1.电动汽车电网接入技术国家地方联合工程实验室(山东大学),山东省济南市 250061
2.山东大学计算机科学与技术学院,山东省青岛市 266237
3.山东大学电气工程学院,山东省济南市 250061
左建辉(1999—),男,硕士研究生,主要研究方向:电力系统暂态电压稳定性分析。E-mail:zuojianhuisdu@gmail.com
石访(1982—),男,通信作者,博士,副教授,主要研究方向:电力系统稳定分析与控制、电力系统同步相量测量技术与应用。E-mail:shifang@sdu.edu.cn
宋雪萌(1990—),女,副教授,博士生导师,主要研究方向:信息检索和社交媒体分析。E-mail:sxmustc@gmail.com
收稿:2024-09-22,
修回:2025-04-21,
网络首发:2025-06-16,
纸质出版:2026-01-25
移动端阅览
左建辉,石访,宋雪萌等.主动学习与自训练相结合的电网暂态电压稳定评估方法[J].电力系统自动化,2026,50(2):177-187.
ZUO Jianhui,SHI Fang,SONG Xuemeng,et al.Assessment Method for Transient Voltage Stability of Power Grids Based on Combined Active Learning and Self-training[J].Automation of Electric Power Systems,2026,50(2):177-187.
左建辉,石访,宋雪萌等.主动学习与自训练相结合的电网暂态电压稳定评估方法[J].电力系统自动化,2026,50(2):177-187. DOI: 10.7500/AEPS20240922002.
ZUO Jianhui,SHI Fang,SONG Xuemeng,et al.Assessment Method for Transient Voltage Stability of Power Grids Based on Combined Active Learning and Self-training[J].Automation of Electric Power Systems,2026,50(2):177-187. DOI: 10.7500/AEPS20240922002.
快速、准确地评估电网暂态电压稳定性对系统安全稳定运行具有重要意义。时域仿真法耗时长,难以满足实时评估需求;人工智能算法因模型训练和迁移的效率较低,难以满足实际应用需求。为此,提出主动学习与自训练相结合的电网暂态电压稳定评估方法。首先,在损失函数中引入对比损失指标,以提升暂态电压稳定分类模型性能。接着,采用主动学习策略筛选目标域中少量样本进行长时间尺度仿真,并精确标注电压稳定性标签,对模型参数进行初次微调。然后,应用调优后模型对目标域剩余无标签样本进行伪标签标注,并选择高置信度样本对模型参数进行二次微调,以充分挖掘目标域无标签样本价值、提升模型预测精度和迁移效率。最后,采用CEPRI-VC标准算例验证了所提方法在准确性和时效性方面优于传统方法。
Fast and accurate assessment of transient voltage stability after power grid disturbance is of great significance for the safe and stable operation of the system. The time-domain simulation method is time-consuming and difficult to meet the requirements of real-time assessment. Artificial intelligence algorithms
due to the low efficiency of model training and transfer
are difficult to meet the requirements of practical applications. To this end
an assessment method for transient voltage stability of power grids based on combined active learning and self-training is proposed. Firstly
a contrastive loss metric is introduced into the loss function to enhance the performance of the transient voltage stability classification model. Then
an active learning strategy is adopted to screen a small number of samples in the target domain for long-timescale simulation and precisely labels the voltage stability tags
and the initial fine-tuning of the model parameters is carried out. Secondly
the optimal fine-tuned model is applied to pseudo-label the remaining unlabeled samples in the target domain
and high-confidence samples are selected for the secondary fine-tuning of the model parameters
to fully explore the value of the unlabeled samples in the target domain
thus improving the prediction accuracy and transfer efficiency of the model. Finally
the CEPRI-VC standard cases are applied to verify that the proposed method is superior to the conventional methods in terms of accuracy and timeliness.
李晖 , 刘栋 , 姚丹阳 . 面向碳达峰碳中和目标的我国电力系统发展研判 [J]. 中国电机工程学报 , 2021 , 41 ( 18 ): 6245 - 6259 .
LI Hui , LIU Dong , YAO Danyang . Development assessment of China’s power system for carbon peaking and carbon neutrality targets [J]. Proceedings of the CSEE , 2021 , 41 ( 18 ): 6245 - 6259 .
周孝信 , 鲁宗相 , 刘应梅 , 等 . 中国未来电网的发展模式和关键技术 [J]. 中国电机工程学报 , 2014 , 34 ( 29 ): 4999 - 5008 .
ZHOU Xiaoxin , LU Zongxiang , LIU Yingmei , et al . Development models and key technologies of future grid in China [J]. Proceedings of the CSEE , 2014 , 34 ( 29 ): 4999 - 5008 .
