For high-speed mobile MIMO-OFDM system, a low-complexity deep learning ( DL) based time- varying channel estimation scheme is proposed. To reduce the number of estimated parameters, the basis expansion model ( BEM) is employed to model the time-varying channel, which converts the channel estimation into the estimation of the basis coefficient. Specifically, the initial basis coeffi- cients are firstly used to train the neural network in an offline manner, and then the high-precision channel estimation can be obtained by small number of inputs. Moreover, the linear minimum mean square error ( LMMSE ) estimated channel is considered for the loss function in training phase, which makes the proposed method more practical. Simulation results show that the proposed method has a better performance and lower computational complexity compared with the available schemes, and it is robust to the fast time-varying channel in the high-speed mobile scenarios.

HU Bo;YANG Lihua;REN Lulu;NIE Qian

College of Communication and Information Engineering,Nanjing University of Posts and Telecommunications,Nanjing 210003,P.R.China

高技术通讯（英文版）

[1]HU Bo;YANG Lihua;REN Lulu;NIE Qian-.Deep learning-based time-varying channel estimation with basis expansion model for MIMO-OFDM system)[J].高技术通讯（英文版）,2022(03):288-294

Deep,learning,varying,channel,estimation,basis,expansion,model,MIMO,OFDM,system,For,high,speed,mobile,complexity,deep,DL,proposed,To,reduce,number,estimated,parameters,BEM,employed,which,converts,into,coefficient,Specifically,initial,cients,firstly,used,neural,network,offline,manner,then,precision,can,obtained,by,small,inputs,Moreover,linear,minimum,mean,square,error,LMMSE,considered,loss,function,training,phase,makes,method,more,practical,Simulation,results,show,that,better,performance,lower,computational,compared,available,schemes,robust,fast,scenarios

0.539069