文章基本信息

标题：Transient Rotor Angle Stability Prediction Based on Deep Belief Network and Long Short-term Memory Network
本地全文：下载
作者：Li Liu ; Yong Li ; Yijia Cao 等
期刊名称：IFAC PapersOnLine
印刷版ISSN：2405-8963
出版年度：2019
卷号：52
期号：4
页码：176-181
DOI：10.1016/j.ifacol.2019.08.175
语种：English
出版社：Elsevier
摘要：AbstractIn this paper, a transient stability prediction method based on deep belief network (DBN) and long short-term memory (LSTM) network is proposed. DBN is utilized to embed the original transient stability data into a low-dimensional representation space and assess transient stability preliminarily. Owing to the good performance of LSTM networks in extracting the features of time series for a longtime span, it is utilized to predict generator rotor angle trajectory of instability samples, which can identify the unstable generator in advance. The proposed method is validated by IEEE New England 39-bus system. Simulation results show that the proposed method has the merits of quickness and accuracy criteria and can provide guidelines for online monitoring of power system stability.
关键词：KeywordsTransient stability assessmentDBNLSTMrotor angle stability