基于分层模型的SC-FDE系统低复杂度稀疏信道估计

The Hierarchical Model Based on Low Complexity Sparse Channel Estimation for SC-FDE System

针对单载波频域均衡(SC-FDE)接收机提出一种低复杂度的贝叶斯稀疏信道估计算法。该算法利用广义平均场(GMF)推理方法结合贝叶斯分层先验模型得到。在GMF推理方法中,使用辅助函数来等效未知变量的联合后验概率密度函数;然后对辅助函数进行因子分解,通过对待估计的稀疏向量的辅助函数进行不同大小的分块来实现降低复杂度的目的,而原始的高复杂度算法(SC-VMP-3L)是所提出的算法的特例。最后,将GMF推理方法用于频域均衡中。仿真结果表明,在信道估计精度和误码率方面,所提出的算法性能与SC-VMP-3L算法的性能接近,且明显优于传统的正交匹配追踪(OMP)稀疏信道估计方法。在复杂度方面,与SC-VMP-3L算法相比有显著降低。

A low complexity sparse Bayesian channel estimation algorithm was proposed for SC-FDE receiver. The proposed algorithm was obtained by applying the generalized mean field（ GMF） inference framework to the Bayesian Hierarchical prior Model. In the GMF framework,we constrained the auxiliary function approximating the posterior probability density function of the unknown variables. The complexity of the method was reduced by blocking the auxiliary function of the sparse vectors into different sizes of groups. The original high-complexity algorithm（ SC-VMP-3L） corresponds to the particular case when the auxiliary function is assigned to one single group. Finally,we applied the GMF inference framework to the Frequency Domain. Numerical results demonstrate that the proposed method has better performance than the traditional Orthogonal Matching Pursuit（ OMP） sparse channel estimation algorithm in estimation precision of the channel and Bit Error Rate（ BER） while it performs nearly as well as SC-VMP-3L algorithm but with much less computational complexity.