杨凯璇,卢国强,傅国斌,张文朝,刘利军,李杏
YANG Kaixuan,LU Guoqiang,FU Guobin,ZHANG Wenzhao,LIU Lijun,LI Xing

• 1:国网青海省电力公司电力科学研究院
• 2:国网青海省电力公司
• 3:北京科东电力控制系统有限责任公司
• 4:国网青海省电力公司物资公司

摘要(Abstract)：

现有暂态稳定评估研究中对关键影响因素的量化分析不足，导致评估结果的准确性受限。为此，提出基于HGNN（层次图神经网络）的电力系统暂态稳定评估方法，重点量化分析故障区域和新能源比例两个关键因素。首先，利用图理论对故障区域进行化简和分区，识别出对暂态稳定评估影响较大的关键故障区域。其次，以双馈异步风机作为典型新能源发电设备，考虑其等效特性，量化分析不同新能源比例对暂态稳定评估输入特征的影响。随后，基于HGNN模型研究关键故障区域和新能源比例对暂态稳定评估的影响。最后，在IEEE 39节点系统上进行算例分析。结果表明，HGNN模型的性能指标均优于其他传统模型，识别关键故障区域能够提升评估的准确性，而新能源比例的增加会在一定程度上降低评估的准确性。
In current research on transient stability assessment, the absence of quantitative analysis of key influencing factors hampers the accuracy of assessment results. Thus, a transient stability assessment method for power systems using hierarchical graph neural network(HGNN) is proposed, concentrating on the quantitative analysis of two crucial factors: fault area and the proportion of renewable energy. Firstly, graph theory is employed to simplify and partition the fault areas, identifying key fault areas that significantly impact transient stability assessment. Secondly, with doubly-fed asynchronous wind turbine generators as typical renew energy generation devices and considering their equivalent characteristics, the influence of different renewable energy proportions on the input features of transient stability assessment is quantitatively analyzed. Then, the impact of key fault areas and renewable energy proportion on transient stability assessment is explored using the HGNN model. Finally, a case study is carried out on the IEEE 39-bus system. The results indicate that the performance indicators of the HGNN model outperform those of traditional models. Identifying key fault areas can enhance assessment accuracy, while an increase in the proportion of renewable energy will reduce assessment accuracy to a certain degree.

关键词(KeyWords)： 暂态稳定评估;HGNN;关键区域识别;特征量化
transient stability assessment;HGNN;critical region identification;feature quantification

Abstract:

Keywords:

基金项目(Foundation): 青海省重点研发与转换计划项目(2023-GX-158)

作者(Author): 杨凯璇,卢国强,傅国斌,张文朝,刘利军,李杏
YANG Kaixuan,LU Guoqiang,FU Guobin,ZHANG Wenzhao,LIU Lijun,LI Xing

