Deep Autoencoder Based CSI Feedback with Feedback Errors and Feedback Delay in FDD Massive MIMO Systems

Youngrok Jang, Gyuyeol Kong, Minchae Jung, Sooyong Choi, Il Min Kim

Research output: Contribution to journalArticle

Abstract

In this letter, we study the channel state information (CSI) feedback based on the deep autoencoder (AE) considering the feedback errors and feedback delay in the frequency division duplex massive multiple-input multiple-output system. We construct the deep AE by modeling the CSI feedback process, which involves feedback transmission errors and delays. The deep AE is trained by setting the delayed version of the downlink channel as the desired output. The proposed scheme reduces the impact of the feedback errors and feedback delay. Simulation results demonstrate that the proposed scheme achieves better performance than other comparable schemes.

Original languageEnglish
Article number8625537
Pages (from-to)833-836
Number of pages4
JournalIEEE Wireless Communications Letters
Volume8
Issue number3
DOIs
Publication statusPublished - 2019 Jun 1

Fingerprint

Channel state information
MIMO systems
Feedback

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Cite this

Jang, Youngrok ; Kong, Gyuyeol ; Jung, Minchae ; Choi, Sooyong ; Kim, Il Min. / Deep Autoencoder Based CSI Feedback with Feedback Errors and Feedback Delay in FDD Massive MIMO Systems. In: IEEE Wireless Communications Letters. 2019 ; Vol. 8, No. 3. pp. 833-836.
@article{53166740baba4d958cfaba884c81fb8f,
title = "Deep Autoencoder Based CSI Feedback with Feedback Errors and Feedback Delay in FDD Massive MIMO Systems",
abstract = "In this letter, we study the channel state information (CSI) feedback based on the deep autoencoder (AE) considering the feedback errors and feedback delay in the frequency division duplex massive multiple-input multiple-output system. We construct the deep AE by modeling the CSI feedback process, which involves feedback transmission errors and delays. The deep AE is trained by setting the delayed version of the downlink channel as the desired output. The proposed scheme reduces the impact of the feedback errors and feedback delay. Simulation results demonstrate that the proposed scheme achieves better performance than other comparable schemes.",
author = "Youngrok Jang and Gyuyeol Kong and Minchae Jung and Sooyong Choi and Kim, {Il Min}",
year = "2019",
month = "6",
day = "1",
doi = "10.1109/LWC.2019.2895039",
language = "English",
volume = "8",
pages = "833--836",
journal = "IEEE Wireless Communications Letters",
issn = "2162-2337",
publisher = "IEEE Communications Society",
number = "3",

}

Deep Autoencoder Based CSI Feedback with Feedback Errors and Feedback Delay in FDD Massive MIMO Systems. / Jang, Youngrok; Kong, Gyuyeol; Jung, Minchae; Choi, Sooyong; Kim, Il Min.

In: IEEE Wireless Communications Letters, Vol. 8, No. 3, 8625537, 01.06.2019, p. 833-836.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Deep Autoencoder Based CSI Feedback with Feedback Errors and Feedback Delay in FDD Massive MIMO Systems

AU - Jang, Youngrok

AU - Kong, Gyuyeol

AU - Jung, Minchae

AU - Choi, Sooyong

AU - Kim, Il Min

PY - 2019/6/1

Y1 - 2019/6/1

N2 - In this letter, we study the channel state information (CSI) feedback based on the deep autoencoder (AE) considering the feedback errors and feedback delay in the frequency division duplex massive multiple-input multiple-output system. We construct the deep AE by modeling the CSI feedback process, which involves feedback transmission errors and delays. The deep AE is trained by setting the delayed version of the downlink channel as the desired output. The proposed scheme reduces the impact of the feedback errors and feedback delay. Simulation results demonstrate that the proposed scheme achieves better performance than other comparable schemes.

AB - In this letter, we study the channel state information (CSI) feedback based on the deep autoencoder (AE) considering the feedback errors and feedback delay in the frequency division duplex massive multiple-input multiple-output system. We construct the deep AE by modeling the CSI feedback process, which involves feedback transmission errors and delays. The deep AE is trained by setting the delayed version of the downlink channel as the desired output. The proposed scheme reduces the impact of the feedback errors and feedback delay. Simulation results demonstrate that the proposed scheme achieves better performance than other comparable schemes.

UR - http://www.scopus.com/inward/record.url?scp=85068157497&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85068157497&partnerID=8YFLogxK

U2 - 10.1109/LWC.2019.2895039

DO - 10.1109/LWC.2019.2895039

M3 - Article

VL - 8

SP - 833

EP - 836

JO - IEEE Wireless Communications Letters

JF - IEEE Wireless Communications Letters

SN - 2162-2337

IS - 3

M1 - 8625537

ER -