| 388 | 2 | 645 |
| 下载次数 | 被引频次 | 阅读次数 |
针对电气运行数据在量测和传输过程中可能出现缺失，导致电力系统暂态稳定评估模型性能下降的问题，提出一种基于缺失数据插补和改进集成策略的暂态稳定评估方法。首先，通过图循环插补网络对电力系统的拓扑结构进行显式建模，学习特征间潜在的时空联系，构建缺失数据插补模型，并基于插补效果生成像素点可信度矩阵和特征值可信度矩阵；其次，利用改进的堆叠方法和闭式连续时间神经网络构建集成评估模型，同时将可信度矩阵融合到该评估模型的训练和应用中；最后，引入时间自适应评估方法以缓解插补模型和评估模型同时应用导致的计算压力。新英格兰39节点电力系统算例结果表明，所提方法具有较强的鲁棒性，能够在多种数据缺失的情况下保持较高评估水准。
Abstract：A transient stability assessment method based on missing data imputation and an improved ensemble strategy is proposed to address the issue of decline in the performance of a power system transient stability assessment model due to the potential loss of electrical operation data during the measurement and transmission processes. First,the topological structure of the power system is explicitly modeled by means of a graph recurrent imputation network,the potential spatio-temporal connection between features is learned,and a missing data imputation model is constructed. In addition,a pixel reliability matrix and a feature reliability matrix are generated based on the imputation performance. Second,an ensemble assessment model is constructed based on an improved stacking method and a closed-form continuous-time neural network. Meanwhile,the reliability matrixes are integrated into the training and application processes of this assessment model. Finally,a time adaptive assessment method is introduced to alleviate the computational pressure caused by the simultaneous application of the imputation and assessment models. The specific results of a New England 39-node power system show that the proposed method has strong robustness and maintains a high assessment level in the case of multiple types of data missing.
[1]周惠怡，刘颂凯，张磊，等（Zhou Huiyi,Liu Songkai,Zhang Lei,et al）.考虑误分类约束的电力系统暂态稳定评估（Transient stability assessment for power system considering misclassification constraints)[J].电力系统及其自动化学报（Proceedings of the CSU-EPSA),2022,34(6):71-78.
[2]范士雄，赵泽宁，郭剑波，等（Fan Shixiong,Zhao Zening,Guo Jianbo,et al）.数据驱动的电力系统暂态稳定评估方法综述（Review on data-driven power system transient stability assessment technology)[J].中国电机工程学报（Proceedings of the CSEE),2024,44(9):3408-3429.
[3]Zhou Yanzhen,Guo Qinglai,Sun Hongbin,et al.A novel data-driven approach for transient stability prediction of power systems considering the operational variability[J].International Journal of Electrical Power and Energy Systems,2019,107:379-394.
[4]Huang Jiyu,Guan Lin,Su Yinsheng,et al.Recurrent graph convolutional network-based multi-task transient stability assessment framework in power system[J].IEEEAccess,2020,8:93283-93296.
[5]Zhu Lipeng,Hill D J.Cost-effective bad synchrophasor data detection based on unsupervised time-series data analytic[J].IEEE Internet of Things Journal,2021,8(3):2027-2039.
[6]Yu James J Q,Lam Albert Y S,Hill D J,et al.Delay aware power system synchrophasor recovery and prediction framework[J].IEEE Transactions on Smart Grid,2019,10(4):3732-3742.
[7]Guo Xiaolong,Zhu Shijia,Yang Zhiwei,et al.Consecutive missing data recovery method based on long-short term memory network[C]//3rd Asia Energy and Electrical Engineering Symposium.Chengdu,China,2021:988-992.
[8]Ren Chao,Xu Yan.A fully data-driven method based on generative adversarial networks for power system dynamic security assessment with missing data[J].IEEE Transactions on Power Systems,2019,34(6):5044-5052.
[9]Fang Jiashu,Zheng Le,Liu Chongru.A novel method for missing data reconstruction in smart grid using generative adversarial networks[J].IEEE Transactions on Industrial Informatics,2024,20(3):4408-4417.
