Parth Jakhaniya, Ashish Pandya, Rizwan Alad, Nirav Desai, Purvang Dalal | International Journal of Telecommunications & Emerging Technologies | Vol 12, Issue 02 | ISSN: 2455-0345
Abstract
Accurate channel estimation is a fundamental requirement for reliable communications in fifth-generation New Radio (5G NR) systems, where highly dynamic propagation environments impose severe challenges on conventional pilot-based methods. This study provides a thorough analysis of channel estimate methods for 5G NR, including everything from contemporary deep learning (DL) techniques based on Convolutional Neural Networks (CNNs) to traditional Least Squares (LS) and Minimum Mean Square Error (MMSE) estimators. Our analysis is grounded in systematic simulation experiments conducted in MATLAB using the 5G NR Toolbox across all five standardized Tapped Delay Line (TDL-A/B/C/D/E) and Clustered Delay Line (CDL-A/B/C/D/E) channel profiles. Baseline modulation performance is first established for QPSK and 16-QAM under ideal AWGN conditions and is subsequently evaluated through OFDM transceivers under fading channels with 2 × 2 and 4 × 4 MIMO configurations. A CNN-based estimator trained on LS pilot observations is benchmarked against conventional methods over TDL-D and TDL-E profiles, demonstrating significant BER gains in high-mobility scenarios. The survey identifies key architectural trade-offs, discusses dataset design and training strategies, and outlines open research directions toward ultra-reliable low latency 6G systems. These results clearly demonstrate how intelligent channel estimates may enhance spectral efficiency, resilience, and dependability in upcoming wireless networks.
Keywords - 5G NR, channel estimation, TDL channels, CDL channels, OFDM, QPSK, 16-QAM, MIMO, Least Squares, MMSE, convolutional neural network, deep learning, BER performance.
🔒 This is a subscription article
Full text is available to subscribers and institutional members. Please choose an option below to access it.
SubscribePurchase this articleInstitutional / Login accessReferences
- Tang P, Xu H, Zhang J, Liu X, Liu E, Miao H, Sun X, Jiang W, Liu G. A Tutorial on 3GPP Rel-19 Channel Modeling for 6G FR3 (7-24 GHz): From Standard Specification to Simulation Implementation. arXiv preprint arXiv:2602.07623. 2026 Feb 7.
- Ye H, Li GY, Juang BH. Power of deep learning for channel estimation and signal detection in OFDM systems. IEEE Wireless Communications Letters. 2017 Sep 28;7(1):114-7.
- He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. InProceedings of the IEEE conference on computer vision and pattern recognition 2016 (pp. 770-778).
- Neumann D, Wiese T, Utschick W. Learning the MMSE channel estimator. IEEE Transactions on Signal Processing. 2018 Jan 30;66(11):2905-17.
- Soltani M, Pourahmadi V, Mirzaei A, Sheikhzadeh H. Deep learning-based channel estimation. IEEE Communications Letters. 2019 Feb 12;23(4):652-5.
- Dong P, Zhang H, Li GY, Gaspar IS, NaderiAlizadeh N. Deep CNN-based channel estimation for mmWave massive MIMO systems. IEEE Journal of Selected Topics in Signal Processing. 2019 Jul 1;13(5):989-1000.
- Ye H, Li GY, Juang BH. Power of deep learning for channel estimation and signal detection in OFDM systems. IEEE Wireless Communications Letters. 2017 Sep 28;7(1):114-7.
- Eisen M, Ribeiro A. Optimal wireless resource allocation with random edge graph neural networks. arXiv preprint arXiv:1909.01865. 2019 Sep 4.
- Mahedi K, Chowdhury MZ, Jang YM. Enhanced Deep Learning-Based Channel Estimation for 5G NR System Using Lightweight U-Net Architecture. In2026 International Conference on Artificial Intelligence in Information and Communication (ICAIIC) 2026 Feb 24 (pp. 399-403). IEEE.
