Imbalanced Sample Generation and Evaluation for Power System Transient Stability Using CTGAN
This work addresses data imbalance issues in power system transient stability assessment, which is incremental as it applies an existing method (CTGAN) to a specific domain with modifications.
The paper tackles the problem of insufficient and imbalanced samples in transient stability assessment for power systems by proposing a CTGAN-based framework to generate specified samples, which effectively balances the data and significantly improves model performance on the IEEE 39-bus system.
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.