摘要
在非地面网络(Non⁃terrestrial network,NTN)场景中,为克服大多普勒频偏对通信的影响,提出一种基于全局信息提取超分辨率和去噪的神经网络(Global information super resolution denoising neural network,GSRDnNet)。此方法将最小二乘估计(Least square,LS)算法得到的导频处信道估计矩阵视为低分辨率小尺寸图像,将其作为神经网络的输入,输入数据经过GSRDnNet网络处理之后将得到更为精确的高分辨率图像,即时频资源块完整的信道响应矩阵。采用4种NTN‑抽头延迟线(Tapped delay line,TDL)A,B,C,D信道模型进行仿真验证,仿真结果表明GSRDnNet相比于传统LS算法,均方误差(Mean squared error,MSE)提升3.37~8.83 dB,相比于实际信道估计(Practical channel estimation,PCE)算法,MSE提升2.11~6.06 dB,相比于需要预插值处理的超分辨率卷积神经网络(Super resolution convolutional neural network,SRCNN)+去噪卷积神经网络(Denoising convolutional neural network,DnCNN)方法,MSE性能提升1.37~4.40 dB。且较SRCNN+DnCNN,GSRDnNet网络模型的输入仅考虑导频处的信道估计矩阵,因此不仅拥有更高的估计精度,计算复杂度也降低了约84%。
In non-terrestrial network(NTN)scenarios,to overcome the effect of large Doppler frequency offset on the communication,a channel estimation method based on global information super resolution denoising neural network(GSRDnNet)is proposed.This method considers the channel estimation matrix at the pilot obtained by the least square(LS)estimation algorithm as a low-resolution small-size image and takes it as the input to the neural network.The input data is then processed by the GSRDnNet network to obtain a more accurate high-resolution image with a complete channel response matrix for the timefrequency resource block.Four NTN-tapped delay line(TDL)A,B,C and D channel models are used for simulation verification.Simulation results indicate that GSRDnNet improves mean squared error(MSE)performance by 3.37—8.83 dB compared to the traditional LS algorithm.Compared with the practical channel estimation(PCE)algorithm,the MSE is improved by 2.11-6.06 dB,and compared with the SRCNN+DnCNN method,which requires pre-interpolation processing,the MSE is improved by 1.37-4.40 dB.And compared with super resolution convolutional neural network(SRCNN)+denoising convolutional neural network(DnCNN),the input of GSRDnNet network model only considers the channel estimation matrix at the pilot,so it not only has higher estimation accuracy,but also reduces the computational complexity by about 84%.
作者
任晓宁
段红光
黄凤翔
董诗康
REN Xiaoning;DUAN Hongguang;HUANG Fengxiang;DONG Shikang(School of Communication and Information Engineering,Chongqing University of Posts and Telecommunications,Chongqing 400065,China)
出处
《数据采集与处理》
北大核心
2025年第6期1424-1433,共10页
Journal of Data Acquisition and Processing
基金
重庆市自然科学基金(cstc2019jcyj-msxmX0079)。
关键词
多普勒频偏
全局信息
超分
去噪
信道估计
Doppler frequency offset
global information
super-resolution
denoise
channel estimation
