Most existing data-driven power system short-term voltage stability
assessment (STVSA) approaches presume class-balanced input data. However, in
practical applications, the occurrence of short-term voltage instability
following a disturbance is minimal, leading to a significant class imbalance
problem and a consequent decline in classifier performance. This work proposes
a Transformer-based STVSA method to address this challenge. By utilizing the
basic Transformer architecture, a stability assessment Transformer (StaaT) is
developed {as a classification model to reflect the correlation between the
operational states of the system and the resulting stability outcomes}. To
combat the negative impact of imbalanced datasets, this work employs a
conditional Wasserstein generative adversarial network with gradient penalty
(CWGAN-GP) for synthetic data generation, aiding in the creation of a balanced,
representative training set for the classifier. Semi-supervised clustering
learning is implemented to enhance clustering quality, addressing the lack of a
unified quantitative criterion for short-term voltage stability. {Numerical
tests on the IEEE 39-bus test system extensively demonstrate that the proposed
method exhibits robust performance under class imbalances up to 100:1 and noisy
environments, and maintains consistent effectiveness even with an increased
penetration of renewable energy}. Comparative results reveal that the CWGAN-GP
generates more balanced datasets than traditional oversampling methods and that
the StaaT outperforms other deep learning algorithms. This study presents a
compelling solution for real-world STVSA applications that often face class
imbalance and data noise challenges.

现有的数据驱动电力系统短期电压稳定性评估 (STVSA) 方法假定输入数据的类别平衡。然而，在实际应用中，干扰后出现短期电压不稳定的情况很少，导致严重的类别不平衡问题和分类器性能下降。为解决这一挑战，本论文提出了一种基于 Transformer 的 STVSA 方法。通过利用基本的 Transformer 结构，提出了一种稳定性评估 Transformer (StaaT) 作为分类模型，反映系统运行状态和稳定性结果之间的相关性。为应对不平衡数据集的负面影响，本研究采用带有梯度惩罚的条件 Wasserstein 生成对抗网络 (CWGAN-GP) 用于合成数据生成，帮助创建一个平衡且代表性的训练集用于分类器。此外，还实施了半监督聚类学习来提高聚类质量，解决了短期电压稳定性缺乏统一量化标准的问题。在 IEEE 39 节点测试系统上进行的数值测试广泛证明了所提出方法在类别不平衡达到 100:1 和噪声环境下的鲁棒性，并且即使增加了可再生能源的渗透，方法的有效性仍然保持一致。比较结果表明，CWGAN-GP 生成的数据集更平衡，而 StaaT 优于其他深度学习算法。该研究提供了一个具有说服力的解决方案，适用于经常面临类别不平衡和数据噪声挑战的实际 STVSA 应用场景。