Title:
CSI COMPRESSION FEEDBACK METHOD BASED ON DEEP LEARNING
Document Type and Number:
WIPO Patent Application WO/2024/045689
Kind Code:
A1
Abstract:
Disclosed in the present invention is a channel state information (CSI) compression feedback solution based on deep learning. In a large-scale multiple-input multiple-output (MIMO) system, CSI is crucial for a base station to achieve high performance gain. In a frequency division duplexing (FDD) mode, a user equipment (UE) needs to estimate CSI and then feeds back same to a base station, and effective CSI compression can greatly reduce the cost of feedback. The present invention achieves effective CSI compression and reconstruction by using a neural network having a two-dimensional sequence-to-sequence (2D Seq2Seq) structure. A base station uses CSI data to train the parameters of the neural network, and, after the training is completed, deploys same at a user end and the base station end to achieve effective CSI compression and reconstruction. The present invention can achieve high-precision CSI compression and reconstruction, providing an efficient and stable channel state information feedback method for MIMO systems.
More Like This:
Inventors:
ZHANG ZHAOYANG (CN)
CHEN ZIRUI (CN)
CHEN ZIRUI (CN)
Application Number:
PCT/CN2023/093244
Publication Date:
March 07, 2024
Filing Date:
May 10, 2023
Export Citation:
Assignee:
UNIV ZHEJIANG (CN)
International Classes:
H04B7/06
Foreign References:
| CN115549742A | 2022-12-30 | |||
| CN108390706A | 2018-08-10 | |||
| CN109672464A | 2019-04-23 | |||
| US20200220593A1 | 2020-07-09 | |||
| US20210273707A1 | 2021-09-02 |
Other References:
CHEN ZIRUI; ZHANG ZHAOYANG; XIAO ZHUORAN: "Viewing the MIMO Channel as Sequence Rather than Image: A Seq2Seq Approach for Efficient CSI Feedback", 2022 IEEE WIRELESS COMMUNICATIONS AND NETWORKING CONFERENCE (WCNC), IEEE, 10 April 2022 (2022-04-10), pages 2292 - 2297, XP034123559, DOI: 10.1109/WCNC51071.2022.9771730
CHEN ZIRUI; ZHANG ZHAOYANG; XIAO ZHUORAN: "Viewing the MIMO Channel as Sequence Rather than Image: A Seq2Seq Approach for Efficient CSI Feedback", 2022 IEEE WIRELESS COMMUNICATIONS AND NETWORKING CONFERENCE (WCNC), IEEE, 10 April 2022 (2022-04-10), pages 2292 - 2297, XP034123559, DOI: 10.1109/WCNC51071.2022.9771730
CHEN ZIRUI; ZHANG ZHAOYANG; XIAO ZHUORAN: "Viewing the MIMO Channel as Sequence Rather than Image: A Seq2Seq Approach for Efficient CSI Feedback", 2022 IEEE WIRELESS COMMUNICATIONS AND NETWORKING CONFERENCE (WCNC), IEEE, 10 April 2022 (2022-04-10), pages 2292 - 2297, XP034123559, DOI: 10.1109/WCNC51071.2022.9771730
Attorney, Agent or Firm:
HANGZHOU QIUSHI PATENT OFFICE CO., LTD. (CN)
Download PDF:
Previous Patent: ANTI-SHORT-CIRCUIT SOLID-STATE BATTERY AND PREPARATION METHOD THEREFOR
Next Patent: MOVABLE JOINT-BASED DOUBLE PLUNGER PUMP
Next Patent: MOVABLE JOINT-BASED DOUBLE PLUNGER PUMP