Imbalanced Sample Generation and Evaluation for Power System Transient Stability Using CTGAN

TL;DR

This paper introduces a CTGAN-based framework for generating balanced transient stability samples in power systems, improving the training of deep learning models for stability assessment.

Contribution

It presents a novel controllable sample generation method using CTGAN with multi-conditional capabilities and evaluation metrics tailored for power system transient stability data.

Findings

Generated samples balance the dataset effectively.

Improved accuracy of transient stability assessment models.

Framework validated on IEEE 39-bus system.

Abstract

Although deep learning has achieved impressive advances in transient stability assessment of power systems, the insufficient and imbalanced samples still trap the training effect of the data-driven methods. This paper proposes a controllable sample generation framework based on Conditional Tabular Generative Adversarial Network (CTGAN) to generate specified transient stability samples. To fit the complex feature distribution of the transient stability samples, the proposed framework firstly models the samples as tabular data and uses Gaussian mixture models to normalize the tabular data. Then we transform multiple conditions into a single conditional vector to enable multi-conditional generation. Furthermore, this paper introduces three evaluation metrics to verify the quality of generated samples based on the proposed framework. Experimental results on the IEEE 39-bus system show that the proposed framework effectively balances the transient stability samples and significantly improves the performance of transient stability assessment models.