电力系统及其自动化学报2024，Vol.36Issue(4)：59-67,75,10.DOI:10.19635/j.cnki.csu-epsa.001311
基于CBAM-CNN的电力系统暂态电压稳定评估
CBAM-CNN-based Short-term Voltage Stability Assessment of Power System
李欣 1柳圣池 2李新宇 3陈德秋 4鲁玲 2郭攀锋1
作者信息
- 1. 三峡大学电气与新能源学院,宜昌 443000||智慧能源技术湖北省工程研究中心(三峡大学),宜昌 443000
- 2. 三峡大学电气与新能源学院,宜昌 443000
- 3. 中国长江三峡集团有限公司,宜昌 443631
- 4. 国网湖北省电力有限公司咸宁供电公司,咸宁 437100
- 折叠
摘要
Abstract
To further improve the feature extraction capability of a short-term voltage stability assessment model for pow-er system and its adaptability when the system topology changes,a method combining an improved convolutional neural network(CNN)with transfer learning is proposed.First,a convolutional block attention module(CBAM)is inserted af-ter the convolution layer of CNN to extract features from the input data in two independent dimensions of channel and space sequentially,thus improving the capability of CNN to recognize the system's short-term voltage state.Then,the module is combined with the fine-tuning technology to improve the model's online update speed when the system topolo-gy changes.Finally,the analysis of numerical examples verifies the effectiveness the proposed model.关键词
深度学习/卷积神经网络/暂态电压稳定评估/卷积块注意力模块/迁移学习Key words
deep learning/convolutional neural network(CNN)/short-term voltage stability assessment/convolution-al block attention module(CBAM)/transfer learning分类
信息技术与安全科学引用本文复制引用
李欣,柳圣池,李新宇,陈德秋,鲁玲,郭攀锋..基于CBAM-CNN的电力系统暂态电压稳定评估[J].电力系统及其自动化学报,2024,36(4):59-67,75,10.
