FreeGNN: 为可再生能源预测的连续无源图神经网络适应
FreeGNN: Continual Source-Free Graph Neural Network Adaptation for Renewable Energy Forecasting
AI总结：
FreeGNN通过连续无源图神经网络适应技术，实现对可再生能源预测的准确鲁棒性，适用于多站点、多时间分辨率的实时环境适应。
摘要：
准确预测可再生能源发电量对于高效电网管理和可持续电力规划至关重要。然而，传统监督模型通常需要访问目标站点的标记数据，这可能由于隐私、成本或物流限制而不可用。在本工作中，我们提出了FreeGNN，一种连续无源图领域适应框架，使模型能够在未见过的可再生能源站点上进行适应性预测，而无需源数据或目标标签。我们的方法整合了时空图神经网络（GNN）主干与教师-学生策略，内存回放机制以缓解灾难性遗忘，基于图的正则化以保持空间相关性，以及一种意识漂移的加权方案，以在流式更新期间动态调整适应强度。这种组合使模型能够持续适应非平稳的环境条件，同时保持鲁棒性和稳定性。我们对三个真实世界数据集进行了广泛的实验：GEFCom2012、Solar PV和Wind SCADA，涵盖多个站点、时间分辨率和气象特征。消融研究确认了每个组件内存、图正则化、意识漂移适应和教师-学生策略对整体性能的显著贡献。实验显示，FreeGNN在GEFCom数据集上达到MAE为5.237和RMSE为7.123，在Solar PV数据集上达到MAE为1.107和RMSE为1.512，在Wind SCADA数据集上达到MAE为0.382和RMSE为0.523。这些结果展示了其在无源连续学习设置中实现准确且稳健预测的能力，突显了其在适应性可再生能源系统中实际部署的潜力。为可重复性，实现细节可在：https://github.com/AraoufBh/FreeGNN上找到。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
