A Physics-Informed Topology-Adaptive Graph Convolutional Network for Harmonic Source Location in Three-phase Distribution Networks with Renewable Energy Integration

The large-scale integration of renewable energy sources has led to a significant increase in the number of harmonic sources within distribution networks. Concurrently, the altered supply modes introduced by renewable integration have caused dynamic changes in the network topology. Therefore, this paper proposes a three-phase distribution network harmonic source location method based on a physics informed topology adaptive graph convolutional network. Firstly, a harmonic pseudo-measurement method based on emission characteristics modelling is developed to address the shortage of harmonic measurements. Secondly, considering the dynamic changes in the distribution network topology, a multi-layer perception topology adaptive graph convolutional neural network is proposed, which is used to establish the mapping relationship between harmonic measurements and state variables. Meanwhile, the harmonic transfer equation and system parameters are embedded into the neural network training as physical constraints to ensure the results conform to physical properties. Then, a harmonic source identification criterion is established, and the long-term statistical index derived from the estimated harmonic injection current is used to locate harmonic sources in the distribution network. Finally, the effectiveness of the proposed method was verified in the IEEE 37-bus system and the actual system.