Unlock instant, AI-driven research and patent intelligence for your innovation.

A Neural Network-Based Feedback Method for CSI Multi-Rate Compression of Large-Scale MIMO

A neural network, multi-magnification technology, applied in the field of communication, can solve problems such as the inability to achieve variable magnification compression feedback, and achieve the effect of improving reconstruction accuracy, reducing parameters, and reducing storage space

Active Publication Date: 2021-03-16
SOUTHEAST UNIV
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to overcome the deficiencies of the prior art, the present invention provides a CSI multi-rate compression feedback method based on neural network massive MIMO to solve the problem that the existing CsiNet model cannot realize variable rate compression feedback, and based on the theory of CsiNet The network design has been improved

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A Neural Network-Based Feedback Method for CSI Multi-Rate Compression of Large-Scale MIMO
  • A Neural Network-Based Feedback Method for CSI Multi-Rate Compression of Large-Scale MIMO
  • A Neural Network-Based Feedback Method for CSI Multi-Rate Compression of Large-Scale MIMO

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] Below in conjunction with accompanying drawing, technical scheme of the present invention is described in further detail:

[0035] Such as figure 1 As shown, the present invention has designed a kind of CSI multi-rate compression feedback method based on massive MIMO of neural network, and this method specifically comprises the following steps:

[0036] Step 1: At the user end, the channel matrix of the MIMO channel state information in the space-frequency domain Do a two-dimensional discrete Fourier transform to obtain a sparse channel matrix H in the angular delay domain;

[0037] Step 2: Construct an improved model CsiNet+ based on CsiNet, including an encoder and a decoder, and introduce the series multi-rate compression framework SM-CsiNet+ and the parallel multi-rate compression framework PM-CsiNet+, that is, introduce series or parallel multi-rates at the user end The compression encoder implements a variable rate compression encoder, and encodes the channel m...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a neural network-based large-scale MIMO CSI multi-rate compression feedback method, including: two network design principles for CSI feedback are proposed, and a new network architecture CsiNet+ is introduced according to these principles, and two Two different variable-rate compression frameworks, namely, the series multi-rate compression framework SM‑CsiNet+ and the parallel multi-rate compression framework PM‑CsiNet+. The invention can greatly reduce the parameters of the CSI feedback network, reduce the storage space of the user end, improve the feasibility of the system, and at the same time improve the reconstruction accuracy, and realize the variability of the compression rate in different scenarios.

Description

technical field [0001] The invention relates to a neural network-based large-scale MIMO CSI multi-rate compression feedback method, which belongs to the technical field of communication. Background technique [0002] The massive MIMO (multiple-input multiple-output) system has been recognized as a key technology for 5G and above communication systems. In a massive MIMO system, the base station is equipped with a large number of antennas, which can recover the information received from the user in the case of low signal-to-noise ratio (SNR), and provide services for multiple users at the same time. However, to obtain these potential benefits, accurate channel state information (CSI) needs to be obtained at the base station side. For the uplink, the base station can obtain accurate CSI by performing channel estimation on the pilot frequency sent by the user terminal. However, downlink CSI is difficult to realize, especially for the Frequency Division Duplex (FDD) system whic...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): H04B7/0413H04B7/06H03M7/30G06N3/04G06N3/08
CPCH04B7/0413H04B7/0626H03M7/6005H03M7/6011H03M7/70G06N3/08G06N3/045
Inventor 金石郭佳佳陈彤温朝凯
Owner SOUTHEAST UNIV