A novel compression CSI feedback based on deep learning for FDD massive MIMO systems

Yuting Wang, Yibin Zhang, Jinlong Sun, Guan Gui, Tomoaki Ohtsuki, Fumiyuki Adachi

研究成果: Conference contribution

2 被引用数 (Scopus)

抄録

Accurate channel state information (CSI) is necessary for frequency-division duplexing (FDD) massive multi-input multi-output (MIMO) systems. Existing deep learning-based CSI feedback methods, e.g., CSI sensing and recovery neural network (CsiNet), designed based on an autoencoder architecture, achieves higher feedback accuracy and reconstruction speed. However, this network needs to be retrained due to different communication scenarios and channel conditions, which is costly in practical deployment. To solve this problem, this paper proposes a deep learning-based modular adaptive multiple-rate (MAMR) compression CSI feedback framework. Extra padding modules are added at the base station to pad compressed CSI into different compression rates into the same dimensions, thereby realizing a general autoencoder performing variable-rate compression. Simulation results are given to confirm the effectiveness of the proposed method in terms of normalized mean square error.

本文言語English
ホスト出版物のタイトル2021 IEEE Wireless Communications and Networking Conference, WCNC 2021
出版社Institute of Electrical and Electronics Engineers Inc.
ISBN(電子版)9781728195056
DOI
出版ステータスPublished - 2021
イベント2021 IEEE Wireless Communications and Networking Conference, WCNC 2021 - Nanjing, China
継続期間: 2021 3月 292021 4月 1

出版物シリーズ

名前IEEE Wireless Communications and Networking Conference, WCNC
2021-March
ISSN(印刷版)1525-3511

Conference

Conference2021 IEEE Wireless Communications and Networking Conference, WCNC 2021
国/地域China
CityNanjing
Period21/3/2921/4/1

ASJC Scopus subject areas

  • 工学(全般)

フィンガープリント

「A novel compression CSI feedback based on deep learning for FDD massive MIMO systems」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル