Uncertainty-Aware Federated Learning for Cyber-Resilient Microgrid Energy Management

TL;DR

This paper introduces a cyber-resilient federated learning framework for microgrid energy management that detects false data attacks, maintains forecast accuracy, and reduces operational costs under cyber threats.

Contribution

It proposes a novel two-stage attack detection method combined with federated LSTM-based forecasting, enhancing security and efficiency in microgrid energy management.

Findings

Reduced false positive detection by 70%

Recovered 93.7% of forecast performance losses

Achieved 5% operational cost savings

Abstract

Maintaining economic efficiency and operational reliability in microgrid energy management systems under cyberattack conditions remains challenging. Most approaches assume non-anomalous measurements, make predictions with unquantified uncertainties, and do not mitigate malicious attacks on renewable forecasts for energy management optimization. This paper presents a comprehensive cyber-resilient framework integrating federated Long Short-Term Memory-based photovoltaic forecasting with a novel two-stage cascade false data injection attack detection and energy management system optimization. The approach combines autoencoder reconstruction error with prediction uncertainty quantification to enable attack-resilient energy storage scheduling while preserving data privacy. Extreme false data attack conditions were studied that caused 58% forecast degradation and 16.9\% operational cost increases. The proposed integrated framework reduced false positive detections by 70%, recovered 93.7% of forecasting performance losses, and achieved 5\% operational cost savings, mitigating 34.7% of attack-induced economic losses. Results demonstrate that precision-focused cascade detection with multi-signal fusion outperforms single-signal approaches, validating security-performance synergy for decentralized microgrids.