中国电机工程学报2018，Vol.38Issue(3)：735-743,后插8,10.DOI:10.13334/j.0258-8013.pcsee.162436
基于深度置信网络的电力系统暂态稳定评估方法
A Method for Power System Transient Stability Assessment Based on Deep Belief Networks
朱乔木 1党杰 2陈金富 1徐友平 2李银红 1段献忠1
作者信息
- 1. 强电磁工程与新技术国家重点实验室(华中科技大学),湖北省武汉市 430074
- 2. 华中电网有限公司,湖北省武汉市 430077
- 折叠
摘要
Abstract
To further improve the assessment accuracy of transient stability assessment (TSA) of power system, deep learning method was introduced into TSA for the first time, and a novel method for TSA based on deep belief networks (DBN) was proposed. A group of 32-dimensional original features reflecting status of power system's transient stability were employed as input, and the stability results were used as output of DBN model. The parameters of DBN model were firstly initialized by unsupervised learning method with no-label samples, and then fine-tuned by supervised learning method with labeled samples. The model is able to take the advantage of feature extraction of deep structure, and can enhance its generation ability by a large amount of no-label samples. Experiment results on New England 39-bus system demonstrate that the proposed method is more accurate than common TSA methods, and that the method performs very well with insufficient training samples or redundant features.关键词
电力系统/暂态稳定评估/深度学习/深度置信网络/机器学习Key words
power system/transient stability assessment (TSA)/deep learning/deep belief networks (DBN)/machine learning分类
信息技术与安全科学引用本文复制引用
朱乔木,党杰,陈金富,徐友平,李银红,段献忠..基于深度置信网络的电力系统暂态稳定评估方法[J].中国电机工程学报,2018,38(3):735-743,后插8,10.
