摘要
针对电力系统电压稳定的高维特征属性,特征选择能有效地降低属性维度。提出了基于交叠概率的静态电压稳定评估特征选择方法,构建用于电压稳定性评估的决策树。以IEEE-39节点测试系统为对象,对样本进行比较,应用结果表明,以该方法对静态电压稳定性相关属性进行特征选择,得到的最简组合在预测静态电压稳定性上具有较高的准确率。
In accordance with the high dimensional characteristics of voltage stability in power system,feature selection method can reduce dimensions effectively.This paper proposes a feature selection method for static voltage stability assessment based on overlapped probability,and constructs decision tree for the assessment.Its application in the IEEE-39 node test system has verified that the simplest combination generated by the proposed method can achieve high accuracy in the static voltage assessment.
出处
《华东电力》
北大核心
2012年第2期248-250,共3页
East China Electric Power
基金
国家自然科学基金重点项目(51037003)
四川省科技厅基础应用计划资助项目(2010jy0018)~~
关键词
交叠概率
特征选择
静态电压
决策树
overlapped probability
feature selection
static voltage
decision tree（DT）
