OFDMA系统中的子载波和功率联合TCNN优化-豆柴文库

您所在位置：网站首页 / OFDMA系统中的子载波和功率联合TCNN优化.docx / 文档详情

在线预览结束，喜欢就下载吧，查找使用更方便

5 金币

下载文档

/ 2

下载提示

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

文本预览

OFDMA系统中的子载波和功率联合TCNN优化
Title:JointSubcarrierandPowerAllocationOptimizationinOFDMASystemusingTCNN
Abstract:
OrthogonalFrequencyDivisionMultipleAccess(OFDMA)iswidelyusedinmodernwirelesscommunicationsystemsduetoitshighspectralefficiencyandabilitytomitigateinter-symbolinterference.InOFDMA,theavailablebandwidthisdividedintomultipleorthogonalsubcarriers,whichenablessimultaneoustransmissionofmultipledatastreamstomultipleusers.Efficientallocationofsubcarriersandpowerplaysacrucialroleinachievingoptimumsystemperformance.ThispaperproposesanovelapproachforjointsubcarrierandpowerallocationoptimizationinOFDMAsystemsusingTemporalConvolutionalNeuralNetworks(TCNN).Themainobjectiveistomaximizeoverallsystemcapacitywhileensuringfairnessamongusersbyoptimizingthesubcarrierandpowerallocationscheme.
1.Introduction:
OFDMAsystemsarebeingincreasinglyusedforvariouswirelesscommunicationapplicationssuchas4G/5GcellularnetworksandWi-Fi.Theefficientallocationofsubcarriersandpowerinthesesystemscansignificantlyimprovetheoverallperformance,includingbetterspectrumutilization,reducedinterference,andincreasedcapacity.Traditionaloptimizationmethodsforsubcarrierandpowerallocationoftenrelyonmathematicaloptimizationalgorithms,whichmaybecomputationallycomplexanddifficulttoimplementinreal-timescenarios.Thismotivatestheexplorationofmachinelearning-basedapproacheslikeTCNNforefficientOFDMAsystemoptimization.
2.SystemModel:
ConsideranOFDMAsystemwithabasestationandmultipleusers.TheavailablebandwidthisdividedintoNorthogonalsubcarriers,andthepowerallocationisdoneonaper-subcarrierbasis.Theobjectiveistoallocatesubcarriersandpoweroptimallytomaximizetheoverallsystemcapacitywhileensuringfairnessamongusers.Thesubcarrierandpowerallocationproblemcanbeformulatedasanoptimizationproblemwithconstraintssuchaspowerbudget,minimumdataraterequirements,andfairnessconstraints.
3.TemporalConvolutionalNeuralNetworks:
TCNNisatypeofdeeplearningmodelthatincorporatesthetemporalorderofinputdatathroughtheuseofconvolutionallayersanddilatedconv