卢国强,李剑,王亦婷,肖智伟,王怀远
LU Guoqiang,LI Jian,WANG Yiting,XIAO Zhiwei,WANG Huaiyuan

• 1:国网青海省电力公司
• 2:福州大学电气工程与自动化学院

摘要(Abstract)：

迁移学习被引入电力系统暂态稳定评估中，以覆盖更多的评估场景。然而，当使用迁移学习方法将已知故障的分类边界知识迁移到潜在故障评估时，目标域中潜在故障的临界样本评估精度往往较低。为解决这一问题，提出一种基于多域鉴别器的多对抗迁移学习模型，引入故障严重程度指标作为先验知识，将故障样本细分为四类；通过多个域鉴别器分别对齐源域和目标域的四类样本，实现了源域与目标域数据的对齐；借助多对抗自适应框架，实现了样本分布的细粒度对齐，提升了目标域临界样本的评估精度，并进一步增强了迁移模型的正向迁移能力。IEEE 39系统和某区域电网的仿真结果验证了方法的有效性。
Transfer learning has been introduced to power system transient stability assessment(TSA) to expand scenario coverage. However, when transferring the classification boundary knowledge from known faults to potential fault assessments, existing methods often exhibit low accuracy for critical samples in the target domain. To address this, this paper proposes a multi-adversarial transfer learning model with multi-domain discriminators. By incorporating fault severity indices as prior knowledge, fault samples are subdivided into four classes. Multiple domain discriminators then align these four sample categories between source and target domains. Through a multi-adversarial adaptation framework, granular alignment of sample distribution is achieved. This approach significantly improves the assessment accuracy for critical samples in the target domain while enhancing the model's positive transfer capability. Simulation results on the IEEE 39-bus system and a regional power grid validate the effectiveness of the proposed method.

关键词(KeyWords)： 暂态稳定评估;迁移学习;对抗迁移;多域鉴别器;故障严重程度
TSA;transfer learning;adversarial transfer;multi-domain discriminator;fault severity

Abstract:

Keywords:

基金项目(Foundation): 福建省自然科学基金（2022J01113）;; 国网青海省电力有限公司科技项目（522800230001）

作者(Author): 卢国强,李剑,王亦婷,肖智伟,王怀远
LU Guoqiang,LI Jian,WANG Yiting,XIAO Zhiwei,WANG Huaiyuan

