Fault Location in Distribution Network Based on RNN and Transfer Learning

Fault location in distribution networks is a major challenge that needs to be addressed in power distribution systems. Currently, fault location methods based on matrix algorithms, genetic algorithms, deep learning, and other algorithms have received wide attention from the industry. However, such methods have some drawbacks: (1) they require high accuracy in fault information uploads, which can lead to low fault tolerance; (2) they tend to converge early and get stuck in local optimal solutions; (3) they involve high computational complexity, leading to location delays. In this study, we propose a fault location framework based on recurrent neural network (RNN) and transfer learning. In this method, we first encode the information data collected from distribution terminals, and then use RNN to establish a nonlinear mapping relationship between fault features and fault location intervals, which effectively improves fault tolerance and reduces misjudgment issues. We then use transfer learning to load the pre-trained model onto the target task to address the problem of insufficient data for fault location in distribution networks. Experimental results show that after 15 rounds of training, our T-RNN model has achieved over 80% accuracy. Benefiting from Glorot weight initialization adopted after transfer learning, the model achieves good performance early on compared to the BP model, converges faster, and ultimately achieves a prediction accuracy of 96.5%.