预览加载中，请您耐心等待几秒...

SOFM-LM-BP神经网络在光伏发电量预测中的应用.docx

预览
1/2
2/2

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

SOFM-LM-BP神经网络在光伏发电量预测中的应用 Abstract: Photovoltaicpowergenerationisanimportantrenewableenergysource,andaccuratepredictionofitspowergenerationisveryimportantforthesafeandefficientoperationandmanagementofthepowergenerationsystem.Inordertoachievethisgoal,manyresearchershaveproposedvariousmodels,amongwhichneuralnetworkshavebecomeapopularchoiceduetotheiroutstandingperformanceinpredictiontasks.ThispaperaimstoexploretheapplicationoftheSOFM-LM-BPneuralnetworkinpredictingtheoutputpowerofphotovoltaiccells,andcomparesitsperformancewiththatofothertraditionalpredictionmodels.ResultsshowthattheSOFM-LM-BPneuralnetworkhashigheraccuracyandbettergeneralizationability,andcanprovidereliablepredictionsforphotovoltaicpowergeneration. Introduction: Photovoltaicpowergenerationisanimportantrenewableenergysource,whichhasreceivedmoreandmoreattentioninrecentyearsduetoitsenvironmentalfriendlinessandeconomicviability.Accuratepredictionofphotovoltaicpowergenerationisveryimportantforefficientandsafeoperationandmanagementofpowergenerationsystems.Therefore,itisnecessarytodevelopaccurateandeffectivepredictionmodels.Inrecentyears,artificialneuralnetworkshavebecomeoneofthepopularchoicestosolvepredictionproblemsduetotheirexcellentperformanceandlearningability.Inthispaper,weproposeanSOFM-LM-BPneuralnetworkmodelforpredictionofphotovoltaicpowergeneration,andcompareitsperformancewithtraditionalpredictionmodels. Methodology: TheproposedSOFM-LM-BPneuralnetworkmodelconsistsofthreelayers:theinputlayer,thehiddenlayer,andtheoutputlayer.Theinputlayeracceptstheinputdata,whichincludesthemeteorologicalparameters(suchastemperature,humidity,andradiation)andtheoutputpowerofphotovoltaiccells.Thehiddenlayerconsistsoftheself-organizingfeaturemap(SOFM)andthebackpropagation(BP)neuralnetwork.SOFMisanunsupervisedlearningalgorithmthatcaneffectivelyreducethedimensionoftheinputdataandextractusefulfeatures.BPalgorithmisasupervisedlearningalgorithmthatcanaccuratelypredicttheoutputvalues.Theoutputlayeroutputstheestimatedvaluesofphoto