IRS辅助毫米波MIMO系统波束赋形优化的低复杂度方案  

A Low-complexity Scheme for Beamforming Optimization of IRS-assisted mmWave MIMO System

作　　者：王长江 傅友华[1,2] WANG Changjiang;FU Youhua(College of Electronic and Optical Engineering and College of Flexible Electronics(Future Technology),Nanjing University of Posts and Telecommunications,Nanjing,Jiangsu 210023,China;National and Local Joint Engineering Laboratory of RF Integration and Micro-Assembly Technology,Nanjing University of Posts and Telecommunications,Nanjing,Jiangsu 210023,China)

机构地区：[1]南京邮电大学电子与光学工程学院、柔性电子(未来技术)学院,江苏南京210023 [2]南京邮电大学射频集成与微组装技术国家地方联合工程实验室,江苏南京210023

出　　处：《信号处理》2022年第9期1965-1974,共10页Journal of Signal Processing

基　　金：国家自然科学基金资助项目(61771257);南京邮电大学射频集成与微组装技术国家地方联合工程实验室开放课题(KFJJ20210101)。

摘　　要：智能反射表面(intelligent reflective surface,IRS)被认为是无线通信网络的前景技术之一。然而由于IRS无源波束赋形优化受到本身所具有的非凸恒模约束,现有工作在IRS辅助的多输入多输出(multiple input multiple output,MIMO)系统中的研究只能得到次优解且具有较高的复杂度。本文考虑一个单用户IRS辅助通信的毫米波MIMO系统,为了最大化频谱效率,优化通信接入点AP(access point)端有源和IRS端无源波束赋形矩阵。首先将有源和无源波束赋形矩阵解耦,得到AP的最优有源波束赋形解,将IRS无源波束赋形设计问题推导为一个非凸二次约束二次规划(quadratically constrained quadratic programming,QCQP)问题;采用低复杂度的连续闭式解(successive closed form,SCF)算法求解IRS无源波束赋形矩阵,为了衡量SCF算法性能,分析对比了现有的最优分支界定(branch and bound,BnB)算法。仿真结果验证了SCF算法在IRS相移连续和离散时均能在较低复杂度达到较高的频谱效率性能。Intelligent reflective surface(IRS)is considered as one of the promising technologies for wireless communication networks.However,due to the non-convex constant modulus constraint of IRS passive beam forming optimization,existing researches in IRS-assisted multiple input multiple output(MIMO)systems only got suboptimal solutions with high complexity.The paper considered a single-user IRS-assisted communication millimeter-wave MIMO system.In order to maximize the spectrum efficiency,the active beamforming matrix at the AP(access point)side and the passive beamforming matrix at the IRS side were optimized.Firstly,the active and passive beamforming matrices were decoupled to obtain the optimal active beamforming solution for AP.The IRS passive beamforming design problem was derived as a non-convex quadratically constrained quadratic programming(QCQP)problem.The low-complexity successive closed form(SCF)algorithm was used to solve the IRS passive beamforming matrix.In order to measure the performance of the SCF algorithm,the existing optimal branch and bound(BnB)algorithm was analyzed and compared.The simulation results verify that the SCF algorithm can achieve higher spectral efficiency performance with lower complexity when the IRS phase shift is continuous and discrete.

关 键 词：智能反射表面 无源波束赋形 恒模约束 连续闭式解 分支界定 

分 类 号：TN928[电子电信—通信与信息系统]