GCN-Based Model for Fault Classification in Distribution Networks under Harmonic DistortionNew

This paper presents a graph convolutional network (GCN) based approach for fault classification in power distribution networks. The model incorporates topology-aware features from the IEEE 34-bus test system, using pre-fault and post-fault voltage and current phasors including harmonic components introduced by inverter-based distributed energy resources. The research addresses the challenge of accurate fault detection under non-sinusoidal conditions typical of modern grids with high renewable penetration.