基于提升方法的短期负荷预测的研究  

Study on Short-term Load Forecasting Based on Lifting

作　　者：彭俊[1] 谢荣传[1] 王大刚[1] 耿波[1] 

机构地区：[1]安徽大学计算机学院,安徽合肥230039

出　　处：《计算机技术与发展》2008年第7期197-199,共3页Computer Technology and Development

基　　金：安徽省自然基金项目(070412051);安徽高校省级重点自然科学研究项目(KJ2007A43)

摘　　要：目前有很多方法可以实现电力负荷预测,但各种方法都有各自的局限性,如何充分利用各种算法,使负荷预测的精确度提高,组合预测方法便应运而生了。然而当前的组合预测方法过于重视算法,而忽略样本。文中给出了一种基于提升方法的电力负荷预测挖掘算法,该方法通过样本权值进行抽样,训练生成模型,并根据模型效率改变样本权值,再次抽样训练生成模型,如此迭代生成多个模型后进行负荷预测。实际应用结果表明该方法比其它方法具有较高的精度。There are many algorithms have the ability to forcast short - term load,but each of them has disadvantage. How to use these algorithms to improve the forcasting precision？ The combination forecasting method can solve the problem. The current combination forecasting method pay more attention on algorithm than samples. Propose a new method for forecasting short- term load based on the lifting. Use the method sampling by sample weight and then training the model. Change the sample weight by efficiency of model. Doing above repeatly , generate multiple model to forcast load. The research shows that this method has higher accuracy.

关 键 词：提升方法 组合预测方法 样本权值 短期负荷预测 CART算法 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]