半月刊

ISSN 1000-1026

CN 32-1180/TP

+高级检索 English
基于集成深度置信网络的精细化电力系统暂态稳定评估
作者:
作者单位:

北京交通大学电气工程学院, 北京市 100044

作者简介:

李宝琴(1996—),女,博士研究生,主要研究方向:人工智能、电力系统暂态稳定。E-mail: 18121454 @bjtu.edu.cn

通讯作者:

吴俊勇(1966—),男,通信作者,博士,教授,博士生导师,主要研究方向:电力系统分析与控制、智能电网、全球能源互联网。E-mail: wujy@bjtu.edu.cn

基金项目:

国家重点研发计划资助项目(2018YFB0904500);国家自然科学基金资助项目(51577009)。


Refined Transient Stability Evaluation for Power System Based on Ensemble Deep Belief Network
Author:
Affiliation:

School of Electrical Engineering, Beijing Jiaotong University, Beijing 100044, China

Fund Project:

This work is supported by National Key R&D Program of China (No. 2018YFB0904500)and National Natural Science Foundation of China (No. 51577009).

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
    摘要:

    为了进一步提高电力系统暂态稳定的预测精度及给出更精细化的评估结果,将深度学习与电力系统暂态稳定相结合,根据故障切除后发电机功角“轨迹簇”特征,提出一种基于集成不同结构的深度置信网络(DBN)的精细化电力系统暂态稳定评估模型。该模型的基分类器DBN能够有效地利用深层架构所具有的特征提取能力,充分挖掘出输入特征与暂态稳定评估结果之间的非线性映射关系。在新英格兰10机39节点系统上的实验结果表明,该方法不仅优于浅层学习框架,也比部分深度学习模型的性能更加优越。除此之外,该集成DBN算法不仅有较高的预测精度,而且可以有效地评估系统的稳定裕度和不稳定程度等级;在部分同步相量测量装置信息缺失以及含有噪声时,表现出较强的鲁棒性。

    Abstract:

    In order to further improve the prediction accuracy of transient stability for power system and give more refined evaluation results, the deep learning is combined with the transient stability of power system. A refined evaluation model of transient stability for power system based on ensemble deep belief network (DBN) with different structures is proposed based on the characteristics of the generator power angle "trajectory cluster" after fault removal. The base classifier DBN of the model can effectively utilize the feature extraction ability of the deep architecture and fully exploit the nonlinear mapping relationship between the input features and the evaluation results of transient stability. Experimental results on the New England 10-machine 39-node system show that this method is not only superior to the shallow learning framework, but also superior to the partial deep learning model. In addition, the ensemble DBN algorithm not only has higher prediction accuracy, but also can effectively evaluate the stability margin and instability level of the system. It shows strong robustness when some information of phasor measurement unit (PMU) is missing and contains noise.

    表 1 混淆矩阵Table 1 Confusion matrix
    表 3 不同基分类器DBN的结构Table 3 Structure of different base classifier DBNs
    表 8 Table 8
    表 9 Table 9
    表 4 不同分类器性能比较Table 4 Performance comparison of different classifiers
    表 7 Table 7
    表 5 缺失多台发电机信息时的集合组成Table 5 Set composition in absence of multiple generator information
    表 6 暂态稳定多级指标划分Table 6 Multilevel index division of transient stability
    表 2 样本集合的分类Table 2 Classification of sample sets
    图1 DBN的网络结构Fig.1 Network structure of DBN
    图2 集成DBN预测模型Fig.2 Prediction model of ensemble DBN
    图3 集成DBN暂态稳定评估流程Fig.3 Evaluation process of transient stability for ensemble DBN
    图4 发电机信息缺失时模型的预测结果Fig.4 Prediction results of model when generator information is missing
    图5 含噪声时浅层学习性能比较Fig.5 Comparison of shallow learning performance with noise
    图6 测试集中失稳样本的失稳时间分布直方图Fig.6 Histograms of instable time distribution of instable samples in test set
    图 特征之间相关性热力图Fig. Correlation thermal maps between features
    参考文献
    相似文献
    引证文献
引用本文

李宝琴,吴俊勇,邵美阳,等.基于集成深度置信网络的精细化电力系统暂态稳定评估[J].电力系统自动化,2020,44(6):17-26. DOI:10.7500/AEPS20190528009.
LI Baoqin,WU Junyong,SHAO Meiyang,et al.Refined Transient Stability Evaluation for Power System Based on Ensemble Deep Belief Network[J].Automation of Electric Power Systems,2020,44(6):17-26. DOI:10.7500/AEPS20190528009.

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2019-05-28
  • 最后修改日期:2019-08-26
  • 录用日期:
  • 在线发布日期: 2020-03-21
  • 出版日期: