摘要
提出了一种将决策树技术同外推算法相接合的短期负荷预测算法。采取"分而治之"的策略:用决策树技术处理负荷中的温度分量,外推预测算法预测除去温度分量之后的负荷分量,最后叠加这两种分量,得到预测结果。这种算法运用于福建省调日调度计划的编制,预测精度较高。
The short-term load forecasting algorithm which combine the multi-points extrapolation with CART (classification and regression tree) is presented in this paper.The strategy is "divide and rule": treat the temperature component by classification and regression tree technology first,and forecast the load component (which the temperature component has been wiped off) by the extrapolation forecasting algorithm,and the two load components are fold to get the forecasting result.This algorithm has been applied in...
出处
《福建电力与电工》
2007年第2期24-27,共4页
Fujian Power and Electrical Engineering
关键词
负荷特性
数据挖掘
决策树技术
外推算法
load characteristics
data mining technology
classification and regression tree technology
extrapolation algorithm
