A Behaviour-Aware Federated Forecasting Framework for Distributed Stand-Alone Wind Turbines

TL;DR

This paper introduces a federated learning framework for wind turbine forecasting that clusters turbines based on behavior, enabling accurate, privacy-preserving short-term predictions for distributed turbines.

Contribution

It presents a novel two-stage federated approach combining behavior-based clustering with cluster-specific LSTM models, improving accuracy and privacy in wind power forecasting.

Findings

Behaviorally coherent groups identified by DRS auto clustering.

Achieved competitive forecasting accuracy while preserving data privacy.

Outperformed geographic partitioning and matched k-means++ baselines.

Abstract

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.