Deep Learning-aided Channel Estimation Combined with Advanced Pilot Assignment Algorithm to Mitigate Pilot Contamination for Cell-Free Networks

Swapnaja Deshpande; Mona Aggarwal; Pooja Sabherwal; Swaran Ahuja

doi:10.17485/IJST/v17i5.2961

Article

Deep Learning-aided Channel Estimation Combined with Advanced Pilot Assignment Algorithm to Mitigate Pilot Contamination for Cell-Free Networks

VIEWS 166
PDF 39

Indian Journal of Science and Technology

DOI: 10.17485/IJST/v17i5.2961

Year: 2024, Volume: 17, Issue: 5, Pages: 465-477

Original Article

Deep Learning-aided Channel Estimation Combined with Advanced Pilot Assignment Algorithm to Mitigate Pilot Contamination for Cell-Free Networks

Swapnaja Deshpande¹, Mona Aggarwal^1*, Pooja Sabherwal¹, Swaran Ahuja¹

¹MDE Department, The NorthCap University, Gurgaon, Haryana, India

*Corresponding Author
Email: [email protected]

Received Date:21 November 2023, Accepted Date:28 December 2023, Published Date:31 January 2024

This work is licensed under a Creative Commons Attribution 4.0 International License.

Abstract

Objectives: The performance of Cell-Free Massive Multiple Input Multiple Output (CFMM) is analyzed in this paper for its two bottlenecks i.e., Pilot Contamination (PC) and Channel Estimation Error (CEE). Methods: The CFMM network is strongly affected by PC which is one of the bottlenecks due to which quality of service and accuracy of channel estimation gets impacted. Therefore, we address this problem by presenting advanced pilot assignment algorithm to mitigate PC and deep learning aided channel estimation for reducing CEE for the CFMM systems to maximize spectral efficiency (SE). We derive achievable uplink and downlink SE expressions for the proposed system, and compare with Minimum Mean Square Error and Maximum Ratio combining techniques. As well, the performance is evaluated for different antenna configurations. The advanced pilot assignment algorithm is compared with greedy pilot assignment and random pilot assignment methods. The performance of cellular massive multiple input multiple output (MIMO) is derived for comparison. The performance of CFMM system is evaluated using MATLAB software. Findings: The UL and DL performance of the proposed system in terms of SE is 3.2 times higher than the conventional CFMM with MMSE and MR combining techniques. Average sum spectral efficiency of the proposed system increases with increase in number of access points (APs). Comparison with different antenna configurations reveals that, with 400 APs equipped with single antenna, only UE with good channel condition shows performance enhancement, but when each AP is equipped with 4 antennas, the UE with unfavourable channel condition also give better performance. Advanced pilot assignment scheme proves to be better than greedy and random pilot assignment techniques. For the same cellular set up, the proposed CFMM system achieves higher SE than the cellular massive MIMO. Novelty: Due to the advanced pilot assignment algorithm used in the proposed CFMM system, at a time, only one AP is selected and the selected AP with its full received power serves the desired UE, which suppresses interference resulting in improved SE performance. The serving AP is selected considering the distance between UE and AP, rather than using large scale fading coefficient which is the unique feature of pilot assignment algorithm. The proposed deep learning-aided channel estimation method, minimizes the mean square error (MSE) between the actual channel and the channel estimates obtained from the MMSE estimation resulting in reduction in channel estimation error. Thus, the use of the proposed advanced pilot assignment algorithm and deep learning-aided channel estimation method increase the SE performance of the CFMM system.

Keywords: CellFree Massive Multiple Input Multiple Output, Pilot Contamination, Channel Estimation Error, Minimum Mean Square Error, Maximum Ratio

