FreeGNN: Continual Source-Free Graph Neural Network Adaptation for Renewable Energy Forecasting

2026-03-02

AI Summary

This work proposes FreeGNN, a novel framework that achieves source-free and label-free continual graph domain adaptation under the extreme constraint of inaccessible source data and target labels. By integrating spatiotemporal graph neural networks with teacher–student learning, memory replay, graph regularization, and a drift-aware weighting mechanism, FreeGNN effectively mitigates catastrophic forgetting while preserving spatial correlations, enabling stable predictions in dynamic environments. Extensive experiments on the GEFCom2012, Solar PV, and Wind SCADA datasets demonstrate its high accuracy and robustness in source-free continual learning scenarios, achieving mean absolute errors (MAE) of 5.237, 1.107, and 0.382, respectively.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

Abstract

Accurate forecasting of renewable energy generation is essential for efficient grid management and sustainable power planning. However, traditional supervised models often require access to labeled data from the target site, which may be unavailable due to privacy, cost, or logistical constraints. In this work, we propose FreeGNN, a Continual Source-Free Graph Domain Adaptation framework that enables adaptive forecasting on unseen renewable energy sites without requiring source data or target labels. Our approach integrates a spatio-temporal Graph Neural Network (GNN) backbone with a teacher--student strategy, a memory replay mechanism to mitigate catastrophic forgetting, graph-based regularization to preserve spatial correlations, and a drift-aware weighting scheme to dynamically adjust adaptation strength during streaming updates. This combination allows the model to continuously adapt to non-stationary environmental conditions while maintaining robustness and stability. We conduct extensive experiments on three real-world datasets: GEFCom2012, Solar PV, and Wind SCADA, encompassing multiple sites, temporal resolutions, and meteorological features. The ablation study confirms that each component memory, graph regularization, drift-aware adaptation, and teacher--student strategy contributes significantly to overall performance. The experiments show that FreeGNN achieves an MAE of 5.237 and an RMSE of 7.123 on the GEFCom dataset, an MAE of 1.107 and an RMSE of 1.512 on the Solar PV dataset, and an MAE of 0.382 and an RMSE of 0.523 on the Wind SCADA dataset. These results demonstrate its ability to achieve accurate and robust forecasts in a source-free, continual learning setting, highlighting its potential for real-world deployment in adaptive renewable energy systems. For reproducibility, implementation details are available at: https://github.com/AraoufBh/FreeGNN.

Problem

• renewable energy forecasting
• source-free adaptation
• continual learning
• graph neural networks
• domain adaptation

Innovation

• Source-Free Domain Adaptation
• Continual Learning
• Graph Neural Networks
• Renewable Energy Forecasting
• Catastrophic Forgetting