[10]杜一星，胡志坚，陈纬楠，等（Du Yixing,Hu Zhijian,Chen Weinan,et al）.基于改进CatBoost的电力系统暂态稳定评估方法（Transient stability assessment method of power system based on improved CatBoost)[J].电力自动化设备（Electric Power Automation Equipment),2021,41(12):115-122.
[11]谭本东，杨军，刘源，等（Tan Bendong,Yang Jun,Liu Yuan,et al）.考虑数据缺失的电力系统暂态稳定自适应集成评估方法（Adaptive integrated assessment method for transient stability of power system considering PMU data missing)[J].电力系统自动化（Automation of Electric Power Systems),2021,45(23):68-75.
[12]周生存，罗毅，易煊承，等（Zhou Shengcun,Lou Yi,Yi Xuancheng,et al）.考虑数据缺失的图注意力网络暂态稳定评估（Transient stability assessment of graph attention networks considering data missing)[J].中国电力（Electric Power),2024,57(5):157-167.
[13]Cini A,Marisca I,Alippi C.Filling the G_AP_S:multivariate time series imputation by graph neural networks[C]//10th International Conference on Learning Representations.Vienna,Austria,2022.
[14]He Miao,Vittal V,Zhang Junshan.Online dynamic security assessment with missing PMU measurements:A data mining approach[J].IEEE Transactions on Power Systems,2013,28(2):1969-1977.
[15]Zhang Yuchen,Xu Yan,Zhang Rui,et al.A missing-data tolerant method for data-driven short-term voltage stability assessment of power systems[J].IEEE Transactions on Smart Grid,2018,10(5):5663-5674.
[16]Chakrabarti S,Kyriakides E.Optimal placement of phasor measurement units for power system observability[J].IEEE Transactions on Power Systems,2008,23(3):1433-1440.
[17]Hasani R,Lechner M,Amini A,et al.Closed-form continuous-time neural networks[J].Nature Machine Intelligence,2022,4(11):992-1003.
[18]Hou Jinxiu,Xie Chang,Wang Tianyue,et al.Power system transient stability assessment based on voltage phasor and convolution neural network[C]//2nd IEEE International Conference on Energy Internet.Beijing,China,2018:247-251.
[19]Li Xin,Liu Chenkai,Guo Panfeng,et al.Deep learningbased transient stability assessment framework for largescale modern power system[J].International Journal of Electrical Power and Energy Systems,2022,139:108010.
[20]Miao Xiaoye,Wu Yangyang,Wang Jun,et al.Generative semi-supervised learning for multivariate time series imputation[C]//35th AAAI conference on Artificial Intelligence.Online,2021,10B:8983-8991.
[21]Zhang Rui,Xu Yan,Dong Zhaoyang,et al.Post-disturbance transient stability assessment of power systems by a self-adaptive intelligent system[J].IET Generation,Transmission and Distribution,2015,9(3):296-305.
[22]Li Xin,Yang Zeguo,Guo Panfeng,et al.An intelligent transient stability assessment framework with continual learning ability[J].IEEE Transactions on Industrial Informatics,2021,17(12):8131-8141.
[23]Yu James J Q,Hill D J,Lam A Y S,et al.Intelligent timeadaptive transient stability assessment system[J].IEEETransactions on Power Systems,2018,33(1):1049-1058.
基本信息:
DOI：10.19635/j.cnki.csu-epsa.001525
中图分类号:TM712
引用信息:
[1]李欣,吴凌霄,李新宇,等.基于缺失数据插补和改进集成策略的电力系统暂态稳定评估[J].电力系统及其自动化学报,2025,37(08):38-48.DOI:10.19635/j.cnki.csu-epsa.001525.
基金信息:
国家自然科学基金资助项目（52107107）
2024-07-16
2024
2024-08-27
2025-08-19
2025
2
2024-09-09
2024-09-09
2024-09-09