King's College London

Research portal

Recurrent Neural Network Channel Estimation Using Measured Massive MIMO Data

Research output: Chapter in Book/Report/Conference proceedingConference paper

Standard

Recurrent Neural Network Channel Estimation Using Measured Massive MIMO Data. / Faghanimakrani, Termeh; Aghvami, Abdol-Hamid; Shojaeifard, Arman; Wong, Kai-Kit.

2020 IEEE 31st Annual International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC). 2020.

Research output: Chapter in Book/Report/Conference proceedingConference paper

Harvard

Faghanimakrani, T, Aghvami, A-H, Shojaeifard, A & Wong, K-K 2020, Recurrent Neural Network Channel Estimation Using Measured Massive MIMO Data. in 2020 IEEE 31st Annual International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC).

APA

Faghanimakrani, T., Aghvami, A-H., Shojaeifard, A., & Wong, K-K. (2020). Recurrent Neural Network Channel Estimation Using Measured Massive MIMO Data. In 2020 IEEE 31st Annual International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC)

Vancouver

Faghanimakrani T, Aghvami A-H, Shojaeifard A, Wong K-K. Recurrent Neural Network Channel Estimation Using Measured Massive MIMO Data. In 2020 IEEE 31st Annual International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC). 2020

Author

Faghanimakrani, Termeh ; Aghvami, Abdol-Hamid ; Shojaeifard, Arman ; Wong, Kai-Kit. / Recurrent Neural Network Channel Estimation Using Measured Massive MIMO Data. 2020 IEEE 31st Annual International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC). 2020.

Bibtex Download

@inbook{95c3522e820a4333b0d406bcc05eae51,
title = "Recurrent Neural Network Channel Estimation Using Measured Massive MIMO Data",
abstract = "In this work, we develop a novel channel estimationmethod using recurrent neural networks (RNNs) for massivemultiple-input multiple-output (MIMO) systems. The proposedframework alleviates the need for channel-state-information(CSI) feedback and pilot assignment through exploiting theinherent time and frequency correlations in practical propagationenvironments. We carry out the analysis using empirical MIMOchannel measurements between a 64T64R active antenna systemand a state-of-the-art multi-antenna scanner for both mobileand stationary use-cases. We also capture and analyze similarMIMO channel data from a legacy 2T2R base station (BS)for comparison purposes. Our findings confirm the applicabilityof utilising the proposed RNN-based massive MIMO channelacquisition scheme particularly for channels with long timecoherence and hardening effects. In our practical setup, theproposed method reduced the number of pilots used by 25{\%}.",
author = "Termeh Faghanimakrani and Abdol-Hamid Aghvami and Arman Shojaeifard and Kai-Kit Wong",
year = "2020",
language = "English",
booktitle = "2020 IEEE 31st Annual International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC)",

}

RIS (suitable for import to EndNote) Download

TY - CHAP

T1 - Recurrent Neural Network Channel Estimation Using Measured Massive MIMO Data

AU - Faghanimakrani, Termeh

AU - Aghvami, Abdol-Hamid

AU - Shojaeifard, Arman

AU - Wong, Kai-Kit

PY - 2020

Y1 - 2020

N2 - In this work, we develop a novel channel estimationmethod using recurrent neural networks (RNNs) for massivemultiple-input multiple-output (MIMO) systems. The proposedframework alleviates the need for channel-state-information(CSI) feedback and pilot assignment through exploiting theinherent time and frequency correlations in practical propagationenvironments. We carry out the analysis using empirical MIMOchannel measurements between a 64T64R active antenna systemand a state-of-the-art multi-antenna scanner for both mobileand stationary use-cases. We also capture and analyze similarMIMO channel data from a legacy 2T2R base station (BS)for comparison purposes. Our findings confirm the applicabilityof utilising the proposed RNN-based massive MIMO channelacquisition scheme particularly for channels with long timecoherence and hardening effects. In our practical setup, theproposed method reduced the number of pilots used by 25%.

AB - In this work, we develop a novel channel estimationmethod using recurrent neural networks (RNNs) for massivemultiple-input multiple-output (MIMO) systems. The proposedframework alleviates the need for channel-state-information(CSI) feedback and pilot assignment through exploiting theinherent time and frequency correlations in practical propagationenvironments. We carry out the analysis using empirical MIMOchannel measurements between a 64T64R active antenna systemand a state-of-the-art multi-antenna scanner for both mobileand stationary use-cases. We also capture and analyze similarMIMO channel data from a legacy 2T2R base station (BS)for comparison purposes. Our findings confirm the applicabilityof utilising the proposed RNN-based massive MIMO channelacquisition scheme particularly for channels with long timecoherence and hardening effects. In our practical setup, theproposed method reduced the number of pilots used by 25%.

M3 - Conference paper

BT - 2020 IEEE 31st Annual International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC)

ER -

View graph of relations

© 2018 King's College London | Strand | London WC2R 2LS | England | United Kingdom | Tel +44 (0)20 7836 5454