时频双选信道OFDM系统的低复杂度MMSE-SD算法

Low-complexity MMSE-SD Algorithm for OFDM Systems over Doubly-selective Channels

在时频双选信道OFDM系统中,针对最小均方误差连续检测(MMSE-SD)算法求逆运算导致计算复杂度过高的问题,该文提出一种改进的低复杂度MMSE-SD算法。该算法首先对信道矩阵和检测矩阵进行扩展处理,然后建立扩展矩阵和原矩阵之间的关系,每次检测用扩展矩阵的迭代求逆代替原矩阵的直接求逆。理论分析和仿真结果表明:和原MMSE-SD算法相比,该改进算法在保持原算法性能的基础上,大幅度降低其计算复杂度;与其它算法相比,该改进算法兼顾了系统性能与计算复杂度,当归一化多普勒频移增大时,其计算复杂度保持不变而性能更优。

Because of the problem of the Minimum Mean Square Error with Successive Detection （MMSE-SD） algorithm with high computational complexity for OFDM systems in the presence of frequency and time double selective channels, an improved low-complexity MMSE-SD algorithm is proposed in this paper. The algorithm extends firstly the channel matrix and detection matrix, then establishes the relationship between them by using recursive inversion instead of direct inversion at each detection. Both theoretical analysis and simulation results show that the improved algorithm retains the performance of the original algorithm with much lower computational complexity compared to the original MMSE-SD algorithm; Compared to other algorithms, the improved algorithm balances the performance with the computational complexity. The larger normalization Doppler frequency shift, the better performance it possesses with the unchanged computational complexity.