摘要
为了提高多输入多输出正交频分复用系统(MIMO-OFDM)的信道估计性能,本文采用改进的加权支持向量回归机对信道参数进行估计。TSVR由KNN算法计算训练样本的权值,加入到TSVR的目标函数。在信道估计过程中,首先利用最小二乘算法对导频位置处的信道参数进行估计,得到对TSVR的训练样本,通过求解改进TSVR的二次优化问题得到MIMO-OFDM系统的信道参数,利用牛顿迭代法在原空间进行仿真实验,本文提出的改进的加权TSVR信道估计算法与其它的算法相比,具有良好的估计性能和抗噪声能力。
In order to improve the channel estimation performance of MIMO-OFDM system,an algorithm based on weighted support vector regression is improved and adopted to evaluate channel parameters.Firstly,the channel parameters are pre estimated based on pilot,and the least square algorithm is used.Then,the training samples of TSVR are obtained,and then the weights are assigned to them.The Newton iterative algorithm is used to solve the optimization problem.Finally,the MIMO-OFDM channel is estimated by the proposed TSVR interpolation.The improved weighted TSVR channel estimation algorithm proposed in this paper shows a better estimation performance and anti-noise ability than the other algorithms.At the same time,this conclusion is verified by simulations.
作者
李朔
雷为民
张伟
LI Shuo;LEI Weimin;ZHANG Wei(School of Computer Science and Engineering,Northeastern University,Shenyang 110819,China;School of Electronic and Information Engineering,University of Science and Technology Liaoning,Anshan 114051,China)
出处
《辽宁科技大学学报》
CAS
2021年第2期123-128,共6页
Journal of University of Science and Technology Liaoning
基金
国家重点研究发展计划(2018YFB1702000)
中央高校基础研究基金(N2016014)
辽宁省自然科学基金(20180551007)。
关键词
信道估计
正交频分复用系统
牛顿迭代法
加权孪生支持向量机
channel estimation
orthogonal frequency division multiplexing
Newton iterative method
weighted twin support vector machine
