Dynamic Doppler prediction in high‐speed rail using long short‐term memory neural network
Lei Xiong, Zhengyu Zhang, Dongpin Yao · Transactions on Emerging Telecommunications Technologies · 2021
Abstract In the high‐speed rail (HSR), wireless communication systems are suffering considerably from the huge Doppler shift caused by the high speed moving of the train. Moreover, the Doppler shift in HSR changes rapidly, and results in the poor Doppler prediction performance on pay‐load symbols. In this paper, a novel Doppler prediction algorithm based on long short‐term memory (LSTM) neural network is proposed. The proposed algorithm is enable to learn the regularity of the Doppler shift by the pretraining and tracking training, and can achieve better prediction performance for high speed moving than traditional algorithms without modification of the communication protocol.