- Liao R, Wen H, Pan F, Song H, Xu A, Jiang Y. A novel physical layer authentication method with convolutional neural network. In2019 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA) 2019 Mar 29 (pp. 231-235). IEEE.
- Edfors O, Sandell M, Van de Beek JJ, Wilson SK, Borjesson PO. OFDM channel estimation by singular value decomposition. IEEE Transactions on communications. 1998 Jul 31;46(7):931-9.
- Van De Beek JJ, Edfors O, Sandell M, Wilson SK, Borjesson PO. On channel estimation in OFDM systems. In1995 IEEE 45th vehicular technology conference. Countdown to the wireless twenty-first century 1995 Jul 25 (Vol. 2, pp. 815-819). IEEE.
- Coleri S, Ergen M, Puri A, Bahai A. Channel estimation techniques based on pilot arrangement in OFDM systems. IEEE Transactions on broadcasting. 2002 Sep 30;48(3):223-9.
- Li Y. Pilot-symbol-aided channel estimation for OFDM in wireless systems. In1999 IEEE 49th Vehicular Technology Conference (Cat. No. 99CH36363) 1999 May 16 (Vol. 2, pp. 1131-1135). IEEE.
- Marzetta TL. Noncooperative cellular wireless with unlimited numbers of base station antennas. IEEE transactions on wireless communications. 2010 Oct 7;9(11):3590-600.
- Björnson E, Hoydis J, Sanguinetti L. Massive MIMO networks: Spectral, energy, and hardware efficiency. Foundations and TrendsŴ in Signal Processing. 2017 Nov 15;11(3-4):154-655.
- Wen CK, Shih WT, Jin S. Deep learning for massive MIMO CSI feedback. IEEE Wireless Communications Letters. 2018 Mar 22;7(5):748-51.
- O’shea T, Hoydis J. An introduction to deep learning for the physical layer. IEEE Transactions on Cognitive Communications and Networking. 2017 Oct 2;3(4):563-75.
- Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser Ł, Polosukhin I. Attention is all you need. Advances in neural information processing systems. 2017;30.
- Alkhateeb A, El Ayach O, Leus G, Heath RW. Channel estimation and hybrid precoding for millimeter wave cellular systems. IEEE journal of selected topics in signal processing. 2014 Jul 1;8(5):831-46.
- Biguesh M, Gershman AB. Training-based MIMO channel estimation: A study of estimator tradeoffs and optimal training signals. IEEE transactions on signal processing. 2006 Mar 31;54(3):884-93.
- Bajwa WU, Haupt J, Sayeed AM, Nowak R. Compressed channel sensing: A new approach to estimating sparse multipath channels. Proceedings of the IEEE. 2010 Apr 26;98(6):1058-76.
- LeCun Y, Bengio Y, Hinton G. Deep learning. nature. 2015 May 28;521(7553):436-44.
- Ye H, Liang L, Li GY, Juang BH. Deep learning-based end-to-end wireless communication systems with conditional GANs as unknown channels. IEEE Transactions on Wireless Communications. 2020 Feb 6;19(5):3133-43.
- Heath RW, Gonzalez-Prelcic N, Rangan S, Roh W, Sayeed AM. An overview of signal processing techniques for millimeter wave MIMO systems. IEEE journal of selected topics in signal processing. 2016 Feb 8;10(3):436-53.
How to cite this article
@article{JakhaniyaP2026,
author = {Parth Jakhaniya and Ashish Pandya and Rizwan Alad and Nirav Desai and Purvang Dalal},
title = {Machine Learning-Based Channel Estimation for 5G NR Systems: A Comprehensive Review of TDL/CDL Channel Models and CNN Architectures},
journal = {International Journal of Telecommunications & Emerging Technologies},
year = {2026},
volume = {12},
number = {02},
issn = {2455-0345},
url = {https://journalspub.com/publication/ijtet/article=27613}
}