杨金洲 , 李业成 , 熊鸿韬 , 等 . 新能源接入的受端电网暂态电压失稳高风险故障快速筛选 [J]. 电工技术学报 , 2024 , 39 ( 21 ): 6746 - 6758 .
YANG Jinzhou , LI Yecheng , XIONG Hongtao , et al . A fast screening method for the high-risk faults with transient voltage instability in receiving-end power grids interconnected with new energy [J]. Transactions of China Electrotechnical Society , 2024 , 39 ( 21 ): 6746 - 6758 .
薛安成 , 周健 , 刘瑞煌 , 等 . 采用多二元表判据的实用暂态电压稳定裕度指标研究 [J]. 中国电机工程学报 , 2018 , 38 ( 14 ): 4117 - 4125 .
XUE Ancheng , ZHOU Jian , LIU Ruihuang , et al . A new practical transient voltage stability margin index based on multiple-two-element notation criterion [J]. Proceedings of the CSEE , 2018 , 38 ( 14 ): 4117 - 4125 .
仲悟之 , 汤涌 . 电力系统微分代数方程模型的暂态电压稳定性分析 [J]. 中国电机工程学报 , 2010 , 30 ( 25 ): 10 - 16 .
ZHONG Wuzhi , TANG Yong . Transient voltage stability analysis of differential-algebra equation in power system [J]. Proceedings of the CSEE , 2010 , 30 ( 25 ): 10 - 16 .
甄永赞 , 阮程 . 基于代价敏感支持向量机和多变量决策树的分级自适应暂态电压稳定评估 [J]. 电网技术 , 2024 , 48 ( 2 ): 778 - 791 .
ZHEN Yongzan , RUAN Cheng . Hierarchical self-adaptation transient voltage stability assessment based on cost-sensitive SVM and multivariate decision tree [J]. Power System Technology , 2024 , 48 ( 2 ): 778 - 791 .
朱利鹏 , 陆超 , 孙元章 , 等 . 基于数据挖掘的区域暂态电压稳定评估 [J]. 电网技术 , 2015 , 39 ( 4 ): 1026 - 1032 .
ZHU Lipeng , LU Chao , SUN Yuanzhang , et al . Data mining based regional transient voltage stability assessment [J]. Power System Technology , 2015 , 39 ( 4 ): 1026 - 1032 .
李京 , 刘道伟 , 安军 , 等 . 基于强化学习理论的静态电压稳定裕度评估 [J]. 中国电机工程学报 , 2020 , 40 ( 16 ): 5136 - 5148 .
LI Jing , LIU Daowei , AN Jun , et al . Static voltage stability margin assessment based on reinforcement learning theory [J]. Proceedings of the CSEE , 2020 , 40 ( 16 ): 5136 - 5148 .
陈达 , 朱林 , 张健 , 等 . 基于卷积神经网络的暂态电压稳定评估及风险量化 [J]. 电力系统自动化 , 2021 , 45 ( 14 ): 65 - 71 .
CHEN Da , ZHU Lin , ZHANG Jian , et al . Transient voltage stability assessment and risk quantification based on convolutional neural network [J]. Automation of Electric Power Systems , 2021 , 45 ( 14 ): 65 - 71 .
季佳伸 , 吴俊勇 , 王彦博 , 等 . 基于深度残差网络的电力系统暂态电压稳定评估 [J]. 电网技术 , 2022 , 46 ( 7 ): 2500 - 2511 .
JI Jiashen , WU Junyong , WANG Yanbo , et al . Power system transient voltage stability assessment based on deep residual network [J]. Power System Technology , 2022 , 46 ( 7 ): 2500 - 2511 .
刘颂凯 , 崔梓琪 , 杨超 , 等 . 基于时空注意机制与LSTM的暂态电压稳定评估 [J]. 电力系统及其自动化学报 , 2024 , 36 ( 6 ): 82 - 91 .
LIU Songkai , CUI Ziqi , YANG Chao , et al . Transient voltage stability assessment based on spatial-temporal attention mechanism and LSTM [J]. Proceedings of the CSU-EPSA , 2024 , 36 ( 6 ): 82 - 91 .
张哲 , 秦博宇 , 高鑫 , 等 . 融合注意力机制和卷积神经网络的电网暂态电压稳定评估及可解释性分析 [J]. 电网技术 , 2024 , 48 ( 11 ): 4648 - 4657 .
ZHANG Zhe , QIN Boyu , GAO Xin , et al . Transient voltage stability assessment of power grids and explainability analysis based on attention mechanism and convolutional neural networks [J]. Power System Technology , 2024 , 48 ( 11 ): 4648 - 4657 .
