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.
@article{arxiv.2603.05263,
title = {A Behaviour-Aware Federated Forecasting Framework for Distributed Stand-Alone Wind Turbines},
author = {Bowen Li and Xiufeng Liu and Maria Sinziiana Astefanoaei},
journal= {arXiv preprint arXiv:2603.05263},
year = {2026}
}