| 引用本文: | 杨佳,蔡晔,曹一家,等.基于元学习与改进 Transformer 的 N-k 小样本暂态稳定事故筛选方法[J].电力系统保护与控制,2026,54(09):175-187. |
| YANG Jia,CAI Ye,CAO Yijia,et al.A few‑shot transient stability screening method for N‑k contingencies based on meta‑learning and an improved Transformer[J].Power System Protection and Control,2026,54(09):175-187 |
|
| 摘要: |
| N-k故障组合庞大，现有基于数据驱动的暂态稳定事故筛选研究需根据典型运行场景获取大量训练样本，
导致计算成本高昂，难以满足电力系统的N-k事故筛选需求。提出了一种基于元学习与改进Transformer的N-k
小样本暂态稳定事故筛选方法，可通过有限的低阶N-1故障来推断未知高阶N-k故障的暂态稳定性。首先，以
系统故障前后电气量作为故障特征矩阵，构造低阶故障为支持、高阶故障为查询的N-k元学习任务集。然后，考
虑低阶故障与高阶故障的复杂耦合特性，提出了一种关系网络与对比网络融合的面向联合故障的Transformer-元学
习算法(Transformer-meta learning for combined failure, T-MLCF)，通过改进 Transformer 构建关系网络以学习低阶故
障与高阶故障的非线性相似函数，通过对比网络挖掘低阶-高阶故障协同效应的组合性知识，基于此实现小样本情
况下对从未见过的N-k故障的泛化。最后，基于IEEE39系统的算例表明，T-MLCF 在小样本学习与泛化能力方
面表现优异，且在小样本规模变化时能够保持鲁棒性。 |
| 关键词: 事故筛选 暂态稳定 改进 Transformer 元学习 小样本学习 |
| DOI：10.19783/j.cnki.pspc.250731 |
| 分类号: |
| 基金项目:国家自然科学基金项目资助(52277076)；湖南省自然科学基金项目资助(2024JJ5019)；湖南省研究生创新项目资助(CX20240783) |
|
| A few‑shot transient stability screening method for N‑k contingencies based on meta‑learning and an improved Transformer |
|
YANG Jia, CAI Ye, CAO Yijia, SHI Xingyu, WANG Yuxun
|
|
State Key Laboratory of Power Grid Disaster Prevention & Reduction (School of Electrical and Information Engineering, Changsha University of Science and Technology), Changsha 410114, China
|
| Abstract: |
| The number of N‑k contingency combinations is enormous, and existing data‑driven transient stability contingency screening methods require large amounts of training data, resulting in high computational costs. To address this issue, a few‑shot N‑k transient stability screening method based on meta‑learning and an improved Transformer is proposed. Fault feature matrices are constructed using pre‑ and post‑fault electrical quantities to form N‑k meta‑learning tasks with low‑order faults as the support set and high‑order faults as the query set. A Transformer‑based meta‑learning algorithm for combined failures (T‑MLCF) fusing a relation network and a contrastive network is proposed to learn the nonlinear similarity and combinatorial knowledge. Case studies on the IEEE 39‑bus system demonstrate that T‑MLCF achieves superior few‑shot learning, generalization, and robustness, significantly reducing simulation costs. |
| Key words: contingency screening transient stability improved Transformer meta‑learning few‑shot learning |
