AI 中文总结
FedGuard-DC是一种联邦学习框架，可在不共享原始数据的情况下，对输电系统数据中心负荷实现准确预测和高检测率的虚假数据注入攻击，且具备隐私保护与抗中毒能力。
AI 中文摘要
大型数据中心（DC）负荷的快速增长给电力系统的可见性、隐私性及网络物理安全带来了新挑战。系统运营商需要这些快速变化负荷的准确短期信息，而DC运营商可能不愿共享原始兆瓦级测量数据，因为这些数据会泄露敏感的工作负载和利用率模式。本文提出FedGuard-DC，这是一种用于隐私保护DC负荷预测和本地虚假数据注入攻击（FDIA）检测的联邦学习（FL）框架。每个DC基于自身测量数据训练一个双头模型，其中共享编码器同时支持预测头和重建头。校准后的异常分数结合预测残差和重建误差，用于本地检测被篡改的测量数据。原始测量数据和绝对兆瓦级需求保留在各DC，仅模型更新与全局控制器共享。框架还包含可选的差分隐私和鲁棒修剪均值聚合，以评估隐私-效用行为和中毒客户端的弹性。该框架通过集成到IEEE 39母线新英格兰系统中的4个额定值在150至350 MW之间的大型DC负荷的EMT仿真数据进行验证。结果显示，提前0.5秒的归一化预测均方根误差（RMSE）为0.023-0.038 pu，而 persistence 方法为0.32-0.34 pu；FedGuard-DC检测FDIA的ROC-AUC为0.979，F1值为0.930，精确率为0.988，同时鲁棒聚合将中毒客户端的RMSE影响从0.042降低至0.035 pu。
英文摘要
The rapid growth of large data-center (DC) loads is creating new challenges for power-system visibility, privacy, and cyber-physical security. System operators need accurate short-term information about these fast-varying loads, while DC operators may avoid sharing raw megawatt measurements because they can reveal sensitive workload and utilization patterns. This paper presents FedGuard-DC, a federated learning (FL) framework for privacy-preserving DC load forecasting and local false-data-injection attack (FDIA) detection. Each DC trains a dual-head model on its own measurements, where a shared encoder supports both a forecasting head and a reconstruction head. A calibrated anomaly score combines forecast residual and reconstruction error to detect corrupted measurements locally. Raw measurements and absolute MW demand remain at each DC, while only model updates are shared with the global controller. Optional differential privacy and robust trimmed-mean aggregation are included to evaluate privacy-utility behavior and poisoned-client resilience. The framework is validated using EMT simulation data from four large DC loads rated between 150 and 350 MW integrated into the IEEE 39-bus New England system. Results show a 0.5 s-ahead normalized forecast RMSE of 0.023-0.038 pu, compared with 0.32-0.34 pu for persistence. FedGuard-DC detects FDIA with ROC-AUC of 0.979, F1 = 0.930, and precision of 0.988, while robust aggregation reduces the poisoned-client RMSE impact from 0.042 to 0.035 pu.
CommentsAccepted on North American Power Symposium (NAPS) 2026
