A Predictive Online Transient Stability Assessment with Hierarchical Generative Adversarial Networks

TL;DR

This paper introduces a novel GAN-based online transient stability assessment method that accurately predicts system stability with minimal data, significantly improving response time and accuracy over traditional techniques.

Contribution

The paper develops a hierarchical GAN approach that learns dynamic behaviors from historical data to enable fast, accurate stability assessment with fewer measurements.

Findings

Achieves higher assessment accuracy with only one data sample.

Provides faster response time compared to conventional methods.

Demonstrates superior performance on IEEE 118-bus system case studies.

Abstract

Online transient stability assessment (TSA) is essential for secure and stable power system operations. The growing number of Phasor Measurement Units (PMUs) brings about massive sources of data that can enhance online TSA. However, conventional data-driven methods require large amounts of transient data to correctly assess the transient stability state of a system. In this paper, a new data-driven TSA approach is developed for TSA with fewer data compared to the conventional methods. The data reduction is enabled by learning the dynamic behaviors of the historical transient data using generative and adversarial networks (GAN). This knowledge is used online to predict the voltage time series data after a transient event. A classifier embedded in the generative network deploys the predicted post-contingency data to determine the stability of the system following a fault. The developed GAN-based TSA approach preserves the spatial and temporal correlations that exist in multivariate PMU time series data. Hence, in comparison with the state-of-the-art TSA methods, it achieves a higher assessment accuracy using only one sample of the measured data and a shorter response time. Case studies conducted on the IEEE 118-bus system demonstrate the superior performance of the GAN-based method compared to the conventional data-driven techniques.