A wireless channel feedback method assisted by AI-based environmental knowledge

A knowledge-assisted, wireless channel technology, applied in the field of communication, can solve the problems of high CSI feedback overhead and low quality, and achieve the effect of improving channel feedback quality and quality enhancement

Active Publication Date: 2022-07-26
SOUTHEAST UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide an AI-based environmental knowledge-assisted wireless channel feedback method, which makes full use of environmental knowledge through AI technology, and uses neural network-based The Refine module assists the feedback of downlink channels, improves the accuracy of channel feedback, and solves the problem of high overhead and low quality of CSI feedback

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 wireless channel feedback method assisted by AI-based environmental knowledge
  • A wireless channel feedback method assisted by AI-based environmental knowledge
  • A wireless channel feedback method assisted by AI-based environmental knowledge

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] The present invention will be further described below in conjunction with the accompanying drawings.

[0023] In the research of CSI feedback, it is found that the user's CSI is closely related to its environment, and CSI can be regarded as an expression under the influence of the environment. In a mobile communication system, users are constantly moving, possibly from one cell to another. The environment around a user in a mobile scenario is constantly changing, and its CSI is also ever-changing. However, in a mobile communication system, once the base station is erected on a tall building or an iron tower, it will not be easily moved. Therefore, the environment around the base station is relatively fixed. Therefore, if such environmental knowledge can be introduced into the CSI feedback, the accuracy of the feedback can certainly be improved. Since CSI feedback based on the autoencoder architecture is difficult to enter the relevant standards in recent years, it is...

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 present invention discloses an AI-based environmental knowledge-assisted wireless channel feedback method, comprising the following steps: (1) quantifying feedback downlink channel state information according to the codebook-based feedback architecture of the existing system; (2) collecting a large number of downlink channels The data h and the corresponding codebook output (3) are constructed as input and h is the output of a neural network; (4) Use the data collected in step (2) to train the neural network constructed in step (3); (5) The user first feeds back the index of the codeword according to the original codebook, and the base station searches for its corresponding codeword according to the index, and inputs the codeword into the neural network trained in step (4), and outputs a high-precision downlink channel. The present invention adopts AI technology. Make full use of environmental knowledge, and use the Refine module based on neural network to assist the feedback of the downlink channel and improve the accuracy of the channel feedback without changing the existing codebook-based wireless channel feedback architecture.

Description

technical field [0001] The invention relates to an AI-based environmental knowledge-assisted wireless channel feedback method, belonging to the technical field of communications. Background technique [0002] Massive Multiple-Input Multiple-Output (Massive MIMO) is one of the core technologies of 5G. By increasing the number of antennas at the base station, it greatly improves system capacity, spectral efficiency, user experience rate, and enhances coverage. Save energy. At the same time, relevant 6G white papers all point out that massive MIMO will be further developed in the next 6G and will continue to play a vital role. However, the development and application of massive MIMO also face many problems, and its performance is closely related to the quality of the channel state information (Channel State Information, CSI) obtained by the transmitter. In a Time-Division Duplexing (TDD) system, the uplink and downlinks work in the same frequency band, and the channels are re...

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): H04B7/0417H04B7/06H04B7/0456G06N3/04G06N3/08
CPCH04B7/0417H04B7/0626H04B7/0456G06N3/08G06N3/045
Inventor 金石郭佳佳温朝凯
Owner SOUTHEAST UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap