Transient Stability Assessment Based on Gated Graph Neural Network With Imbalanced Data in Internet of Energy

Abstract

Transient stability assessment (TSA) plays an important role to ensure the safe operation of the power system in Internet of Energy (IoE). Many time-domain simulation (TDS)-based and transient energy function (TEF)-based methods have been proposed to assess the transient stability of the power system. With the wide area measurement system (WAMS) and the phasor measure units (PMUs) applied to observe the real-time data, methods of TSA based on the machine learning and data-driven are continuously studied. These kinds of methods can only assess the transient stability of the power system when subjected to large disturbances. However, these kinds of methods cannot infer the type of event which leads to the collapse of the power system. In this article, the gated graph neural network (GGNN) is applied to assess the power system transient stability and infer the type of event leading the instability of the power system. First, conditional generative adversarial network (CGAN) is applied to generate unstable samples making the training data more balanced. With the balanced data graph-structured and used to train the GGNN-based TSA model, the GGNN-based TSA model achieves better performances. Finally, the real-time data is input into the trained TSA model and the transient stability of the power system is assessed. When the power system is considered unstable, the proposed TSA model can also infer the type of event leading the instability of the power system, classifying the unstable state to the corresponding event. Simulations performed on the New England 39-bus system verify the effectiveness of the proposed method.