Loading [MathJax]/extensions/MathMenu.js
Learning Based CSI Look Up Table: A Novel Vector Quantization Approach for High Accuracy CSI Reconstruction | IEEE Conference Publication | IEEE Xplore

Learning Based CSI Look Up Table: A Novel Vector Quantization Approach for High Accuracy CSI Reconstruction


Abstract:

To fully exploit the benefits of spatial multiplexing gains within Frequency Division Duplex (FDD) Multiple-Input Multiple-Output (MIMO) systems, the development of a rob...Show More

Abstract:

To fully exploit the benefits of spatial multiplexing gains within Frequency Division Duplex (FDD) Multiple-Input Multiple-Output (MIMO) systems, the development of a robust Channel State Information (CSI) feedback compression methodology with low over- the-air CSI overhead while achieving high reconstruction accuracy is critical. Such methodology must be able to effectively reduce communication overhead without compromising system level performance. Traditional codebook-based approach, as outlined in the 3rd Generation Partnership Project (3GPP) standards encounters significant challenges to balance air-interface overhead and computational complexity. In this paper, we introduce a novel and adaptable Deep Leaning (DL) based CSI codebook technique leveraging vector quantization known as the CSI-Look-Up Table (CSI-LUT). Our numerical results show that the CSI - L UT has potential in reducing > 90 % of CSI overhead for max rank 1 while still achieving better average reconstruction accuracy and system level performance than traditional codebook-based approach. We anticipate that such advancements will play a pivotal role in enhancing the efficiency and performance of CSI feedback in MIMO systems, contributing significantly to the evolving landscape of 5G and beyond.
Date of Conference: 09-13 June 2024
Date Added to IEEE Xplore: 20 August 2024
ISBN Information:

ISSN Information:

Conference Location: Denver, CO, USA
References is not available for this document.

I. Introduction

MIMO stands as a promising technique aimed at enhancing spectrum and energy efficiency in the context of next-generation wireless system [1], [2]. However, this advancement introduces new challenges, particularly with regard to base stations (B S). The next-generation B S (gNB) must acquire real-time CSI for precoding purposes, a requirement accentuated in FDD systems. Downlink CSI acquisition involves two primary steps. First, the UE estimates the downlink CSI by utilizing the received pilot signals transmitted by the BS. Subsequently, the UE relays this estimated downlink CSI to the BS via the uplink control channel. In the context of massive MIMO systems, where the BS is equipped with a large number of antennas, the resulting CSI dimension becomes extensive, necessitating significant feedback overhead.

Select All
1.
E. G. Larsson, O. Edfors, F. Tufvesson and T. L. Marzetta, "Massive MIMO for next generation wireless systems", IEEE Commun. Mag., vol. 52, no. 2, pp. 186-195, Feb. 2014.
2.
T. L. Marzetta and H. Yang, Fundamentals of Massive MIMO, Cam-bridge University Press, Feb. 2016.
3.
Z. Qin and H. Yin, "A review of codebooks for CSI Feedback in 5G new radio and beyond", arXiv preprint, Jun. 2023.
4.
P.-H. Kuo, H. Kung and P.-A. Ting, "Compressive sensing based channel feedback protocols for spatially-correlated massive antenna arrays", 2012 IEEE Wirel. Commun. and Netw. Conf. (WCNC), pp. 492-497, Jun. 2012.
5.
P. Liang, J. Fan, W. Shen, Z. Qin and G. Y. Li, "Deep learning and compressive sensing-based CSI feedback in FDD massive MIMO systems", IEEE Trans. Veh. Technol., vol. 69, no. 8, pp. 9217-9222, Aug. 2020.
6.
S. Jere, Y. Song, Y. Yi and L. Liu, "Distributed learning meets 6g: A communication and computing perspective", IEEE Wirel. Communic., vol. 30, no. 1, pp. 112-117, 2023.
7.
H. Huang, S. Guo, G. Gui, Z. Yang, J. Zhang, H. Sari, et al., "Deep learning for physical-layer 5g wireless techniques: Opportunities challenges and solutions", IEEE Wirel. Communic., vol. 27, no. 1, pp. 214-222, 2019.
8.
New SI: Study on Artificial Intelligence (AI)/Machine Learning (ML) for NR Air Interface. RP-213599 3 GPP Qualcomm RAN-94bis-e, Dec. 2021.
9.
Z. Cheng, H. Sun, M. Takeuchi and J. Katto, "Deep convolutional autoencoder-based lossy image compression", 2018 Picture Coding Symposium (PCS), pp. 253-257, 2018.
10.
Discussion on improving performance and robustness of vector quan-tization. R1–2306433 3 GPP Futurewei 3GPP TSG RAN1-112bis-e, April 2023.
11.
J. Guo, C.-K. Wen, S. Jin and X. Li, "AI for CSI feedback enhancement in 5G-advanced", IEEE Wirel. Commun., 2022.
12.
S. Ravula and S. Jain, "Deep autoencoder-based massive MIMO CSI feedback with quantization and entropy coding", 2021 IEEE Global Commun. Conf. (GLOBECOM), pp. 1-6, Feb. 2021.
13.
T. Wang, C.-K. Wen, S. Jin and G. Y. Li, "Deep learning-based CSI feedback approach for time-varying massive MIMO channels", IEEE Wirel. Commun. Lett., vol. 8, no. 2, pp. 416-419, Apr. 2018.
14.
S. Tang, J. Xia, L. Fan, X. Lei, W. Xu and A. Nallanathan, "Dilated convolution based CSI feedback compression for massive MIMO systems", IEEE Trans. Veh. Technol., vol. 71, no. 10, pp. 11216-11221, Oct. 2022.
15.
A. Van Den Oord, O. Vinyals et al., "Neural discrete representation learning", Advances in neural information processing systems, vol. 30, 2017.
16.
V. Rizzello, M. Nerini, M. Joham, B. Clerckx and W. Utschick, "User-driven adaptive csi feedback with ordered vector quantization", IEEE Wirel. Commun. Lett., 2023.
17.
J. Shen, X. Liang, X. Gu and L. Zhang, "Clustering algorithm-based quantization method for massive mimo csi feedback", IEEE Wirel. Commun. Lett., vol. 11, no. 10, pp. 2155-2159, 2022.
18.
Study on Artificial Intelligence (AI)/Machine Learning (ML) for NR Air Interface. R1–2205695 3 GPP Ad-hoc Chair (CMCC) RAN-109bis-e, May 2022.
19.
N. Jindal, "Mimo broadcast channels with finite-rate feedback", IEEE Trans. Inf. Theory, vol. 52, no. 11, pp. 5045-5060, 2006.
20.
Study on Channel Model for Frequencies from 0.5 to 100 GHz (Release 16). 3GPP TR 38.901 V16.1.0 Tech. Rep., Nov. 2020.
21.
Z. Qin and H. Yin, "A review of codebooks for csi feedback in 5 g new radio and beyond", arXiv preprint, 2023.

Contact IEEE to Subscribe

References

References is not available for this document.