DOI: 10.19585/j.zjdl.202507004

参考文献(References)：

• [1]周艳真，吴俊勇，冀鲁豫，等.基于两阶段支持向量机的电力系统暂态稳定预测及预防控制[J].中国电机工程学报，2018,38(1):137-147.ZHOU Yanzhen,WU Junyong,JI Luyu,et al.Two-stage support vector machines for transient stability prediction and preventive control of power systems[J].Proceedings of the CSEE,2018,38(1):137-147.
• [2]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.
• [3]陈水耀，胡晨，马伟，等.基于故障信息的风机并网系统暂态稳定分析方法[J].浙江电力，2023,42(9):89-98.CHEN Shuiyao,HU Chen,MA Wei,et al. A Transient stability analysis method for power systems with wind turbines integrated based on fault information[J]. Zhejiang Electric Power,2023,42(9):89-98.
• [4]项中明，倪秋龙，李振华，等.采用功率同步控制的构网型换流器并网暂态同步稳定研究[J].浙江电力，2023,42(9):77-88.XIANG Zhongming,NI Qiulong,LI Zhenhua,et al. Research on transient synchronous stability of integrated gridforming converters using power synchronization control[J].Zhejiang Electric Power,2023,42(9):77-88.
• [5]李欣，付豫韬，李新宇，等.基于GAF-CNN的电力系统暂态稳定评估[J].智慧电力，2023,51(11):45-52.LI Xin,FU Yutao,LI Xinyu,et al.Power system transient stability assessment based on GAF-CNN[J]. Smart Power,2023,51(11):45-52.
• [6]ZHU L P,WEN W J,LI J Y,et al.Integrated data-driven power system transient stability monitoring and enhancement[J].IEEE Transactions on Power Systems,2024,39(1):1797-1809.
• [7]李永康，刘宝柱，胡俊杰.基于数据驱动与时域仿真融合的电力系统暂态稳定快速评估[J].电网技术，2023,47(11):4386-4396.LI Yongkang,LIU Baozhu,HU Junjie.Rapid evaluation of power system transient stability based on fusion of datadriven and time-domain simulation[J]. Power System Technology,2023,47(11):4386-4396.
• [8]BHUI P,SENROY N.Real-time prediction and control of transient stability using transient energy function[J].IEEE Transactions on Power Systems,2017,32(2):923-934.
• [9]WANG H Y,CHEN Q F,ZHANG B H.Transient stability assessment combined model framework based on costsensitive method[J]. IET Generation,Transmission&Distribution,2020,14(12):2256-2262.
• [10]SHAO Z H,WANG Q C,CAO Y Z,et al.A novel datadriven LSTM-SAF model for power systems transient stability assessment[J].IEEE Transactions on Industrial Informatics,2024,20(7):9083-9097.
• [11]叶林，施媛媛，王启亨，等.面向暂态分析的分布式光伏集群多步分群与等值建模[J].电力系统自动化，2023,47(14):72-81.YE Lin,SHI Yuanyuan,WANG Qiheng,et al.Multi-step grouping and equivalent modeling of distributed photovoltaic clusters for transient analysis[J].Automation of Electric Power Systems,2023,47(14):72-81.
• [12]SHI Z T,YAO W,TANG Y,et al.Intelligent power system stability assessment and dominant instability mode identification using integrated active deep learning[J].IEEE Transactions on Neural Networks and Learning Systems,2024,35(7):9970-9984.
• [13]SHEN Y,PENG Y L,SHUAI Z K,et al. Hierarchical time-series assessment and control for transient stability enhancement in islanded microgrids[J]. IEEE Transactions on Smart Grid,2023,14(5):3362-3374.
• [14]管敏渊，姚瑛，吴圳宾，等.基于RBF神经网络的储能VSG控制策略优化[J].浙江电力，2024,43(3):55-64.GUAN Minyuan,YAO Ying,WU Zhenbin,et al.Optimization of energy storage VSG Control strategy based on RBF neural networks[J].Zhejiang Electric Power,2024,43(3):55-64.
• [15]任顺鑫，王怀远，李剑，等.主导模式引导的电力系统暂态稳定数据驱动评估方法[J/OL].中国电机工程学报，2024:1-13.(2024-04-23)[2024-09-27].https：//kns.cnki.net/kcms/detail/11.2107.tm.20240420.1802.003.html.REN Shunxin,WANG Huaiyuan,LI Jian,et al. Datadriven assessment method for transient stability of power system guided by dominant mode[J/OL].Proceedings of the CSEE,2024:1-13.(2024-04-23)[2024-09-27].https：//kns.cnki.net/kcms/detail/11.2107.tm.20240420.1802.003.html.
• [16]刘雨晴，刘曌，王小君，等.融合同步知识和时空信息的电力系统暂态稳定评估框架[J].电网技术，2025,49(6):2334-2346.LIU Yuqing,LIU Zhao,WANG Xiaojun,et al.Power system transient stability assessment framework based on fusion of synchronization knowledge and spatial-temporal information[J]. Power System Technology,2025,49(6):2334-2346..
• [17]齐航，任喆，李常刚，等.动态安全智能评估中故障位置特征表达的电气坐标距离保持[J].中国电机工程学报，2024,44(12):4615-4626.QI Hang,REN Zhe,LI Changgang,et al.Distance preservation of electrical coordinate for fault location feature representation in intelligent dynamic security assessment[J].Proceedings of the CSEE,2024,44(12):4615-4626.
• [18]黄思琪，李长城，康海鹏.计及输电线路开断时间的连锁故障快速阻断控制策略[J].电力系统自动化，2023,47(12):111-120.HUANG Siqi,LI Changcheng,KANG Haipeng. Fast blocking control strategy against cascading failures considering tripping time of transmission lines[J].Automation of Electric Power Systems,2023,47(12):111-120.
• [19]张建新，刘宇明，邱建，等.区域新能源并网暂态功角稳定分析与紧急控制策略优化[J].南方电网技术，2024,18(7):129-138.ZHANG Jianxin,LIU Yuming,QIU Jian,et al.Trainsient power angle stability analysis of regional new energy integration and coordinated control strategy[J]. Southern Power System Technology,2024,18(7):129-138.
• [20]YUE Z Y,LIU Y L,YU Y X,et al.Probabilistic transient stability assessment of power system considering wind power uncertainties and correlations[J].International Journal of Electrical Power&Energy Systems,2020,117:105649.
• [21]MORSHED M J.A nonlinear coordinated approach to enhance the transient stability of wind energy-based power systems[J]. IEEE/CAA Journal of Automatica Sinica,2020,7(4):1087-1097.
• [22]YUAN H L,XU Y,ZHANG C. Robustly coordinated generation dispatch and load shedding for power systems against transient instability under uncertain wind power[J].IEEE Transactions on Power Systems,2022,37(2):1032-1043.
• [23]程富豪，徐泰华，陈建军，等.基于顶点粒k步搜索和粗糙集的强连通分量挖掘算法[J].计算机科学，2022,49(8):97-107.CHENG Fuhao,XU Taihua,CHEN Jianjun,et al.Strongly connected components mining algorithm based on k-step search of vertex granule and rough set theory[J].Computer Science,2022,49(8):97-107.
• [24]韩金龙，袁枭添，江晗，等.基于状态反馈精确线性化的双馈异步风机最优控制策略[J].中国电机工程学报，2024,44(9):3508-3518.HAN Jinlong,YUAN Xiaotian,JIANG Han,et al.Optimal control of doubly fed induction generator based on feedback linearization[J].Proceedings of the CSEE,2024,44(9):3508-3518.
• [25]薛安成，吴雨，王子哲，等.次同步扰动下的双馈风机系统多频率响应分析[J].电网技术，2018,42(6):1804-1810.XUE Ancheng,WU Yu,WANG Zizhe,et al.Analysis of frequency response of DFIG system under subsynchronous disturbance[J].Power System Technology,2018,42(6):1804-1810.
• [26]MARQUES G D,IACCHETTI M F. DFIG topologies for DC networks:a review on control and design features[J]. IEEE Transactions on Power Electronics,2019,34(2):1299-1316.
• [27]CHEN C,LI K L,WEI W,et al.Hierarchical graph neural networks for few-shot learning[J].IEEE Transactions on Circuits and Systems for Video Technology,2022,32(1):240-252.