally hosted FL enhances performance when data aggregation is not feasible, while cloud-based FL becomes more practical with a significant increase in the number of clients, addressing scalability and connectivity challenges. |
| title | An Adaptive ML Framework for Power Converter Monitoring via Federated Transfer Learning |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2504.16866 |