ETRI-Knowledge Sharing Plaform

KOREAN
논문 검색
Type SCI
Year ~ Keyword

Detail

Journal Article Practical Denoising Autoencoder for CSI Feedback without Clean Target in Massive MIMO Networks
Cited 2 time in scopus Share share facebook twitter linkedin kakaostory
Authors
Anseok Lee, Hanjun Park, Yongjin Kwon, Heesoo Lee, Song Chong
Issue Date
2024-02
Citation
IEEE Wireless Communications Letters, v.13, no.2, pp.525-529
ISSN
2162-2337
Publisher
IEEE Communications Society
Language
English
Type
Journal Article
DOI
https://dx.doi.org/10.1109/LWC.2023.3334736
Abstract
In this letter, we present a novel approach for denoising channel state information (CSI) feedback in massive multiple-input multiple-output (MIMO) cellular networks. Our method utilizes Deep Learning (DL) techniques to compress and remove noise from measured CSI. Traditional DL-based denoising requires pairs of noisy input and corresponding clean targets, which are impractical to obtain in real-world wireless networks. To address this challenge, we propose a training method of denoising autoencoder using pairs of noisy CSIs and practical data acquisition strategies. Extensive evaluations demonstrate the superior reconstruction performance of our method compared to a vanilla autoencoder and legacy codebook-based CSI feedback.
KSP Keywords
CSI Feedback, Cellular networks, Channel State Information(CSI), Data Acquisition(DAQ), MIMO networks, Multiple input multiple output(MIMO), Novel approach, Real-world, Reconstruction performance, Wireless network, deep learning(DL)