典型文献
Environment Information-Based Channel Prediction Method Assisted by Graph Neural Network
文献摘要：
Recently,whether the channel predic-tion can be achieved in diverse communication sce-narios by directly utilizing the environment informa-tion gained lots of attention due to the environment impacting the propagation characteristics of the wire-less channel.This paper presents an environment information-based channel prediction(EICP)method for connecting the environment with the channel as-sisted by the graph neural networks(GNN).Firstly,the effective scatterers(ESs)producing paths and the primary scatterers(PSs)generating single prop-agation paths are detected by building the scatterer-centered communication environment graphs(SC-CEGs),which can simultaneously preserve the struc-ture information and highlight the pending scatterer.The GNN-based classification model is implemented to distinguish ESs and PSs from other scatterers.Sec-ondly,large-scale parameters(LSP)and small-scale parameters(SSP)are predicted by employing the GNNs with multi-target architecture and the graphs of detected ESs and PSs.Simulation results show that the average normalized mean squared error(NMSE)of LSP and SSP predictions are 0.12 and 0.008,which outperforms the methods of linear data learning.
文献关键词：
中图分类号：
作者姓名：
Yutong Sun;Jianhua Zhang;Yuxiang Zhang;Li Yu;Qixing Wang;Guangyi Liu
作者机构：
State Key Lab of Networking and Switching Technology,Beijing University of Posts and Telecommunications,Beijing 100876,China;Future Research Laboratory,China Mobile Research Institute,Beijing 100053,China
文献出处：
引用格式：
[1]Yutong Sun;Jianhua Zhang;Yuxiang Zhang;Li Yu;Qixing Wang;Guangyi Liu-.Environment Information-Based Channel Prediction Method Assisted by Graph Neural Network)[J].中国通信（英文版）,2022(11):前插1-前插3,1-15
A类：
CEGs
B类：
Environment,Information,Based,Channel,Prediction,Method,Assisted,by,Graph,Neural,Network,Recently,whether,channel,can,be,achieved,diverse,communication,sce,narios,directly,utilizing,environment,gained,lots,attention,due,impacting,propagation,characteristics,wire,less,This,paper,presents,information,EICP,connecting,neural,networks,Firstly,effective,scatterers,ESs,producing,paths,primary,PSs,generating,single,detected,building,centered,graphs,SC,which,simultaneously,preserve,struc,highlight,pending,classification,model,implemented,distinguish,from,other,Sec,ondly,large,scale,parameters,LSP,small,SSP,predicted,employing,GNNs,multi,target,architecture,Simulation,results,show,that,average,normalized,mean,squared,error,NMSE,predictions,outperforms,methods,linear,data,learning
AB值：
0.576534
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
