检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:邵凯[1,2] 张雅洁 SHAO Kai;ZHANG Yajie(School of Communications and Information Engineering,Chongqing University of Posts and Telecommunications,Chongqing 400065,P.R.China;Engineering Research Center of Mobile Communications of the Ministry of Education,Chongqing 400065,P.R.China)
机构地区:[1]重庆邮电大学通信与信息工程学院,重庆400065 [2]重庆邮电大学移动通信教育部工程研究中心,重庆400065
出 处:《重庆邮电大学学报(自然科学版)》2023年第5期838-846,共9页Journal of Chongqing University of Posts and Telecommunications(Natural Science Edition)
摘 要:在大规模多输入多输出(multiple input multiple output,MIMO)系统中,压缩感知(compressed sensing,CS)技术常用于具有稀疏特性的信道状态信息(channel state information,CSI)反馈。针对CS重构时信道稀疏度通常未知的问题,基于深度展开技术提出了一种变化信道稀疏度的CSI反馈方法(a CSI-feedback method for varying channel sparsity,AVCS)。AVCS将信道稀疏度作为训练参数,学习得到通用的网络架构。随着天线数量增大导致信道(矩阵)维度激增,学习网络所得的相互抑制矩阵会呈现二次增长问题,AVCS利用相互抑制矩阵托普利兹(Toeplitz)特性设计了降维卷积网络,解决CSI反馈时的计算复杂度问题。仿真结果表明,所提方法提高了在大规模MIMO系统下CSI重构的适用性,减少了反馈开销且对信道稀疏度具有鲁棒性。In massive multiple input multiple output(MIMO)systems,compressed sensing(CS)technology is often used for sparse characteristics-based channel state information(CSI)feedback.This paper proposes a CSI-feedback method for varying channel sparsity(AVCS)in order to solve the problem that the channel sparsity is usually unknown in CS reconstruction.AVCS uses channel sparsity as a training parameter to learn a general network architecture.As the dimension of the channel(matrix)increases due to the increasing number of antennas,the mutual inhibition matrix obtained from the learning network will show a quadratic growth problem.AVCS uses the Toeplitz feature of the mutual inhibition matrix to design a dimensionality reduction convolutional network to solve computational complexity problem of the CSI feedback.Simulation results show that the proposed method improves the applicability of CSI reconstruction in massive MIMO systems,reduces feedback overhead and is robust to channel sparsity.
关 键 词:信道状态信息(CSI) 压缩感知(CS) 大规模输入多输出(MIMO) 深度学习 变化稀疏度 计算复杂度
分 类 号:TN929.5[电子电信—通信与信息系统]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:3.145.81.212