一种用于MIMO系统的动态信道估计技术研究

Research on Dynamic Channel Estimation in MIMO Communication System

信道估计是数字通信系统中的一项关键技术。现在应用的MIMO信道估计主要针对非频率平稳衰落信道,所以限制了MIMO技术只能在室内有好的应用。本文在小训练序列的支持向量拟合机(SVR)的基础上提出一种用于MIMO信道估计的自适应多维支持向量拟合机(AM-SVR),不同于通常用于求解M-SVR二次规划的方法,采用迭代权值最小二乘法大大加速了拟合机的训练收敛速度,同时通过计算机仿真试验讨论了该算法用于MIMO系统的性能。

Channel estimation is essential in digital communications. But non-frequency and stationary fading channel is the prerequisite for MIMO transmission nowadays, which limits the usage of MIMO technique mainly to indoor communication. In this paper an adaptive multiple dimensional support vector regressor （AM-SVR） is proposed to estimate the MIMO communication channels based on the good generalization properties of short training sequences. Instead of using quadratic programming （QP） procedures for solving the M-SVR, this paper presents an iterative re-weighted least squares procedure to improve the training convergence speed of M-SVR, which is a procedure simple to implement and allows a recursive formulation. The performance of the proposed algorithm is verified using computer simulations in MIMO communication scenarios.