Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A channel estimation method for passive smart reflective surfaces based on deep learning

A deep learning, reflective surface technology, applied in neural learning methods, channel estimation, baseband system components, etc., to reduce hardware complexity, improve robustness, and improve power efficiency

Active Publication Date: 2021-10-26
NANTONG UNIVERSITY +1
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

When IRS assists in wireless communication, the base station adjusts the reflected beam to change the transmission environment. However, due to the high-dimensional cascaded channel and a large number of passive reflective elements, it is estimated that the cascaded channel state information will generate a large amount of pilot training overhead and hardware complexity. Spend

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 channel estimation method for passive smart reflective surfaces based on deep learning
  • A channel estimation method for passive smart reflective surfaces based on deep learning
  • A channel estimation method for passive smart reflective surfaces based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0028] see Figure 1-3 , the network architecture of the IRS assisted wireless communication system in this embodiment is as follows figure 1 As shown, the illustrated scene is composed of an IRS, base station and users. The communication between the base station and the user is assisted by the IRS, and both the base station and the user are single-antenna (can be extended to multi-antenna transceivers), and the direct link is covered by the building block. ...

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 channel estimation method of a passive intelligent reflective surface based on deep learning, which is realized by two parts: an offline channel estimation stage and an online channel prediction stage. In the offline channel estimation phase, the user terminal sends pilot signals in the uplink, and the base station controls the IRS to turn on the passive components to reflect the incident pilot signals in turn. The base station receives the pilot signals and uses the minimum mean square error method to estimate the corresponding concatenated channel. information, and then use the method of equal probability uniform sampling to select a small number of sampled concatenated channel information from the estimated concatenated channel information, and use a small number of sampled concatenated channel information and fully concatenated channel information to construct a new data set; online channel prediction In the stage, the base station estimates a small amount of sampled cascaded channel information online and inputs it to the trained ResNet network to recover the fully concatenated channel information. The invention can flexibly select the number of passive components and set the residual unit of the residual neural network to meet the characteristics of different systems and user service quality.

Description

technical field [0001] The invention relates to the technical field of wireless communication, in particular to a channel estimation method of a passive intelligent reflective surface based on deep learning. Background technique [0002] With the commercialization of 5G communication networks, large-scale MIMO transmission brings huge energy consumption and hardware complexity. Recently, the next generation (6G) communication technology has been explored. Among them, the intelligent reflecting surface (Intelligent Reflecting Surface, IRS) has attracted the attention of academia and industry because of its low cost, low hardware complexity, and easy to change the wireless propagation environment. . The IRS is a two-dimensional surface with electromagnetic properties, composed of a large number of passive reconfigurable reflective units made of metamaterials. These units interact with incoming signals by controlling phase, amplitude, frequency, and even polarization to impro...

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): H04L25/02H04L27/26H04B7/0413G06N3/08G06N3/04
CPCH04L25/0202H04L25/024H04L27/2601H04B7/0413G06N3/08G06N3/045
Inventor 孙强赵欢齐月月钱盼盼章嘉懿王珏徐晨杨永杰
Owner NANTONG UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com