多奇异值下的预编码码字选择方法  

A Method for Selecting Precoded Codeword Based on Multiple Singular Values

作　　者：谷瑞欣 谢怡 戴谭明 吴君钦[1] GU Ruixin;XIE Yi;DAI Tanming;WU Junqin(Jiangxi University of Science and Technology,Ganzhou Jiangxi 341000,China)

机构地区：[1]江西理工大学,江西赣州341000

出　　处：《通信技术》2024年第9期886-891,共6页Communications Technology

基　　金：国家自然科学基金应急管理基金项目(61741109);江西省教育厅科技项目(GJJ200881)。

摘　　要：为了在大规模多输入多输出(Multi Input Multi Output,MIMO)下行系统中得到精准的信道状态信息(Channel State Information,CSI),提出了基于多奇异值的预编码码字选择方法。该方法在重构信道矩阵的基础上对信道自相关矩阵进行奇异值分解,利用分解出的前两个特征值对应的特征向量对信道进行在垂直和水平两个维度上联合量化。此方法在降低系统选码复杂度的同时,还能保持较好地逼近真实信道的性能。此外,基于假设的信道模型给出了量化反馈比特数与量化精度的关系。通过MATLAB实验仿真,证实了该方法的有效性和可行性。In order to obtain accurate CSI(Channel State Information)in massive MIMO(Multi-Input Multi-Output)downlink systems,this paper proposes a precoded codeword selection method based on multiple singular values.The method carries out a singular value decomposition of the channel autocorrelation matrix based on the reconstructed channel matrix,and uses the eigenvectors corresponding to the first two eigenvalues decomposed to jointly quantize the channel in both vertical and horizontal dimensions.This method can reduce the complexity of system code selection while maintaining good approximation of the real channel performance.In addition,the channel model based on assumptions provides the relationship between the number of quantization feedback bits and the quantization accuracy.The effectiveness and feasibility of the method are confirmed through MATLAB experimental simulation.

关 键 词：大规模多输入多输出系统 信道状态信息 多奇异值预编码 自相关矩阵 量化精度 

分 类 号：TN911.22[电子电信—通信与信息系统]