References

Khanna H, Aggarwal M, Ahuja S. Statistical characteristics and performance evaluation of FSO links with misalignment fading influenced by correlated sways. AEU - International Journal of Electronics and Communications. 2018;85:118–125. Available from: https://doi.org/10.1016/j.aeue.2017.12.032
Sharma R, Aggarwal M, Ahuja S. Performance Analysis of Indoor FSO Communication Systems under Receiver Mobility. In: 2016 International Conference on Micro-Electronics and Telecommunication Engineering (ICMETE). (pp. 652-657) IEEE. 2017.
Aggarwal M, Garg P, Puri P, Sharma PK. Performance analysis of optical wireless communication system with a decode and forward relay. In: 2014 International Conference on Signal Processing and Integrated Networks (SPIN). (pp. 333-337) IEEE. 2014.
Xu S, Cao Y, Li C, Wang D, Yang L. Spanning Tree Method for Over-the-Air Channel Calibration in 6G Cell-Free Massive MIMO. IEEE Transactions on Wireless Communications. 2023;22(8):5567–5582. Available from: https://doi.org/10.1109/TWC.2023.3235355
Wang CXX, You X, Gao X, Zhu X, Li Z, Zhang C, et al. On the Road to 6G: Visions, Requirements, Key Technologies, and Testbeds. IEEE Communications Surveys & Tutorials. 2023;25(2):905–974. Available from: https://doi.org/10.1109/COMST.2023.3249835
Murthy KC, Mandi MV, Murali R. Performance evaluation of chaotic spreading codes in massive MIMO OFDM system. Indian Journal of Science and Technology. 2020;13(42):4374–4385. Available from: https://doi.org/10.17485/IJST/v13i42.2027
Matta JCP, Siddiah P. A Modified OMP Algorithm with Reduced Feedback Overhead for Massive MIMO System. Indian Journal of Science and Technology. 2021;14(33):2663–2670. Available from: https://doi.org/10.17485/IJST/v14i33.1442
Abose TA, Olwal TO, Hassen MR. Hybrid Beamforming for Millimeter Wave Massive MIMO under Multicell Multiuser Environment. Indian Journal of Science and Technology. 2022;15(20):1001–1011. Available from: https://doi.org/10.17485/IJST/v15i20.114
Obakhena HI, Imoize AL, Anyasi FI, Kavitha KVN. Application of cell-free massive MIMO in 5G and beyond 5G wireless networks: a survey. Journal of Engineering and Applied Science. 2021;68(1):1–41. Available from: https://doi.org/10.1186/s44147-021-00014-y
Bjornson E, Sanguinetti L. Making Cell-Free Massive MIMO Competitive With MMSE Processing and Centralized Implementation. IEEE Transactions on Wireless Communications. 2020;19(1):77–90. Available from: https://doi.org/10.1109/TWC.2019.2941478
Gkonis PK. A Survey on Machine Learning Techniques for Massive MIMO Configurations: Application Areas, Performance Limitations and Future Challenges. IEEE Access. 2022;11:67–88. Available from: https://doi.org/10.1109/ACCESS.2022.3232855
Shukla NK, Garg A, Bhutto J, Aggarwal M, Raja MR, Hussein HS, et al. An insight into the prediction of mechanical properties of concrete using machine learning techniques. Computers and Concrete. 2023;32(3):263–286. Available from: https://doi.org/10.12989/cac.2023.32.3.263
Liu H, Zhang J, Jin S, Ai B. Graph Coloring Based Pilot Assignment for Cell-Free Massive MIMO Systems. IEEE Transactions on Vehicular Technology. 2020;69(8):9180–9184. Available from: https://doi.org/10.1109/TVT.2020.3000496
Deshpande S, Sharma P, Aggarwal M, Ahuja S. Mitigating pilot contamination in Rician faded massive MIMO 5G systems using enhanced zero forcing precoding and ring partitioning. Physical Communication. 2021;49:101467. Available from: https://doi.org/10.1016/j.phycom.2021.101467
Victor CM, Mvuma AN, Mrutu SI. Multi‐input fully CNN for joint pilot decontamination and symbol detection in 5G massive MIMO. IET Communications. 2023;17(16):1899–1906. Available from: https://doi.org/10.1049/cmu2.12670
Polegre AA, Sanguinetti L, Armada AG. Pilot Decontamination Processing in Cell-Free Massive MIMO. IEEE Communications Letters. 2021;25(12):3990–3994. Available from: https://doi.org/10.1109/LCOMM.2021.3118890
Ayidh AA, Sambo Y, Imran MA. Mitigation pilot contamination based on matching technique for uplink cell-free massive MIMO systems. Scientific Reports. 2022;12(1):1–14. Available from: https://doi.org/10.1038/s41598-022-21241-0
Zheng J, Zhang J, Bjornson E, Ai B. Cell-Free Massive MIMO with Channel Aging and Pilot Contamination. In: GLOBECOM 2020 - 2020 IEEE Global Communications Conference. (pp. 1-6) IEEE. 2021.
Misso A, Kissaka M, Maiseli B. Exploring pilot assignment methods for pilot contamination mitigation in massive MIMO systems. Cogent Engineering. 2020;7(1):1–19. Available from: https://doi.org/10.1080/23311916.2020.1831126
Shi E, Zhang J, Du Y, Wang Z, Ai B, Ng DWK. Spatially Correlated RIS-Aided CF Massive MIMO Systems With Generalized MR Combining. IEEE Transactions on Vehicular Technology. 2022;71(10):11245–11250. Available from: https://doi.org/10.1109/TVT.2022.3186077
Bjornson E, Sanguinetti L. Scalable Cell-Free Massive MIMO Systems. IEEE Transactions on Communications. 2020;68(7):4247–4261. Available from: https://doi.org/10.1109/TCOMM.2020.2987311
Ha AL, Chien TV, Nguyen TH, Choi WH, Nguyen VD. Deep Learning-Aided 5G Channel Estimation. In: 2021 15th International Conference on Ubiquitous Information Management and Communication (IMCOM). (pp. 1-7) IEEE. 2021.
Ozdogan O, Bjornson E, Zhang J. Performance of Cell-Free Massive MIMO With Rician Fading and Phase Shifts. IEEE Transactions on Wireless Communications. 2019;18(11):5299–5315. Available from: https://doi.org/10.1109/TWC.2019.2935434
Dey A, Pattanayak P, Gurjar DS. Arithmetic/Geometric Progression Based Pilot Allocation With Antenna Scheduling for Massive MIMO Cellular Systems. IEEE Networking Letters. 2021;3(1):1–4. Available from: https://doi.org/10.1109/LNET.2021.3054644

Copyright

© 2024 Deshpande et al. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Published By Indian Society for Education and Environment (iSee)