FedGuard-DC: Privacy-Preserving Federated Load Forecasting and Cyber-Attack Detection for Data-Center Loads in Transmission Systems
2026-08-19 • Cryptography and Security
Cryptography and Security
AI summaryⓘ
The authors developed FedGuard-DC, a system that helps data centers forecast their power use without sharing sensitive data. Each data center trains a local model that predicts load and checks for tampered data, keeping private information safe. The models send only updates to a central controller, preserving privacy and security. Their testing showed accurate forecasting and effective detection of false data, even when some data inputs were corrupted.
federated learningdata center loadload forecastingfalse-data-injection attackprivacy-preservinganomaly detectiondifferential privacymachine learningpower systemsrobust aggregation
Authors
Md Kibria Saroare, Md Rubel Ahmed
Abstract
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.