A Deep Learning-based Approach to 5G-New Radio Channel Estimation

Following the continuous development of the information technology, the concept of dense urban networks has evolved as well. The powerful tools, like machine learning, break new ground in smart network and interface design. In this paper the concept of using deep learning for estimating the radio channel parameters of the LTE (Long Term Evolution) radio interface is presented. It was proved that the deep learning approach provides a significant gain (almost 40%) with 10.7% compared to the linear model with the lowest RMSE (Root Mean Squared Error) 17.01%. The solution can be adopted as a part of the data allocation algorithm implemented in the telemetry devices equipped with the 4G radio interface, or, after the adjustment, the NB-IoT (Narrowband Internet of Things), to maximize the reliability of the services in harsh indoor or urban environments. Presented results also prove the existence of the inverse proportional dependence between the number of hidden layers and the number of historical samples in terms of the obtained RMSE. The increase of the historical data memory allows using models with fewer hidden layers while maintaining a comparable RMSE value for each scenario, which reduces the total computational cost.

Download Full-text

Computerized indoor radio channel estimation using ray tracing

annals of telecommunications - annales des télécommunications ◽

10.1007/bf02996068 ◽

1997 ◽

Vol 52 (5-6) ◽

pp. 251-263

Author(s):

Marc Kimpe ◽

Harry Leib

Keyword(s):

Channel Estimation ◽

Ray Tracing ◽

Radio Channel ◽

Indoor Radio ◽

Indoor Radio Channel

Download Full-text

SAMPLE CLOCK OFFSET COMPENSATION IN THE FIFTH-GENERATION NEW RADIO UPLINK

Электросвязь ◽

10.34832/elsv.2021.23.10.007 ◽

2021 ◽

Author(s):

О.Г. ПОНОМАРЕВ ◽

М. АСАФ

Keyword(s):

Signal To Noise Ratio ◽

Radio Channel ◽

Estimation Method ◽

Estimation Methods ◽

Fifth Generation ◽

New Radio ◽

Shared Channel ◽

Wide Range ◽

Offset Compensation ◽

Clock Offset

Рассмотрена проблема коррекции искажений OFDM-сигнала, вызванных смещением частоты дискретизации сигнала в приемном и передающем устройствах системы сотовой связи пятого поколения. Предлагаемый метод компенсации смещения частоты дискретизации основывается на прямой коррекции искажений, вносимых в передаваемый сигнал наличием смещения, и не предполагает какой-либо оценки величины смещения. Метод предназначен для коррекции сигналов в восходящем канале системы сотовой связи пятого поколения и основывается на использовании референсных сигналов, рекомендованных стандартами 3GPP. Результаты численного моделирования показали, что использование предлагаемого метода позволяет повысить эффективность передачи данных по многолучевому радиоканалу более чем на 15% в широком диапазоне значений отношения сигнал/шум. 5G-NR, CP-OFDM, synchronization, sample clock offset, PUSCH. О The paper investigates the issue of sampling clock offset ( SCO) in the fifth generation new radio systems. Due to the imperfect SCO estimation methods, the correction methods relying on the SCO estimation are not perfect, so the proposed method directly corrects the effect of SCO without using any kind of estimation method. Our method is designed to correct the signals in the physical uplink shared channel (PUSCH). The method uses reference signals as recommended by the 3rd generation partnership project (3GPP) standards. The results of the numerical simulation show that the use of the proposed method increases the efficiency of data transmission over the multipath radio channel by more than 15% in a wide range of signal-to-noise ratio values.

Download Full-text