DOI: 10.19585/j.zjdl.202601003

参考文献(References)：

• [1]胡博，谢开贵，邵常政，等.双碳目标下新型电力系统风险评述：特征、指标及评估方法[J].电力系统自动化，2023,47(5):1-15.HU Bo,XIE Kaigui,SHAO Changzheng,et al.Commentary on risk of new power system under goals of carbon emission peak and carbon neutrality:characteristics,indices and assessment methods[J]. Automation of Electric Power Systems,2023,47(5):1-15.
• [2]王博文，王龙飞，董炜，等.受端电网暂态失稳场景识别及控制措施优化[J].浙江电力，2023,42(3):71-78.WANG Bowen,WANG Longfei,DONG Wei,et al.Recognition of transient instability scenarios of the receivingend grid and control strategy optimization[J]. Zhejiang Electric Power,2023,42(3):71-78.
• [3]孙海斌，傅国斌，宋锐，等.面向新型电力系统的静态电压稳定评估方法研究[J].电力电容器与无功补偿，2025,46(2):9-14.SUN Haibin,FU Guobin,SONG Rui,et al.Research on static voltage stability evaluation method for new power systems[J].Power Capacitor&Reactive Power Compensation,2025,46(2):9-14.
• [4]兰宇田，姚伟，张文栋，等.基于CatBoost的新型电力系统两阶段轻量化暂稳智能评估方法[J].山东电力技术，2024,51(2):1-10.LAN Yutian,YAO Wei,ZHANG Wendong,et al.Twostage lightweight transient stability intelligent assessment method for new type power systems based on CatBoost[J].Shandong Electric Power,2024,51(2):1-10.
• [5]李雅晗，夏世威，马琳琳，等.交直流混联系统暂态功角稳定评估及特征量可解释性分析[J].电力建设，2024,45(2):1-9.LI Yahan,XIA Shiwei,MA Linlin,et al.Transient power angle stability evaluation and interpretability analysis of AC/DC hybrid power system[J]. Electric Power Construction,2024,45(2):1-9.
• [6]赵晋泉，夏雪，徐春雷，等.新一代人工智能技术在电力系统调度运行中的应用评述[J].电力系统自动化，2020,44(24):1-10.ZHAO Jinquan,XIA Xue,XU Chunlei,et al.Review on application of new generation artificial intelligence technology in power system dispatching and operation[J].Automation of Electric Power Systems,2020,44(24):1-10.
• [7]曹瑞峰，刘子华，袁婷，等.基于改进SVM的新能源电站故障诊断方法[J].浙江电力，2023,42(11):11-20.CAO Ruifeng,LIU Zihua,YUAN Ting,et al.A fault diagnosis method for new energy power plants based on an improved SVM[J].Zhejiang Electric Power,2023,42(11):11-20.
• [8]翟雨佳，戴昀翔，刘浩，等.基于磁场和支持向量机的空心电抗器匝间短路诊断研究[J].电力电容器与无功补偿，2024,45(5):28-36.ZHAI Yujia,DAI Yunxiang,LIU Hao,et al.Research on inter-turn short circuit diagnosis of dry-type air-core reactor based on magnetic field and support vector machine[J].Power Capacitor&Reactive Power Compensation,2024,45(5):28-36.
• [9]刘俐，李勇，曹一家，等.基于支持向量机和长短期记忆网络的暂态功角稳定预测方法[J].电力自动化设备，2020,40(2):129-139.LIU Li,LI Yong,CAO Yijia,et al.Transient power angle stability prediction method based on support vector machine and long-term and short-term memory network[J].Electric Power Automation Equipment,2020,40(2):129-139.
• [10]王怀远，陈启凡.基于代价敏感堆叠变分自动编码器的暂态稳定评估方法[J].中国电机工程学报，2020,40(7):2213-2220.WANG Huaiyuan,CHEN Qifan.A transient stability assessment method based on cost-sensitive stacked variational auto-encoder[J].Proceedings of the CSEE,2020,40(7):2213-2220.
• [11]陆旭，张理寅，李更丰，等.基于内嵌物理知识卷积神经网络的电力系统暂态稳定评估[J].电力系统自动化，2024,48(9):107-119.LU Xu,ZHANG Liyin,LI Gengfeng,et al.Transient stability assessment of power system based on physics informed convolution neural network[J]. Automation of Electric Power Systems,2024,48(9):107-119.
• [12]朱乔木，陈金富，李弘毅，等.基于堆叠自动编码器的电力系统暂态稳定评估[J].中国电机工程学报，2018,38(10):2937-2946.ZHU Qiaomu,CHEN Jinfu,LI Hongyi,et al. Transient stability assessment based on stacked autoencoder[J].Proceedings of the CSEE,2018,38(10):2937-2946.
• [13]赵恺，石立宝.基于改进一维卷积神经网络的电力系统暂态稳定评估[J].电网技术，2021,45(8):2945-2957.ZHAO Kai,SHI Libao. Transient stability assessment of power system based on improved one-dimensional convolutional neural network[J]. Power System Technology,2021,45(8):2945-2957.
• [14]ZHUANG F Z,QI Z Y,DUAN K Y,et al.A comprehensive survey on transfer learning[J]. Proceedings of the IEEE,2021,109(1):43-76.
• [15]李晶晶，孟利超，张可，等.领域自适应研究综述[J].计算机工程，2021,47(6):1-13.LI Jingjing,MENG Lichao,ZHANG Ke,et al.Review of studies on domain adaptation[J].Computer Engineering,2021,47(6):1-13.
• [16]JAFARZADEH S,MOARREF N,YASLAN Y,et al.A CNN-based post-contingency transient stability prediction using transfer learning[C]//2019 11th International Conference on Electrical and Electronics Engineering(ELECO).November 28-30,2019.Bursa,Turkey.IEEE,2019:156-160.
