A semi-supervised guided two-stage dimensionality reduction and visualization method for power system transient stability assessment

LI Rongxi; YU Zhihong; WANG Zigan; XIE Mei; WEI Xiao

doi:10.19783/j.cnki.pspc.251250

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

A semi-supervised guided two-stage dimensionality reduction and visualization method for power system transient stability assessment

更新时间：2026-05-14

- A semi-supervised guided two-stage dimensionality reduction and visualization method for power system transient stability assessment
- Power System Protection and Control Vol. 54, Issue 10, (2026)
- 作者机构：
  
  电网安全全国重点实验室 (中国电力科学研究院有限公司),北京,100192
- 作者简介：
- 基金信息：
- DOI：10.19783/j.cnki.pspc.251250
  CLC：
- Published：2026
- 稿件说明：
移动端阅览
LI Rongxi, YU Zhihong, WANG Zigan, et al. A semi-supervised guided two-stage dimensionality reduction and visualization method for power system transient stability assessment[J]. Power System Protection and Control, 2026, 54(10).
DOI：

LI Rongxi, YU Zhihong, WANG Zigan, et al. A semi-supervised guided two-stage dimensionality reduction and visualization method for power system transient stability assessment[J]. Power System Protection and Control, 2026, 54(10). DOI： 10.19783/j.cnki.pspc.251250.

摘要

针对现有数据驱动暂态稳定评估方法中高维样本可分性差、内在关联不清晰的问题，提出一种半监督指导的两阶段降维可视化方法。首先，采用基于双指标置信度和层次聚类引导的伪标签生成方法，对无标签样本进行高置信度筛选。然后，结合半监督修正 t 分布式随机邻居嵌入 (t-distributed stochastic neighbor embedding

t-SNE) 的距离度量，在有效分离不同类别样本的同时，最大程度保留数据的内部结构。最后，利用成对控制流形近似投影 (pairwise controlled manifold approximation projection

PaCMAP) 将高维数据映射至二维可视化空间。该方法可将电网运行状态及其稳定性的高维样本投影到二维空间；对未知状态数据，能基于已知运行点分布快速确定其位置与状态。在万节点标准算例和某实际电网上的验证结果表明了该方法的有效性。

Abstract

To address the issues of poor separability and unclear intrinsic correlations of high-dimensional samples in existing data-driven transient stability assessment methods

a semi-supervised guided two-stage dimensionality reduction and visualization method is proposed. First

a pseudo-label generation method based on dual-index confidence and hierarchical clustering guidance is used to screen unlabeled samples with high confidence. Then

by incorporating a semi-supervised modification into the distance metric of modified t-distributed stochastic neighbor embedding (t-SNE)

the method effectively separates samples of different categories while preserving the intrinsic structure of the data to the greatest extent. Finally

pairwise controlled manifold approximation projection (PaCMAP) is applied to map high-dimensional samples into a two-dimensional visualization space. The proposed method enables high-dimensional samples representing power system operating states and their stability to be projected into a 2D plane. For unknown operating conditions

their positions and stability status can be quickly determined based on the distribution of known operating point. Verification results on a large-scale system with tens of thousands of nodes and on a real-world power grid demonstrate the effectiveness of the proposed method.

关键词

Keywords

references

ZHOU Yibo, AN Jun, MU Gang, et al. An improved constraint-inference approach for causality exploration of power system transient stability[J]. Protection and Control of Modern Power Systems, 2023, 8(4): 1-12.

FAN Hang, HUANG Shaowei, CHEN Ying, et al. Visualization of power system transient process based on manifold learning[C] // 2016 35th Chinese Control Conference (CCC), July 27-29, 2016, Chengdu, China: 10119-10123.

SARAJCEV P, LOVRIC D. Manifold learning in electric power system transient stability analysis[J]. Energies, 2003, 16(23).

ROUSSEEUW P J. Silhouettes: a graphical aid to the interpretation and validation of cluster analysis[J]. Journal of Computational Applied Mathematics, 1987, 20(1): 53-65.

MAATEN L J P V D, HINTON G E. Visualizing high-dimensional data using t-SNE[J]. Journal of Machine Learning Research, 2008, 9: 2579-2605.

WANG Y, HUANG H, RUDIN C, et al. Understanding how dimension reduction tools work: an empirical approach to deciphering t-SNE, UMAP, TriMap, and PaCMAP for data visualization[J]. Journal of Machine Learning Research, 2021, 22: 1-7.

JOHNSON K, SONESON C, FONTES M. Low bias local intrinsic dimension estimation from expected simplex skewness[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(1): 196-202.

ALBERGANTE L, BAC J, ZINOVYEV A. Estimating the effective dimension of large biological datasets using Fisher separability analysis[C] // 2019 International Joint Conference on Neural Networks (IJCNN), July 14-19, 2019, Budapest, Hungary: 1-8.

ESTER M, KRIEGEL H P, SANDER J, et al. A density-based algorithm for discovering clusters in large spatial databases with noise[C] // Proceedings of the 2nd International Conference on Knowledge Discovery and Data Mining, August 2-4, 1996, Portland, Oregon, USA: 226-231.

LI Baoluo, XU Shiyun, LI Zonghan, et al. A short-term voltage stability evaluation method combining data-driven and mechanism criterion[J]. IEEE Transactions on Power Systems, 2025, 40(2): 1891-1902.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Adaptive power system transient stability assessment based on conditional denoising diffusion models and active transfer learning

基于改进CNNA的含风电电力系统暂态稳定评估

基于失稳模式自适应捕捉的暂态稳定评估方法

Transient stability assessment of power system with time-adaptive method based on ensemble learning

考虑代价敏感的AC-LSTM暂态稳定评估

Related Author

QU Ying

HAN Xiaoqing

JI Yue

WU Chaohui

NIU Zhewen

路敬祎

胡歆岳

刘伟

Related Institution

电力系统运行与控制山西省重点实验室(太原理工大学)

国网山西省电力公司电力科学研究院

1.东北石油大学电气信息工程学院

东北石油大学三亚海洋油气研究院

LU Guoqiang(1. Key Laboratory of New Energy Generation and Power Conversion (Fuzhou University)

AI问答

⁰