基于主动学习的电力系统暂态稳定评估方法

谢培元; 袁文; 刘永刚; 潘飞来; 叶文浩; 杨俊

谢培元,袁文,刘永刚,潘飞来,叶文浩,杨俊.基于主动学习的电力系统暂态稳定评估方法[J].电测与仪表,2021,58(5):86-91.
Xie Peiyuan,Yuan Wen,Liu Yonggang,Pan Feilai,Ye Wenhao,Yang Jun.Transient stability assessment method in power system based on active learning[J].Electrical Measurement & Instrumentation,2021,58(5):86-91.

基于主动学习的电力系统暂态稳定评估方法

Transient stability assessment method in power system based on active learning

DOI：10.19753/j.issn1001-1390.2021.05.012

中文关键词: 泛在电力物联网概念相量测量单元主动学习暂态稳定评估

英文关键词:concept of ubiquitous power internet of things, phasor measurement unit, active learning, transient stability assessment

基金项目:

作者中文名	作者英文名	单位
谢培元	Xie Peiyuan	国网湖南省电力公司，长沙 410007
袁文	Yuan Wen	国网常德供电分公司，湖南常德 415001
刘永刚	Liu Yonggang	国网湖南省电力公司，长沙 410007
潘飞来	Pan Feilai	国网湖南省电力公司，长沙 410007
叶文浩	Ye Wenhao	国网湖南省电力公司，长沙 410007
杨俊	Yang Jun	国网长沙供电分公司，长沙 410015

摘要点击次数: 2850

中文摘要:

随着泛在电力物联网概念的提出，暂态稳定在电力系统运行控制中扮演着越来越重要的角色。由于相量测量单元（Phasor Measurement Unit，PMU）的广泛配置，基于机器学习的暂态稳定实时评估方法展现出了巨大的发展潜力。针对这类方法在应用中离线训练数据生成耗时及造成的难以在网架发生变化后快速更新模型的问题，论文提出了一种基于主动学习的电力系统暂态稳定评估方法。考虑不同运行方式、不同故障下进行短时间仿真（仿真至故障切除时刻）生成无标注样本；随机选取一部分样本进行长时间仿真以标注这些样本的稳定状态，并进一步训练基于支持向量机的暂态稳定评估模型；最后循环选择剩余未标注样本中信息熵较高的部分数据进行标注对模型重新训练，直至模型准确率不再变化。在新英格兰10机39节点测试电力系统的仿真表明，论文提出的方法能够有效降低离线仿真的时间，大大提高评估模型部署的效率，并对广域噪声具有鲁棒性。

英文摘要:

With the concept of ubiquitous power internet of things, the transient stability plays an increasingly important role in the operation and control of power system. Due to the extensive configuration of the phasor measurement unit (PMU), the real-time evaluation method of machine-based transient stability shows great potential for development. Aiming at the problem that data generation of the offline training is time-consuming and it is difficult to update the model quickly after the grid changes, this paper proposes a power system transient stability assessment method based on active learning. Firstly, implementing short-time simulations (simulation to fault clearing time) to generate unlabeled samples in different kind of operations and faults; and then, randomly select a part of samples for long-term simulation to mark these samples; Then, a part of samples are randomly selected for long-term simulation to be labeled with transient stability status, and support vector machine is further trained to build the transient stability assessment model; Finally, the data with high information entropy in the remaining unlabeled samples is re-trained until the model accuracy does not change. The simulation of the New England 10-machine 39-bus test power system shows that the proposed method can effectively reduce the time of offline simulation, which greatly improves the efficiency of model configuration, and it is robust to wide-area noise.

查看全文查看/发表评论下载PDF阅读器

关闭