基于Grassmannian流形共轭梯度算法的干扰对齐方案  

Interference alignment based on the conjugate gradient algorithm on the Grassmannian manifold

作　　者：李汀[1] 赵娟 

机构地区：[1]南京邮电大学通信与信息工程学院,南京210003 [2]南京邮电大学计算机学院,南京210003

出　　处：《扬州大学学报（自然科学版）》2017年第4期58-62,共5页Journal of Yangzhou University：Natural Science Edition

基　　金：国家自然科学基金资助项目(61771254,61471200);江苏省自然科学基金资助项目(BK20140881);南京邮电大学横向基金资助项目(2016外71)

摘　　要：在Grassmannian流形Gn,p上对多用户多入多出(multiple input multiple output,MIMO)干扰系统中的发射子空间和干扰子空间进行建模,使得复欧氏空间中有约束的最优化问题转化为Grassmannian流形上降维的无约束最优化问题.利用微分流形的几何特性设计Grassmannian流形上的共轭梯度干扰对齐算法,交替迭代优化发射预编码矩阵和接收滤波矩阵.仿真结果表明:该算法的收敛性能优越,用户干扰的残余功率小,系统的传输速率及频谱效率高.For the multiuser MIMO interference system, the transmit subspace and the interference subspace are modeled on the Grassmannnian Manifold The constrained optimization problemon the Euclidean space is transformed into the unconstrained optimization problem with the degener-ate dimension on the Grassmannnian manifold. The geometric characteristics of differential mani-folds are used to design the conjugate gradient algorithm on the Grassmannnian manifold to apply it to the iterative optimization of transmitter precoding matrix and the receiver postprocessing matrix. Simulation results show that the proposed algorithm has better convergence performance, lower residual power of the user interference, higher transmission rate and spectral efficiency.

关 键 词：MIMO系统 干扰对齐 Grassmannian流形 预编码 

分 类 号：TN911.5[电子电信—通信与信息系统]