• [17]申锦鹏，杨军，李蕊，等.基于改进域对抗迁移学习的电力系统暂态稳定自适应评估[J].电力系统自动化，2022,46(23):67-75.SHEN Jinpeng,YANG Jun,LI Rui,et al. Self-adaptive transient stability assessment of power system based on improved domain adversarial transfer learning[J].Automation of Electric Power Systems,2022,46(23):67-75.
• [18]吴思婕，王怀远.基于集成学习的时间自适应电力系统暂态稳定评估方法[J].电力系统保护与控制，2022,50(24):112-119.WU Sijie,WANG Huaiyuan. Transient stability assessment of power system with time-adaptive method based on ensemble learning[J]. Power System Protection and Control,2022,50(24):112-119.
• [19]解治军，张东霞，韩肖清，等.基于改进长短期记忆网络的电力系统暂态稳定评估方法研究[J].电网技术，2024,48(3):998-1010.XIE Zhijun,ZHANG Dongxia,HAN Xiaoqing,et al.Research on transient stability assessment method of power system based on improved long short term memory network[J]. Power System Technology,2024,48(3):998-1010.
• [20]胡杰祥，刘君，李岩松，等.基于GAN关键样本增强和迁移学习的暂态稳定自适应评估方法[J/OL].华北电力大学学报（自然科学版），2023:1-14(2023-12-12)[2025-03-12]. https：//link. cnki. net/urlid/13.1212. TM. 20231212.1209.004.HU Jiexiang,LIU Jun,LI Yansong,et al.Adaptive transient stability assessment method based on Gan key sample enhancement and transfer learning[J]. Journal of North China Electric Power University(Natural Science Edition),2023:1-14(2023-12-12)[2025-03-12].https：//link.cnki.net/urlid/13.1212.TM.20231212.1209.004.
• [21]肖龙，张靖，何宇，等.基于时间卷积和自适应图卷积网络的电力系统暂态稳定评估[J].电网技术，2025,49(11):4580-4590.XIAO Long,ZHANG Jing,HE Yu,et al.Power system transient stability assessment based on temporal convolution and adaptive graph convolution network[J]. Power System Technology,2025,49(11):4580-4590.
• [22]陈剑，杜文娟，王海风.基于对抗式迁移学习的含柔性高压直流输电的风电系统次同步振荡源定位[J].电工技术学报，2021,36(22):4703-4715.CHEN Jian,DU Wenjuan,WANG Haifeng. Location method of subsynchronous oscillation source in wind power system with VSC-HVDC based on adversarial transfer learning[J].Transactions of China Electrotechnical Society,2021,36(22):4703-4715.
• [23]赵冬梅，谢家康，王闯，等.基于Bagging集成学习的电力系统暂态稳定在线评估[J].电力系统保护与控制，2022,50(8):1-10.ZHAO Dongmei,XIE Jiakang,WANG Chuang,et al.Online transient stability assessment of a power system based on Bagging ensemble learning[J].Power System Protection and Control,2022,50(8):1-10.
• [24]REN C,XU Y.Transfer learning-based power system online dynamic security assessment:using one model to assess many unlearned faults[J]. IEEE Transactions on Power Systems,2020,35(1):821-824.
• [25]方熙，王怀远，党然，等.考虑样本加权的迁移学习暂态稳定评估模型更新方法[J].福州大学学报（自然科学版），2023,51(6):777-783.FANG Xi,WANG Huaiyuan,DANG Ran,et al.Transfer learning-based updating method of transient stability assessment model considering sample-weighted[J].Journal of Fuzhou University(Natural Science Edition),2023,51(6):777-783.
• [26]SUN B C,SAENKO K.Deep CORAL:correlation alignment for deep domain adaptation[C]//Computer Vision–ECCV 2016 Workshops.Cham:Springer International Publishing,2016:443-450.
• [27]CUI S H,WANG S H,ZHUO J B,et al.Towards discriminability and diversity:batch nuclear-norm maximization under label insufficient situations[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR). June 13-19,2020. Seattle,WA,USA.IEEE,2020:3940-3949.
• [28]许立雄，刘俊勇，刘洋，等.基于负荷电流场的电网分区方法[J].电网技术，2015,39(4):1039-1044.XU Lixiong,LIU Junyong,LIU Yang,et al.A load current field-based algorithm for partitioning power networks[J].Power System Technology,2015,39(4):1039-1044.
• [29]吴旻昊，王建功，朱英刚，等.基于t-SNE降维与聚类的主动配电网运行方式在线识别[J].电力建设，2023,44(8):52-60.WU Minhao,WANG Jiangong,ZHU Yinggang,et al.Online identification of active distribution network operation mode based on t-SNE dimensionality reduction and clustering[J]. Electric Power Construction,2023,44(8):52-60.
• [30]林楠，王怀远，陈启凡.基于后验分布信息的SSAE暂态稳定评估模型倾向性修正方法[J].电力自动化设备，2022,42(3):135-141.LIN Nan,WANG Huaiyuan,CHEN Qifan.Tendency correction method of SSAE transient stability assessment model based on posterior distribution information[J].Electric Power Automation Equipment,2022,42(3):135-141.