Bi-LSTM based deep learning method for 5G signal detection and channel estimation

D Venkata Ratnam; K Nageswara Rao; D Venkata Ratnam; K Nageswara Rao

doi:10.3934/electreng.2021017

AIMS Electronics and Electrical Engineering

2021, Volume 5, Issue 4: 334-341. doi: 10.3934/electreng.2021017

Previous Article Next Article

Research article Special Issues

Bi-LSTM based deep learning method for 5G signal detection and channel estimation

D Venkata Ratnam ^{1
,
,},
K Nageswara Rao ²

1.
Department of Electronics and Communication Engineering, Koneru Lakshmaiah Education Foundation, Vaddeswaram, Andhra Pradesh, India
2.
National Institute of Technology, Warangal 506004, India

Received: 01 October 2021 Accepted: 07 December 2021 Published: 14 December 2021

The advanced neural network methods solve significant signal estimation and channel characterization difficulties in the next-generation 5G wireless communication systems. The number of transmitted signal copies received through multiple paths at the receiver leads to delay spread, which intern causes interference in communication. These adverse effects of the interference can be mitigated with the orthogonal frequency division modulation (OFDM) technique. Furthermore, the proper signal detection methods optimal channel estimation enhances the performance of the multicarrier wireless communication system. In this paper, bi-directional long short-term memory (Bi-LSTM) based deep learning method is implemented to estimate the channel in different multipath scenarios. The impact of the pilots and cyclic prefix on the performance of Bi LSTM algorithm is analyzed. It is evident from the symbol-error rate (SER) results that the Bi-LSTM algorithm performs better than the state of art channel estimation methods known as the Minimum Mean Square and Error (MMSE) estimation method.
- deep learning,
- LSTM,
- Bi-LSTM,
- OFDM,
- channel estimation
Citation: D Venkata Ratnam, K Nageswara Rao. Bi-LSTM based deep learning method for 5G signal detection and channel estimation[J]. AIMS Electronics and Electrical Engineering, 2021, 5(4): 334-341. doi: 10.3934/electreng.2021017

Related Papers:

Abstract

The advanced neural network methods solve significant signal estimation and channel characterization difficulties in the next-generation 5G wireless communication systems. The number of transmitted signal copies received through multiple paths at the receiver leads to delay spread, which intern causes interference in communication. These adverse effects of the interference can be mitigated with the orthogonal frequency division modulation (OFDM) technique. Furthermore, the proper signal detection methods optimal channel estimation enhances the performance of the multicarrier wireless communication system. In this paper, bi-directional long short-term memory (Bi-LSTM) based deep learning method is implemented to estimate the channel in different multipath scenarios. The impact of the pilots and cyclic prefix on the performance of Bi LSTM algorithm is analyzed. It is evident from the symbol-error rate (SER) results that the Bi-LSTM algorithm performs better than the state of art channel estimation methods known as the Minimum Mean Square and Error (MMSE) estimation method.

References

[1]	Agiwal M, Roy A, Saxena N (2016) Next Generation 5G Wireless Networks: A Comprehensive Survey. IEEE Commun Surv Tut 18: 1617-1655. doi: 10.1109/COMST.2016.2532458. doi: 10.1109/COMST.2016.2532458
[2]	Sun S, Rappaport TS, Shafi M, et al. (2018) Propagation Models and Performance Evaluation for 5G Millimeter-Wave Bands. IEEE T Veh Technol 67: 8422-8439. doi: 10.1109/TVT.2018.2848208. doi: 10.1109/TVT.2018.2848208
[3]	Chen J, Wu Y, Ma S, et al. (2008) Joint CFO and Channel Estimation for Multiuser MIMO-OFDM Systems With Optimal Training Sequences. IEEE T Signal Proces 56: 4008-4019. doi: 10.1109/TSP.2008.925896. doi: 10.1109/TSP.2008.925896
[4]	Sampath H, Talwar S, Tellado J, et al. (2002) A fourth generation MIMO-OFDM broadband wireless system: Design, performance, and field trial results. IEEE Commun Mag 40: 143-149. doi: 10.1109/MCOM.2002.1031841
[5]	Kbashi HJ, Sharma V, Sergeyev S (2021) Dual-wavelength fiber-laser-based transmission of millimeter waves for 5G-supported Radio-over-Fiber (RoF) links. Opt Fiber Technol 65: 102588. doi: 10.1016/j.yofte.2021.102588. doi: 10.1016/j.yofte.2021.102588
[6]	Kbashi HJ, Sharma V, Sergeyev S (2020) Phase-stable millimeter-wave generation using switchable dual-wavelength fiber laser. Opt Laser Eng 137: 106390. doi: 10.1016/j.optlaseng.2020.106390. doi: 10.1016/j.optlaseng.2020.106390
[7]	Li Y, Cimini LJ, Sollenberger NR (1998) Robust channel estimation for ofdm systems with rapid dispersive fading channels. IEEE T Commun 46: 902-915. doi: 10.1109/26.701317
[8]	Thien HT, Tuan PV, Koo I (2020) Deep Learning-Based Approach to Fast Power Allocation in SISO SWIPT Systems with a Power-Splitting Scheme. Applied Sciences 10: 3634. doi: 10.3390/app10103634
[9]	Maimó LF, Gómez ALP, Clemente FJG, et al. (2018) A Self-Adaptive Deep Learning-Based System for Anomaly Detection in 5G Networks. IEEE Access 6: 7700-7712. doi: 10.1109/ACCESS.2018.2803446. doi: 10.1109/ACCESS.2018.2803446
[10]	Schuster M, Paliwal KK (1997) Bidirectional recurrent neural networks. IEEE T Signal Proces 45: 2673-2681. doi: 10.1109/78.650093
[11]	Narengerile (2020) Deep learning-based signal detection in OFDM systems (https://www.mathworks.com/matlabcentral/fileexchange/72321-deep-learning-based-signal-detection-in-ofdm-systems), MATLAB Central File Exchange. Retrieved September 26, 2020.
[12]	Le HA, Van Chien T, Nguyen TH, et al. (2021) Machine Learning-Based 5G-and-Beyond Channel Estimation for MIMO-OFDM Communication Systems. Sensors 21: 4861. doi: 10.3390/s21144861

Reader Comments

Your name:*

Email:*
© 2021 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)