IEICE TRANSACTIONS on Fundamentals
Open Access
CsiNet-Plus Model with Truncation and Noise on CSI Feedback
-
Full Text Views
7
- Cite this
- Free PDF (430.5KB)
Summary :
For the frequency-division-duplex (FDD)-based massive multiple-input multiple-output (MIMO) systems, channel state information (CSI) feedback plays a critical role. Although deep learning has been used to compress the CSI feedback, some issues like truncation and noise still need further investigation. Facing these practical concerns, we propose an improved model (called CsiNet-Plus), which includes a truncation process and a channel noise process. Simulation results demonstrate that the CsiNet-Plus outperforms the existing CsiNet. The performance interchangeability between truncated decimal digits and the signal-to-noise-ratio helps support flexible configuration.
- Publication
- IEICE TRANSACTIONS on Fundamentals Vol.E103-A No.1 pp.376-381
- Publication Date
- 2020/01/01
- Publicized
- Online ISSN
- 1745-1337
- DOI
- 10.1587/transfun.2019EAL2123
- Type of Manuscript
- LETTER
- Category
- Communication Theory and Signals
Authors
Feng LIU
Shanghai Maritime University
Xuecheng HE
Shanghai Maritime University
Conggai LI
Shanghai Maritime University
Yanli XU
Shanghai Maritime University
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Feng LIU, Xuecheng HE, Conggai LI, Yanli XU, "CsiNet-Plus Model with Truncation and Noise on CSI Feedback" in IEICE TRANSACTIONS on Fundamentals,
vol. E103-A, no. 1, pp. 376-381, January 2020, doi: 10.1587/transfun.2019EAL2123.
Abstract: For the frequency-division-duplex (FDD)-based massive multiple-input multiple-output (MIMO) systems, channel state information (CSI) feedback plays a critical role. Although deep learning has been used to compress the CSI feedback, some issues like truncation and noise still need further investigation. Facing these practical concerns, we propose an improved model (called CsiNet-Plus), which includes a truncation process and a channel noise process. Simulation results demonstrate that the CsiNet-Plus outperforms the existing CsiNet. The performance interchangeability between truncated decimal digits and the signal-to-noise-ratio helps support flexible configuration.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.2019EAL2123/_p
Copy
@ARTICLE{e103-a_1_376,
author={Feng LIU, Xuecheng HE, Conggai LI, Yanli XU, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={CsiNet-Plus Model with Truncation and Noise on CSI Feedback},
year={2020},
volume={E103-A},
number={1},
pages={376-381},
abstract={For the frequency-division-duplex (FDD)-based massive multiple-input multiple-output (MIMO) systems, channel state information (CSI) feedback plays a critical role. Although deep learning has been used to compress the CSI feedback, some issues like truncation and noise still need further investigation. Facing these practical concerns, we propose an improved model (called CsiNet-Plus), which includes a truncation process and a channel noise process. Simulation results demonstrate that the CsiNet-Plus outperforms the existing CsiNet. The performance interchangeability between truncated decimal digits and the signal-to-noise-ratio helps support flexible configuration.},
keywords={},
doi={10.1587/transfun.2019EAL2123},
ISSN={1745-1337},
month={January},}
Copy
TY - JOUR
TI - CsiNet-Plus Model with Truncation and Noise on CSI Feedback
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 376
EP - 381
AU - Feng LIU
AU - Xuecheng HE
AU - Conggai LI
AU - Yanli XU
PY - 2020
DO - 10.1587/transfun.2019EAL2123
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E103-A
IS - 1
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - January 2020
AB - For the frequency-division-duplex (FDD)-based massive multiple-input multiple-output (MIMO) systems, channel state information (CSI) feedback plays a critical role. Although deep learning has been used to compress the CSI feedback, some issues like truncation and noise still need further investigation. Facing these practical concerns, we propose an improved model (called CsiNet-Plus), which includes a truncation process and a channel noise process. Simulation results demonstrate that the CsiNet-Plus outperforms the existing CsiNet. The performance interchangeability between truncated decimal digits and the signal-to-noise-ratio helps support flexible configuration.
ER -
English
