摘要
介绍了线性回归分析中虚拟变量的概念和意义,根据日用电量随时间和温度变化的特性,将其分段并引入相应的虚拟变量,在此基础上建立电量预测的回归模型,并以南京市2002年至2004年日用电量为样本进行预测检验,预测结果表明了该方法的有效性。
The daily power consumption was sectionized according to its characteristics of value changing with time and temperature and corresponding dummy variables were imported. The regressive models of power consumption wore established based on that method. Forecasting check took the daily power consumption of Nanjing from 2002 to 2004 as samples. Check results showed that the method was effective.
出处
《江苏电机工程》
2006年第3期1-3,共3页
Jiangsu Electrical Engineering
关键词
虚拟变量
日用电量
预测
温度
dummy variable
daily power consumption
forecasting
temperature
