An Interpretable Federated Learning Control Framework Design for Smart Grid Resilience
Ibrahim Shahbaz, Eman Hammad, Abdallah Farraj
TL;DR
The paper addresses transient stability resilience in cyber-physical power grids by introducing a federated learning control framework that trains interpretable Chebyshev Kolmogorov-Arnold Network controllers on a centralized policy and deploys them as distributed edge controllers at generator buses. It combines a physics-informed swing equation model with an FL learning loop using FedAvg to approximate centralized control actions through local measurements, yielding an interpretable, scalable control solution for modern smart grids. Key findings show that the FLC generalizes to unseen faults and outperforms a distributed baseline at moderate controller penetration, though performance declines at high penetration due to coordination challenges, and real-time inference remains a bottleneck requiring optimization. The approach offers privacy-preserving, adaptable resilience with potential for broader contingencies and RL-enhanced adaptivity, representing a practical step toward scalable, interpretable learning-based grid control.
Abstract
Power systems remain highly vulnerable to disturbances and cyber-attacks, underscoring the need for resilient and adaptive control strategies. In this work, we investigate a data-driven Federated Learning Control (FLC) framework for transient stability resilience under cyber-physical disturbances. The FLC employs interpretable neural controllers based on the Chebyshev Kolmogorov-Arnold Network (ChebyKAN), trained on a shared centralized control policy and deployed for distributed execution. Simulation results on the IEEE 39-bus New England system show that the proposed FLC consistently achieves faster stabilization than distributed baselines at moderate control levels (10\%--60\%), highlighting its potential as a scalable, resilient, and interpretable learning-based control solution for modern power grids.