Transferable Learning of GCN Sampling Graph Data Clusters from Different Power Systems

EasyChair Preprint 15038

Abstract

Contemporary neural network (NN) detectors for power systems face two primary challenges. First, each power sys- tem requires individual training of NN detectors to accommodate its unique configuration and base demands. Second, significant changes within the power system, such as the introduction of new substations or new generators, necessitate retraining. To overcome these issues, we introduce a novel architecture, the Nodal Graph Convolutional Neural Network (NGCN), which utilizes graph convolutions at each bus and its neighborhoods. This approach allows the training process to encompass multiple power systems and include all buses, thereby enhancing the transferability of the method across different power systems. The NGCN is particularly effective for detection tasks, such as cyber-attacks on smart inverters and false data injection attacks. Our tests demonstrate that the NGCN significantly improves performance over traditional NNs, boosting detection accuracy from approximately 85% to around 97% for the aforementioned task. Furthermore, the transferable NGCN, which is trained by samples from multiple power systems, performs considerably better in evaluations than the NGCN trained on a single power system.

Keyphrases: Cyber Attack Detection, Graph Convolutional Neural Networks, Power Grid Universal Learning

@booklet{EasyChair:15038,
  author    = {Tong Wu and Anna Scaglione and Daniel Arnold and Tianyi Chen},
  title     = {Transferable Learning of GCN Sampling Graph Data Clusters from Different Power Systems},
  howpublished = {EasyChair Preprint 15038},
  year      = {EasyChair, 2024}}