基于孪生支持向量机的OFDM系统信道估计

Channel Estimation of OFDM System based on Twin Support Vector Machine

正交频分复用系统(Orthogonal Frequency Division Multiplexing,OFDM)的信道估计是进行相干解调的前提,通常采用孪生支持向量机(Twin Support Vector Machines,TSVM)对信道参数进行估计。提出的算法利用TSVM适用于非线性函数回归的特点,提高信道参数的回归性能。在信道估计过程中,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TSVM的训练样本,然后通过求解TSVM的二次优化问题得到OFDM系统的信道参数。理论分析和仿真实验结果显示,提出的孪生支持向量机信道估计算法与其他算法相比具有良好的估计性能和抗噪声能力。

The channel estimation of OFDM(Orthogonal Frequency Division Multiplexing)system is the premise of coherent demodulation.In this paper,TSVM(Twin Support Vector Machine)is used to estimate channel parameters.The proposed algorithm makes use of the characteristics of TSVM which is suitable for nonlinear function regression to improve the regression performance of channel parameters.In the process of channel estimation,the least square algorithm is used to estimate the channel parameters at the pilot position,and the training samples of TSVM are obtained.Then the channel parameters of OFDM system are obtained by solving the quadratic optimization problem of TSVM.Theoretical analysis and simulation results indicate that the proposed twin support vector machine channel estimation algorithm has good estimation performance and anti-noise ability compared with other algorithms.