• CSCD核心库收录期刊
  • 中文核心期刊
  • 中国科技核心期刊

电力建设 ›› 2018, Vol. 39 ›› Issue (2): 103-.doi: 10.3969/j.issn.1000-7229.2018.02.013

• 智能电网 • 上一篇    下一篇

  基于深度学习的电力系统暂态稳定评估方法 

  周悦1,谭本东2,李淼1,杨旋1,周强明1,张振兴1,谭敏1,杨军2 

 
  

  1.  (1. 国网湖北省电力公司, 武汉市 430077;2. 武汉大学电气工程学院,武汉市 430072) 
     
  • 出版日期:2018-02-01
  • 作者简介:周悦(1985),男,硕士,工程师,主要研究方向为电网调度与运行; 谭本东(1994),男,通信作者,硕士研究生,研究方向为大数据在电力系统中的应用; 李淼(1976),女,博士,高级工程师,主要研究方向为电网调度与运行; 杨旋(1979),男,本科,高级工程师,主要研究方向为电网调度与运行; 周强明(1984),男,硕士,高级工程师,主要研究方向为电网调度与运行; 张振兴(1975),男,本科,中级工程师,主要研究方向为电网调度与运行; 谭敏(1982),男,本科,中级工程师,主要研究方向为电网调度与运行; 杨军(1977),男,教授,博士生导师,主要研究方向为电力系统运行与控制。
  • 基金资助:
       基金项目: 国家自然科学基金项目(51277135);国家电网公司科技项目(521500160011) 
     

 Transient Stability Assessment of Power System Based on   Deep Learning Technology 

 ZHOU Yue1, TAN Bendong2, LI Miao1, YANG Xuan1, ZHOU Qiangming1,  ZHANG Zhenxing1, TAN Min1, YANG Jun2 

 
  

  1.  (1.State Grid Hubei Electric Power Company, Wuhan  430077, China;2.School of Electrical Engineering, Wuhan University, Wuhan 430072, China) 
     
  • Online:2018-02-01
  • Supported by:
     Project supported by National Natural Science Foundation of China(51277135);Science and Technology Project of State Grid Corporation of China(521500160011) 
     

摘要:  摘要:在机器学习领域,暂态稳定评估问题被定义为通过大量故障样本来估计稳定边界的二分类问题。该文提出了一种深度学习方法来解决这个二分类问题。该方法包含4个步骤:首先,利用样本数据构建原始输入特征来描述电力系统动态特性;然后,采用变分自动编码器(variational auto-encoders ,VAE)对原始输入特征进行无监督学习实现特征抽取,从而获得高阶特征;之后,对卷积神经网络(convolution neural network ,CNN)进行有监督学习训练得到高阶特征与电力系统暂态稳定性之间的映射关系;最后,将训练得到的模型应用于电力系统在线暂态稳定评估。在新英格兰39节点测试电力系统的仿真试验表明,所提出的暂态稳定评估(transient stability assessment,TSA)模型具有评估精度高、不稳定样本评估错误率低、抗噪声干扰能力强的特点,适合基于广域测量信息的准实时在线暂态稳定评估。 

 

关键词:  , KEYWORDS: deep learning, variational auto-encoders (VAE), high-order features, convolution neural network (CNN), transient stability assessment (TSA), machine learning, unsupervised learning  ,  ,

Abstract:  ABSTRACT: In the field of machine learning, transient stability assessment can be considered as a two-class problem of estimating the stability boundary through large number of fault samples. This paper proposes a method of deep learning to solve this problem. The method consists of four stages: firstly, using samples to construct the original input feature for describing the dynamic characteristics of the power system;secondly, variational auto-encoders (VAE) is used to perform unsupervised learning on the original input feature to obtain high-order features;thirdly, the supervised training of convolution neural network (CNN) is carried out to obtain the relationship between high order characteristic and transient stability of power system;finally, the model is applied to the transient stability assessment of power system. Simulation on the New England 39-bus test system shows that the proposed approach has high accuracy, rare misclassification of unstable sample and excellent robustness with noise for transient stability assessment (TSA). Therefore, it is suitable for quasi-real-time online transient stability assessment based on wide-area measurement information.

 

Key words:

 

中图分类号: