摘要
在分析、比较目前较为成熟的短期负荷预测模型的优、缺点的基础上,提出一种基于支持向量机理论的复合预测模型的构想,该模型通过对2个训练集样本的选择,弥补因单一训练集过大(包含冗余信息)或过小(必要信息遗失)造成的预测精度下降。为提高训练的收敛速度,预测时,可通过将负荷分类的方式简化模型。
This paper proposed a hybrid model for short-term load forecasting based on SVM (support vector machines). This model made good for content size too big (embodying redundancy) or too small (losing indispensable message)to unitary training anthology by selecting two training anthologies, and created decreasing of forecasting accuracy. When forecasting, it may simplify the model by means of load classification to raise the convergence rate.
出处
《吉林电力》
2006年第4期16-19,共4页
Jilin Electric Power
关键词
复合预测模型
电力系统
短期负荷预测
hybrid model for short-term load forecasting
electric power system
short-term load forecasting