EVCsiNet: Eigenvector-Based CSI Feedback Under 3GPP Link-Level Channels

被引：21

作者：

Liu, Wendong ^{[1
]}

Tian, Wenqiang ^{[1
]}

Xiao, Han ^{[1
]}

Jin, Shi ^{[2
]}

Liu, Xiaofeng ^{[3
]}

Shen, Jia ^{[1
]}

机构：

[1] OPPO, Dept Stand Res, Beijing 100026, Peoples R China

[2] Southeast Univ, Natl Mobile Commun Res Lab, Nanjing 210096, Peoples R China

[3] China Acad Informat & Commun Technol, Mobile Commun Innovat Ctr, Beijing 100191, Peoples R China

来源：

IEEE WIRELESS COMMUNICATIONS LETTERS | 2021年 / 10卷 / 12期

关键词：

Decoding; 3GPP; Downlink; Channel models; 5G mobile communication; Training; Quantization (signal); CSI feedback; deep learning; eigenvector; 3GPP channel;

D O I：

10.1109/LWC.2021.3112747

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Recently, deep learning based methods have been widely used for wireless communications. In this letter, different from current researches considering full channel state information (F-CSI) feedback, the eigenvector based CSI feedback with deep learning approach is proposed, referred to as EVCsiNet, where the joint eigenvector concatenated from multiple subbands is compressed and recovered at the encoder and decoder, respectively. Simulation results verify the superiority of our schemes over CSI recovery accuracy and feedback overhead compared with conventional methods using codebooks on link-level channel models in different scenarios.

引用

页码：2688 / 2692

页数：5

共 10 条

[1] 3GPP, 2020, 38214 3GPP NR
[2] [Anonymous], 2020, 38901V1610 3GPP TR
[3] Cheng T. S., 2019, 2019 Compound Semiconductor Week (CSW), DOI 10.1109/ICIPRM.2019.8819142
[4] Guo Jiajia, 2020, [Journal of Communications and Information Networks, 通信与信息网络学报], V5, P310
[5] Guo JJ, 2020, IEEE T WIREL COMMUN, V19, P2827, DOI [10.1109/TNSE.2020.2997359, 10.1109/TWC.2020.2968430]
[6] Deep Residual Learning for Image Recognition
He, Kaiming
Zhang, Xiangyu
Ren, Shaoqing
Sun, Jian
[J]. 2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, : 770 - 778
[7] MIMO Channel Information Feedback Using Deep Recurrent Network
Lu, Chao
Xu, Wei
Shen, Hong
Zhu, Jun
Wang, Kezhi
[J]. IEEE COMMUNICATIONS LETTERS, 2019, 23 (01) : 188 - 191
[8] Deep Learning for Wireless Physical Layer: Opportunities and Challenges
Wang, Tianqi
Wen, Chao-Kai
Wang, Hanqing
Gao, Feifei
Jiang, Tao
Jin, Shi
[J]. CHINA COMMUNICATIONS, 2017, 14 (11) : 92 - 111
[9] Deep Learning for Massive MIMO CSI Feedback
Wen, Chao-Kai
Shih, Wan-Ting
Jin, Shi
[J]. IEEE WIRELESS COMMUNICATIONS LETTERS, 2018, 7 (05) : 748 - 751
[10] Xiao H., 2021, ENLIGHTENS WIRELESS

← 1 →