基于时序特征选择与改进MSPCA算法的电网暂态稳定态势智能评估

鲁广明; 张璐路; 马晶; 魏亚威; 李宏强; 杨慧彪

鲁广明,张璐路,马晶,魏亚威,李宏强,杨慧彪.基于时序特征选择与改进MSPCA算法的电网暂态稳定态势智能评估[J].电测与仪表,2023,60(6):125-133.
Lu Guangming,Zhang Lulu,Ma Jing,Wei Yawei,Li Hongqiang,Yang Huibiao.Intelligent transient stability situation assessment of power system based on time-series feature selection and improved MSPCA algorithm[J].Electrical Measurement & Instrumentation,2023,60(6):125-133.

基于时序特征选择与改进MSPCA算法的电网暂态稳定态势智能评估

Intelligent transient stability situation assessment of power system based on time-series feature selection and improved MSPCA algorithm

DOI：10.19753/j.issn1001-1390.2023.06.018

中文关键词: 电网暂态稳定态势评估时序特征选择邻域互信息特征贡献率改进MSPCA算法

英文关键词:power system stability situation assessment, time-series feature selection, neighborhood mutual information, feature contribution rate, improved MSPCA algorithm

基金项目:国家电网有限公司总部管理科技项目资助，项目名称《跨区电网源荷不确定性安全风险在线评估与智能防御技术》（5100-202135022A-0-0-00）

作者中文名	作者英文名	单位
鲁广明	Lu Guangming	中国电力科学研究院有限公司
张璐路	Zhang Lulu	中国电力科学研究院有限公司
马晶	Ma Jing	中国电力科学研究院有限公司
魏亚威	Wei Yawei	中国电力科学研究院有限公司
李宏强	Li Hongqiang	国网宁夏电力有限公司电力科学研究院
杨慧彪	Yang Huibiao	国网宁夏电力有限公司电力科学研究院

摘要点击次数: 1228

中文摘要:

在充分利用电网海量历史运行数据及大量仿真分析数据评估暂态稳定态势过程中，恰当的选择与稳定特征以及提取非正常态势关键影响特征是实现电网暂态稳定态势评估的基础。文中提出了一种基于时序特征选择的暂态稳定态势智能评估方法。首先给出了基于未来运行点的邻域样本在线生成方法及稳定态势等级描述，选择输电断面作为主要特征；其次基于时序邻域信息度量算法，依据累积贡献率对特征降序排列，并采用基于邻域互信息的计算并伴随基于SVM的特征子集搜索实现冗余特征的剔除，形成稳定特征子集；在应用电网稳定特征子集进行态势评估场景中，采用改进的多尺度主元分析法对稳定相关信息进行提取，通过特征贡献率排序实现非正常态势关键影响特征识别。最后结合IEEE 39节点算例系统，仿真结果验证了文中所提方法的有效性。

英文摘要:

In the process of making full use of the massive historical operation data and simulation analysis data of large power grid, the proper selection of features closely related to stability and the extraction of key factors affecting the abnormal stability situation are the basis. In this paper, an intelligent stability situation assessment based on time series feature selection is proposed. Firstly, the online generation method of neighborhood samples based on the future operation section and the stability situation levels are given, and then the transmission section is determined as the main features; Secondly, with the support of the neighborhood information measurement algorithm of the power grid time series data, the features are arranged in descending order according to the cumulative contribution rate, and then the redundant features are eliminated by the calculation based on the temporal neighborhood mutual information and the feature subset search based on SVM to form a stable feature subset; In the scenario of applying the feature subset, the extraction of Stability-Related Information based on MSPCA algorithm is adapted, and the identification of key features is realized through the ranking of SRI contribution rate. Finally, the simulation results of IEEE 39-bus verify the effectiveness of the proposed methods.

查看全文查看/发表评论下载PDF阅读器

关闭