电网技术2017，Vol.41Issue(10)：3140-3146,7.DOI:10.13335/j.1000-3673.pst.2017.1889
基于深度学习的电力系统故障后暂态稳定评估研究
Research on Power System Transient Stability Assessment Based on Deep Learning of Big Data Technique
摘要
Abstract
In order to maintain the stable operation of power system, it is important to assess transient stability quickly and accurately. However, traditional methods cannot satisfy quickness and accuracy simultaneously. With big data technique, a deep learning based transient stability assessment method has been proposed in this paper. Firstly, the stability rule learned by machine learning method is interpreted as the stability region boundary. Then the deep belief network is utilized to map the original feature space to a representation space, where the stable cases can be linearly separated from the unstable cases. Finally, simulations in a province power system have validated the proposed algorithm. The proposed method can provide new directions to online transient stability assessment for its quickness and accuracy.关键词
暂态稳定评估/稳定域/深度置信网络/深度学习/大数据技术Key words
transient stability assessment/stability region/deep belief network/deep learning/big data technique分类
信息技术与安全科学引用本文复制引用
胡伟,郑乐,闵勇,董昱,余锐,王磊..基于深度学习的电力系统故障后暂态稳定评估研究[J].电网技术,2017,41(10):3140-3146,7.基金项目
国家电网公司科技项目 （）
清华大学电力系统国家重点实验自主课题(SKLD16Z08).Project Supported by Science and Technology Project of State Grid Corporation of China （SKLD16Z08）
Science and Technology Project of State Key Lab of Power System of Tsinghua University (SKLD16Z08). （SKLD16Z08）
