Doppler frequency offset estimation and diversity reception scheme of high-speed railway with multiple antennas on separated carriage

The challenges of severe Doppler effects in high-speed railway are considered. By building a cooperative antenna system; an algorithm of joint channel estimation and Doppler frequency offset （DFO） estimation is proposed based on Ricean channel model. First, a maximum likelihood estimation （MLE） algorithm for DFO is designed, show- ing that the Doppler estimation can be obtained by estimating moving velocity of the train and the path loss with the exploitation of pilots that are placed inside the frame. Then a joint detection algorithm for the receiver is proposed to exploit multi-antenna diversity gains. Last, the theoretical Crammer Rao bound （CRB） for joint channel estimation and DFO estimation is derived. The steady performance of the system is confirmed by numerical simulations. In particular, when the Ricean fading channel parameter equals 5 and the velocities of train are 100 m/s and 150 m/s, the estimation variances of DFO are very close to the theoretical results obtained by using CRB. Meanwhile, the corresponding sig- nal to noise ratio loss is less than 1.5 dB when the bit error rate is 10-5 for 16QAM signals.

Deep learning based Doppler frequency offset estimation for 5G-NR downlink in HSR scenario

In the fifth-generation new radio(5G-NR) high-speed railway(HSR) downlink,a deep learning(DL) based Doppler frequency offset(DFO) estimation scheme is proposed by using the back propagation neural network(BPNN).The proposed method mainly includes pre-training,training,and estimation phases,where the pre-training and training belong to the off-line stage,and the estimation is the online stage.To reduce the performance loss caused by the random initialization,the pre-training method is employed to acquire a desirable initialization,which is used as the initial parameters of the training phase.Moreover,the initial DFO estimation is used as input along with the received pilots to further improve the estimation accuracy.Different from the training phase,the initial DFO estimation in pre-training phase is obtained by the data and pilot symbols.Simulation results show that the mean squared error(MSE) performance of the proposed method is better than those of the available algorithms,and it has acceptable computational complexity.