摘要
在建立区域需水量预测的多元回归、神经网络和灰色系统模型的基础上,提出基于集对分析的区域需水量组合预测模型(SPA-CF),从同、异、反3个方面对各单个预测模型的预测精度进行定性和定量的综合分析,合理确定各单个预测模型的权重。应用结果表明,SPA-CF是一种直观、简便、通用的组合预测新模型,在区域需水量预测中具有推广应用价值。
Based on multiple regression, neural network and grey system models for regional water demand prediction, a combined prediction model for regional water demand using set pair analysis is presented. Qualitative and quantitative analysis of the prediction accuracy of every single forecast model were conducted from the aspects of identical, discrepant and contrary degrees, and the weight of every forecast model was reasonably determined. Application of the model shows that the SPA-CF is an intuitive convenient and general combined prediction method, which has extensive value in regional water demand prediction.
出处
《水利水电科技进展》
CSCD
北大核心
2009年第5期42-45,60,共5页
Advances in Science and Technology of Water Resources
关键词
区域需水量
集对分析
需水量预测
regional water demand
set pair analysis
water demand prediction
