Deep Channel Learning For Large Intelligent Surfaces Aided mm-Wave Massive MIMO Systems

Ahmet M. Elbir; Anastasios Papazafeiropoulos; Pandelis Kourtessis; Symeon Chatzinotas; John Senior

doi:10.1109/LWC.2020.2993699

Deep Channel Learning For Large Intelligent Surfaces Aided mm-Wave Massive MIMO Systems

Ahmet M. Elbir, Anastasios Papazafeiropoulos, Pandelis Kourtessis, Symeon Chatzinotas, John Senior

Research output: Contribution to journal › Article › peer-review

215 Citations (Scopus)

70 Downloads (Pure)

Abstract

This letter presents the first work introducing a deep learning (DL) framework for channel estimation in large intelligent surface (LIS) assisted massive MIMO (multiple-input multiple-output) systems. A twin convolutional neural network (CNN) architecture is designed and it is fed with the received pilot signals to estimate both direct and cascaded channels. In a multi-user scenario, each user has access to the CNN to estimate its own channel. The performance of the proposed DL approach is evaluated and compared with state-of-the-art DL-based techniques and its superior performance is demonstrated.

Original language	English
Article number	9090876
Pages (from-to)	1447-1451
Number of pages	5
Journal	IEEE Wireless Communications Letters
Volume	9
Issue number	9
Early online date	11 May 2020
DOIs	https://doi.org/10.1109/LWC.2020.2993699
Publication status	Published - Sept 2020

Keywords

Deep learning
channel estimation
large intelligent surfaces
massive MIMO

Access to Document

10.1109/LWC.2020.2993699Licence: Unspecified

Deep Channel Learning For Large Intelligent Surfaces Aided mm_Wave Massive MIMO Systems
© 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Accepted author manuscript, 566 KBLicence: Unspecified

Cite this

@article{b9b1de89808f40e28b243965b1cc72a6,

title = "Deep Channel Learning For Large Intelligent Surfaces Aided mm-Wave Massive MIMO Systems",

abstract = "This letter presents the first work introducing a deep learning (DL) framework for channel estimation in large intelligent surface (LIS) assisted massive MIMO (multiple-input multiple-output) systems. A twin convolutional neural network (CNN) architecture is designed and it is fed with the received pilot signals to estimate both direct and cascaded channels. In a multi-user scenario, each user has access to the CNN to estimate its own channel. The performance of the proposed DL approach is evaluated and compared with state-of-the-art DL-based techniques and its superior performance is demonstrated.",

keywords = "Deep learning, channel estimation, large intelligent surfaces, massive MIMO",

author = "Elbir, {Ahmet M.} and Anastasios Papazafeiropoulos and Pandelis Kourtessis and Symeon Chatzinotas and John Senior",

note = "{\textcopyright} 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.",

year = "2020",

month = sep,

doi = "10.1109/LWC.2020.2993699",

language = "English",

volume = "9",

pages = "1447--1451",

journal = "IEEE Wireless Communications Letters",

publisher = "IEEE Communications Society",

number = "9",

}

TY - JOUR

T1 - Deep Channel Learning For Large Intelligent Surfaces Aided mm-Wave Massive MIMO Systems

AU - Elbir, Ahmet M.

AU - Papazafeiropoulos, Anastasios

AU - Kourtessis, Pandelis

AU - Chatzinotas, Symeon

AU - Senior, John

N1 - © 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

PY - 2020/9

Y1 - 2020/9

N2 - This letter presents the first work introducing a deep learning (DL) framework for channel estimation in large intelligent surface (LIS) assisted massive MIMO (multiple-input multiple-output) systems. A twin convolutional neural network (CNN) architecture is designed and it is fed with the received pilot signals to estimate both direct and cascaded channels. In a multi-user scenario, each user has access to the CNN to estimate its own channel. The performance of the proposed DL approach is evaluated and compared with state-of-the-art DL-based techniques and its superior performance is demonstrated.

AB - This letter presents the first work introducing a deep learning (DL) framework for channel estimation in large intelligent surface (LIS) assisted massive MIMO (multiple-input multiple-output) systems. A twin convolutional neural network (CNN) architecture is designed and it is fed with the received pilot signals to estimate both direct and cascaded channels. In a multi-user scenario, each user has access to the CNN to estimate its own channel. The performance of the proposed DL approach is evaluated and compared with state-of-the-art DL-based techniques and its superior performance is demonstrated.

KW - Deep learning

KW - channel estimation

KW - large intelligent surfaces

KW - massive MIMO

UR - http://www.scopus.com/inward/record.url?scp=85091179272&partnerID=8YFLogxK

U2 - 10.1109/LWC.2020.2993699

DO - 10.1109/LWC.2020.2993699

M3 - Article

VL - 9

SP - 1447

EP - 1451

JO - IEEE Wireless Communications Letters

JF - IEEE Wireless Communications Letters

IS - 9

M1 - 9090876

ER -

Deep Channel Learning For Large Intelligent Surfaces Aided mm-Wave Massive MIMO Systems

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this