Improving accuracy and convergence of federated learning edge computing methods for generalized DER forecasting applications in power grid
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916437420933120 |
|---|---|
| author | Nair, Vineet Jagadeesan Pereira, Lucas |
| author_facet | Nair, Vineet Jagadeesan Pereira, Lucas |
| contents | This proposal aims to develop more accurate federated learning (FL) methods with faster convergence properties and lower communication requirements, specifically for forecasting distributed energy resources (DER) such as renewables, energy storage, and loads in modern, low-carbon power grids. This will be achieved by (i) leveraging recently developed extensions of FL such as hierarchical and iterative clustering to improve performance with non-IID data, (ii) experimenting with different types of FL global models well-suited to time-series data, and (iii) incorporating domain-specific knowledge from power systems to build more general FL frameworks and architectures that can be applied to diverse types of DERs beyond just load forecasting, and with heterogeneous clients. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_10018 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Improving accuracy and convergence of federated learning edge computing methods for generalized DER forecasting applications in power grid Nair, Vineet Jagadeesan Pereira, Lucas Machine Learning Artificial Intelligence Distributed, Parallel, and Cluster Computing Systems and Control This proposal aims to develop more accurate federated learning (FL) methods with faster convergence properties and lower communication requirements, specifically for forecasting distributed energy resources (DER) such as renewables, energy storage, and loads in modern, low-carbon power grids. This will be achieved by (i) leveraging recently developed extensions of FL such as hierarchical and iterative clustering to improve performance with non-IID data, (ii) experimenting with different types of FL global models well-suited to time-series data, and (iii) incorporating domain-specific knowledge from power systems to build more general FL frameworks and architectures that can be applied to diverse types of DERs beyond just load forecasting, and with heterogeneous clients. |
| title | Improving accuracy and convergence of federated learning edge computing methods for generalized DER forecasting applications in power grid |
| topic | Machine Learning Artificial Intelligence Distributed, Parallel, and Cluster Computing Systems and Control |
| url | https://arxiv.org/abs/2410.10018 |