• 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 ›› 2016, Vol. 37 ›› Issue (12): 96-.doi: 10.3969/j.issn.1000-7229.2016.12.013

• 输配电技术 • 上一篇    下一篇

 改进Sammon映射算法在分析暂态稳定评估输入特征有效性中的应用

 

 
张春1, 田芳2, 于之虹2, 李岩松1, 张爽3, 田蓓3
  

  1.  1.华北电力大学电气与电子工程学院, 北京市 102206;2.中国电力科学研究院,
    北京市 100192;3.国网宁夏电力公司电力科学研究院,银川市 750002
  • 出版日期:2016-12-01
  • 作者简介:张春(1991),男,硕士研究生,主要研究方向为电力系统稳定与控制; 田芳(1973),女,博士,教授级高工,主要研究方向为电力系统分析与控制,电力系统数字仿真等; 于之虹(1975),女,工学博士,高级工程师,主要从事电力系统安全稳定评估与控制、仿真分析技术等方面的工作; 李岩松(1975),男,博士,教授,研究方向为电力系统分析与控制、光学传感技术等; 张爽(1982),男,高级工程师,主要从事电力系统计算、试验、科研方面的工作; 田蓓(1977),女,高级工程师,从事电力系统计算与分析方面的工作。
  • 基金资助:
     国家重点基础研究发展计划项目(973项目)(2013CB228203);国家电网公司科技(XT71-15-001) 

 
 
Application of Improved Sammon Mapping Algorithm in Input Features Validity Analysis of Transient Stability Assessment 

 ZHANG Chun1, TIAN Fang2, YU Zhihong2, LI Yansong1, ZHANG Shuang3, TIAN Bei3   

  1.  1. School of Electrical and Electronic Engineering, North China Electric Power University, Beijing 102206, China;
    2. China Electric Power Research Institute, Beijing 100192, China;
    3. Electric Power Research Institute, State Grid Ningxia Electric Power Company, Yinchuan 750002, China
  • Online:2016-12-01
  • Supported by:
     Project supported by National Basic Research Program of China (973 Program) (2013CB228203)

摘要:  基于机器学习技术的电力系统暂态稳定评估方法中,输入特征提取的是否合理往往决定了最终的分类效果。然而,目前却缺乏一种工具去评价选择的输入特征是否具有可分性。鉴于此,引入Sammon映射算法将高维样本数据映射到低维空间中,通过观察映射点的分布情况判断提取的特征是否有效,并针对原算法的不足之处进行改进。首先利用主成分分析法(principal component analysis, PCA)求出包含原始数据信息最多的前两维主成分向量,代替原算法随机取值的方法,作为映射点坐标向量的初始值。然后,采用迭代修正法求解最终的映射点坐标向量,加快了求解速度。最后,以改进Sammon映射算法作为工具,分析IEEE 39节点系统的仿真数据和某地区实际在线历史数据提取特征的有效性,证明该算法在指导特征选择中具有良好的应用前景。

 

关键词:  , 暂态稳定, 机器学习, Sammon映射, 特征有效性

Abstract:  In the method of power system transient stability assessment based on machine learning technology, the reasonableness of the input feature extraction  decides the final classification result. However, there were no tools to judge whether the selected input features are the separable. Therefore, this paper introduces the Sammon mapping algorithm to map high dimensional sample data to low dimensional space, determines the effectiveness of selected feature through observing the distribution of mapping points, and improves the original algorithm according to its deficiencies. Firstly, we adopted principal component analysis (PCA) method to obtain the first two dimensional principal component vectors containing the most original data information, which worked as the initial value of the mapping point coordinate vector instead of the random selection method in the original algorithm. Then, we used the iterative method to solve the coordinate vector of mapping points to accelerate the solving speed. Finally, we used the improved Sammon mapping algorithm as a tool to analyze the effectiveness of selected features of the numerical simulation data in IEEE39-bus system and the actual online historical data of a certain area. The analysis results show that the improved algorithm has a good application prospect in guiding feature selection.

Key words:   transient stability, machine learning, Sammon mapping, feature effectiveness

中图分类号: