Adaptive Compression of Massive MIMO Channel State Information With Deep Learning

被引：0

作者：

Mismar, Faris B. ^{[1
]}

Kaya, Aliye Ozge ^{[1
]}

机构：

[1] The authors are with the Technology Leadership, Nokia Bell Labs Consulting, Dallas, TX 75019 USA, and also with the Bell Labs Core Research, Nokia Bell Labs, Murray Hill, NJ 07974 USA

来源：

IEEE Networking Letters | 2024年 / 6卷 / 04期

关键词：

6G; artificial intelligence; autoencoders; channel compression; deep learning; massive MIMO;

D O I：

10.1109/LNET.2024.3475269

中图分类号：

学科分类号：

摘要：

This letter proposes the use of deep autoencoders to compress the channel information in a massive multiple input and multiple output (MIMO) system. Although autoencoders perform lossy compression, they still have adequate usefulness when applied to massive MIMO system channel state information (CSI) compression. To demonstrate their impact on the CSI, we measure the performance of the system under two different channel models for different compression ratios. We disclose a few practical considerations in using autoencoders for this propose. We show through simulation that the run-time complexity of this deep autoencoder is irrelative to the compression ratio and thus an adaptive compression rate is feasible with an optimal compression ratio depending on the channel model and the signal to noise ratio. © 2019 IEEE.

引用

页码：267 / 271

页数：4

共 18 条

[1]

Mismar F.B., AlAmmouri A., Alkhateeb A., Andrews J.G., Evans B.L., Deep learning predictive band switching in wireless networks, IEEE Trans. Wireless Commun., 20, 1, pp. 96-109, (2021)

[2]

Study on artificial intelligence (AI)/machine learning (ML) for NR air interface, Version 18. 0. 0, 3GPP, (2024)

[3]

Mismar F.B., Gundogan A., Kaya A.O., Chistyakov O., Deep learning for multi-user proactive beam handoff: A 6G application, IEEE Access, 11, pp. 46271-46282, (2023)

[4]

Mismar F.B., Evans B.L., Alkhateeb A., Deep reinforcement learning for 5G networks: Joint beamforming, power control, and interference coordination, IEEE Trans. Commun., 68, 3, pp. 1581-1592, (2020)

[5]

Zhang Y., Zhang X., Liu Y., Deep learning based CSI compression and quantization with high compression ratios in FDD massive MIMO systems, IEEE Wireless Commun. Lett., 10, 10, pp. 2101-2105, (2021)

[6]

Guo J., Wen C.-K., Jin S., Li G.Y., Overview of deep learningbased CSI feedback in massive MIMO systems, IEEE Trans. Commun., 70, 12, pp. 8017-8045, (2022)

[7]

Shehzad M.K., Rose L., Wesemann S., Assaad M., ML-based massive MIMO channel prediction: Does it work on real-world data?, IEEE Wireless Commun. Lett., 11, 4, pp. 811-815, (2022)

[8]

Liu H., Long K., A deep learning channel estimator for millimeterwave hybrid massive MIMO systems, IEEE Wireless Commun. Lett., 12, 12, pp. 2103-2107, (2023)

[9]

Son H., Cho Y.-H., Analysis of compressed CSI feedback in MISO systems, IEEE Wireless Commun. Lett., 8, 6, pp. 1671-1674, (2019)

[10]

← 1 2 →