Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.05263 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908868496326656 |
|---|---|
| author | Li, Bowen Liu, Xiufeng Astefanoaei, Maria Sinziiana |
| author_facet | Li, Bowen Liu, Xiufeng Astefanoaei, Maria Sinziiana |
| contents | Accurate short-term wind power forecasting is essential for grid dispatch and market operations, yet centralising turbine data raises privacy, cost, and heterogeneity concerns. We propose a two-stage federated learning framework that first clusters turbines by long-term behavioural statistics using Double Roulette Selection (DRS) initialisation with recursive Auto-split refinement, and then trains cluster-specific LSTM models via FedAvg. Experiments on 400 stand-alone turbines in Denmark show that DRS-auto discovers behaviourally coherent groups and achieves competitive forecasting accuracy while preserving data locality. Behaviour-aware grouping consistently outperforms geographic partitioning and matches strong k-means++ baselines, suggesting a practical privacy-friendly solution for heterogeneous distributed turbine fleets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_05263 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A Behaviour-Aware Federated Forecasting Framework for Distributed Stand-Alone Wind Turbines Li, Bowen Liu, Xiufeng Astefanoaei, Maria Sinziiana Machine Learning Accurate short-term wind power forecasting is essential for grid dispatch and market operations, yet centralising turbine data raises privacy, cost, and heterogeneity concerns. We propose a two-stage federated learning framework that first clusters turbines by long-term behavioural statistics using Double Roulette Selection (DRS) initialisation with recursive Auto-split refinement, and then trains cluster-specific LSTM models via FedAvg. Experiments on 400 stand-alone turbines in Denmark show that DRS-auto discovers behaviourally coherent groups and achieves competitive forecasting accuracy while preserving data locality. Behaviour-aware grouping consistently outperforms geographic partitioning and matches strong k-means++ baselines, suggesting a practical privacy-friendly solution for heterogeneous distributed turbine fleets. |
| title | A Behaviour-Aware Federated Forecasting Framework for Distributed Stand-Alone Wind Turbines |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2603.05263 |