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

2026-03-05

AI Summary

This study addresses the challenges of data privacy leakage, high communication costs, and turbine heterogeneity in short-term power forecasting for distributed standalone wind turbines. To this end, a two-stage federated learning framework is proposed. First, turbines are clustered based on long-term operational behavior through an innovative behavior-aware grouping strategy that integrates Double Roulette Selection for initialization and recursive Auto-split optimization, yielding privacy-preserving clusters that outperform geographical partitioning and rival k-means++ in quality. Subsequently, within each cluster, LSTM models are trained federatively to balance data locality with predictive accuracy. Experiments on a dataset comprising 400 wind turbines from Denmark demonstrate that the method effectively identifies groups of turbines with consistent operational behavior and achieves significantly higher prediction accuracy than geographical partitioning, exhibiting strong practicality and competitiveness.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Search and Optimization: Distributed Search
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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.

Problem

• federated forecasting
• wind power prediction
• data privacy
• behavioral heterogeneity
• distributed wind turbines

Innovation

• Federated Learning
• Behaviour-Aware Clustering
• Double Roulette Selection
• Wind Power Forecasting
• LSTM