预览加载中，请您耐心等待几秒...

基于改进RBF算法的建筑能效预测模型的构建.docx

预览
1/3
2/3
3/3

在线预览结束，喜欢就下载吧，查找使用更方便

下载提示 文本预览

如果您无法下载资料，请参考说明：

1、部分资料下载需要金币，请确保您的账户上有足够的金币

2、已购买过的文档，再次下载不重复扣费

3、资料包下载后请先用软件解压，在使用对应软件打开

基于改进RBF算法的建筑能效预测模型的构建 Abstract: Withtheincreaseinglobalenergyconsumption,improvingbuildingenergyefficiencyhasbecomeanimportanttaskforsustainabledevelopment.Inthispaper,weproposeanimprovedRadialBasisFunction(RBF)algorithmforbuildingenergyefficiencyprediction.Theproposedalgorithmusesanewdistancefunctiontocalculatethedistancebetweeninputsandcenters,andoptimizestheparametersofRBFnetworkwithdifferentialevolutionalgorithm.Weapplytheproposedmodeltotworeal-worldcasestudiestoevaluateitspredictionaccuracy,andcompareitwithtraditionalRBFalgorithmandotherpopularmachinelearningalgorithms.ExperimentalresultsshowthattheproposedalgorithmoutperformstraditionalRBFalgorithmandachievescompetitiveperformancecomparedtootherpopularalgorithms. Introduction: Buildingsaccountforasignificantproportionofglobalenergyconsumption,andtheenergyefficiencyofbuildingshasbecomeanimportanttopicinrecentyears.Accurateenergyefficiencypredictioncanhelpbuildingmanagersoptimizeenergyconsumptionandreduceenergycosts.Inrecentyears,machinelearningalgorithmshavebeenwidelyusedinthefieldofbuildingenergyefficiencypredictionduetotheirhighaccuracyandeaseofimplementation.Amongthem,RadialBasisFunction(RBF)algorithmisoneofthemostwidelyusedandpopularalgorithms. However,traditionalRBFalgorithmhassomeshortcomings.Forexample,thedistancebetweeninputsandcentersiscalculatedusingEuclideandistance,whichmaynotbeoptimalforsomedatasets.Inaddition,theparametersoftheRBFnetworkareusuallyoptimizedwithgradientdescentmethod,whichmayeasilygettrappedinlocaloptimaandleadtopoorperformance. Inthispaper,weproposeanimprovedRBFalgorithmforbuildingenergyefficiencyprediction.Specifically,weuseanewdistancefunctiontocalculatethedistancebetweeninputsandcenters,whichismorerobusttooutliersandnoiseindatasets.WealsooptimizetheparametersofRBFnetworkwithadifferentialevolutionalgorithm,whichcanavoidthelocaloptimaproblemandachievebetterperformance.Weapplytheproposedmodeltotworeal-worldcasestudiestoevaluateitspredictionaccuracy,andcompareitwithtraditionalRBFalgo