REN J Y , CHEN J F , LI B Y , et al . A method for power system transient stability assessment based on transfer learning [C]// 2020 IEEE Power & Energy Society General Meeting , August 2-6 , 2020 , Montreal, Canada : 1 - 5 .
PAN S J , YANG Q . A survey on transfer learning [J]. IEEE Transactions on Knowledge and Data Engineering , 2010 , 22 ( 10 ): 1345 - 1359 .
LI Y , ZHANG S T , LI Y Z , et al . PMU measurements-based short-term voltage stability assessment of power systems via deep transfer learning [J]. IEEE Transactions on Instrumentation and Measurement , 2023 , 72 : 2526111 .
王渝红 , 何其多 , 郑宗生 , 等 . 基于条件生成对抗网络与迁移学习的暂态电压稳定超前判别 [J]. 电力自动化设备 , 2025 , 45 ( 2 ): 159 - 166 .
WANG Yuhong , HE Qiduo , ZHENG Zongsheng , et al . Early prediction of transient voltage stability based on conditional generative adversarial networks and transfer learning [J]. Electric Power Automation Equipment , 2025 , 45 ( 2 ): 159 - 166 .
FU Y F , ZHU X Q , LI B . A survey on instance selection for active learning [J]. Knowledge and Information Systems , 2013 , 35 ( 2 ): 249 - 283 .
陈阳 , 陆超 , 刘迪 , 等 . 多故障场景下基于主动学习的暂态电压安全评估与安全裕度估计 [J]. 武汉大学学报(工学版) , 2023 , 56 ( 11 ): 1336 - 1346 .
CHEN Yang , LU Chao , LIU Di , et al . Transient voltage security assessment and security margin estimation based on active learning under multiple fault scenarios [J]. Journal of Wuhan University (Engineering Edition) , 2023 , 56 ( 11 ): 1336 - 1346 .
LEE D H . Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks [C]// Workshop on Challenges in Representation Learning , June 21-22 , 2013 , Atlanta, USA : 1 - 8 .
KHOSLA P , TETERWAK P , WANG C , et al . Supervised contrastive learning [EB/OL]. [ 2024-12-01 ]. https://arxiv.org/abs/2004.11362v5 https://arxiv.org/abs/2004.11362v5 .
ABBASS M J , LIS R , REBIZANT W . A predictive model using long short-time memory (LSTM) technique for power system voltage stability [J]. Applied Sciences , 2024 , 14 ( 16 ): 7279 .
姜涛 , 董雨 , 王长江 , 等 . 基于图卷积和双向长短期记忆网络的受端电力系统暂态电压稳定评估 [J]. 电网技术 , 2023 , 47 ( 12 ): 4937 - 4951 .
JIANG Tao , DONG Yu , WANG Changjiang , et al . Transient voltage stability assessment of receiving-end power system based on graph convolution and bidirectional long/short-term memory networks [J]. Power System Technology , 2023 , 47 ( 12 ): 4937 - 4951 .
CHEN Y C , XIE H P . Transient voltage stability assessment based on an improved TCN-BiLSTM framework [C]// 2022 IEEE 5th International Electrical and Energy Conference , May 27-29 , 2022 , Nangjing, China : 4420 - 4426 .
电力系统电压稳定评价导则 : GB/T 40615—2021 [S]. 北京 : 中国标准出版社 , 2021 .
Guides of power system voltage stability evaluation : GB/T 40615—2021 [S]. Beijing : Standards Press of China , 2021 .
LI Baoluo . CSEE-Benchmark [EB/OL]. [ 2024-12-01 ]. https://github.com/lbl-hub/CSEE-Benchmark/tree/main/CSEE-VC-88 https://github.com/lbl-hub/CSEE-Benchmark/tree/main/CSEE-VC-88 .
CAI G W , CAO Z C , LIU C , et al . Online assessment of short-term voltage stability based on hybrid model and data-driven approach [J]. International Journal of Electrical Power & Energy Systems , 2024 , 158 : 109930 .
赵兵 , 徐式蕴 , 兰天楷 , 等 . 新型电力系统标准算例(三):电压稳定CSEE-VS [J]. 中国电机工程学报 , 2024 , 44 ( 21 ): 8353 - 8364 .
ZHAO Bing , XU Shiyun , LAN Tiankai , et al . Benchmark for AC-DC hybrid system with high penetration of renewables (Ⅲ): voltage stability benchmark CSEE-VS [J]. Proceedings of the CSEE , 2024 , 44 ( 21 ): 8353 - 8364 .
0
浏览量
0
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621