Browse by author
Lookup NU author(s): Bilal Jebur,
Dr Charalampos Tsimenidis
This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0).
Recently much research work has focused on employing deep learning (DL) algorithms toperform channel estimation in the upcoming 6G communication systems. However, these DL algorithmsare usually computationally demanding and require a large number of training samples. Hence, this workinvestigates the feasibility of designing efficient machine learning (ML) algorithms that can effectivelyestimate and track time-varying, frequency-selective channels. The proposed algorithm is integrated withorthogonal frequency-division multiplexing (OFDM) to eliminate intersymbol interference (ISI) inducedby the frequency-selective multipath channel and compared with the well-known least square (LS) andlinear minimum mean square error (LMMSE) channel estimation algorithms. The obtained results havedemonstrated that even when a small number of pilot samples, N P , is inserted before the N subcarriersOFDM symbol, the introduced ML-based channel estimation is superior to the LS and LMMSE algorithms.This dominance is reflected in the bit-error-rate (BER) performance of the proposed algorithm, which attainsa gain of 2.5 dB and 5.5 dB over the LMMSE and LS algorithms, respectively, when N P = N 8 . Furthermore,the BER performance of the proposed algorithm is shown to degrade by only 0.2 dB when the maximumDoppler frequency is randomly varied. Finally, the number of iterations required by the proposed algorithmto converge to the smallest achievable mean-squared error (MSE) are thoroughly examined for varioussignal-to-noise ratio (SNR) levels.
Publication type: Article
Publication status: Published
Journal: IEEE Access
Issue: ePub ahead of Print
Online publication date: 15/07/2021
Acceptance date: 11/07/2021
Date deposited: 19/07/2021
ISSN (print): 2169-3536
ISSN (electronic): 2169-3536
Altmetrics provided by Altmetric