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

Wi-Fi standard system channel estimation method based on super-resolution image restoration technology

A low-resolution image and image restoration technology, which is applied in channel estimation, baseband system components, diversity/multi-antenna systems, etc., can solve problems such as few researches on data locations, and achieve superior feature learning ability and high feasibility , avoid the effect of complex nonlinear interpolation relationship

Inactive Publication Date: 2019-07-05
SHANGHAI UNIV
View PDF3 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, at present, most of the traditional theoretical methods and deep learning-based channel estimation only focus on the CSI recovery at the pilot position, while the channel interpolation estimation at the data position is seldom studied.

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
  • Wi-Fi standard system channel estimation method based on super-resolution image restoration technology
  • Wi-Fi standard system channel estimation method based on super-resolution image restoration technology
  • Wi-Fi standard system channel estimation method based on super-resolution image restoration technology

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] Such as Figure 1a As shown, it is a MIMO-OFDM system model involved in this embodiment, including N t root transmit antenna with N r root receiving antenna, then the received symbol at the i-th subcarrier after fast Fourier transform is: y i (t)=H i (t)x(t)+n i (t), where: by N r ×N t A complex matrix H consisting of elements i (t) is the MIMO fading correlation coefficient CSI, x i (t) is the symbol sent, and n i (t) is additive white Gaussian noise with zero mean and unit variance.

[0024] Such as Figure 1b As shown, in this embodiment, two commercial machines that communicate with the IEEE 802.11n Wi-Fi protocol are set, the open source tool Atheros CSI Tool is installed to collect actual real-time CSI, and line-of-sight (LOS) and non-line-of-sight are respectively set. (NLOS) scenarios. Since some subcarriers are used as guard subcarriers in the Wi-Fi system, their values ​​are all zero, so the number of elements in the input and output matrix can be sl...

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 Wi-Fi standard system channel estimation method based on super-resolution image restoration technology, which includes: estimating the CSI at the corresponding position by using the known pilot signal to obtain a channel estimation value; adopting an SR image recovery network to train and learn the relation between the state information of the channel at the pilot position and the state information of the channel at the data position, inputting the channel estimation value serving as a low-resolution image into the trained SR image recovery network, and obtaining complete CSI under the optimization precision. According to the invention, the method can be applied to Wi-Fi standard system, an SR image restoration technology is utilized to learn a nonlinear interpolation relation in a channel estimation problem, and channel data generated by a statistical channel model is offline utilized to train an SR network, so that the network can be applied to actual Wi-Fistandard system on line to avoid the problem that an actual CSI data set is difficult to obtain.

Description

technical field [0001] The present invention relates to a technology in the wireless communication field, in particular to a channel estimation method for a Wi-Fi standard system based on a super-resolution image restoration technology. Background technique [0002] Channel estimation is generally considered a key component of modern wireless systems. By inserting pre-known pilot sequences between the data to be transmitted, the receiver should be able to estimate the real-time wireless channel environment accordingly. Existing literature has devoted considerable effort to improving channel estimation accuracy, especially for multiple-input multiple-output (MIMO) orthogonal frequency-division multiplexing (OFDM) configurations, which are currently commonly used in cellular or wireless local area network (WLAN) technology in the system. [0003] However, most schemes rely on abstract channel models with certain characteristics, such as channel sparsity, and their applicatio...

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 Applications(China)
IPC IPC(8): H04L25/02H04L27/26H04B7/08
CPCH04B7/0854H04L25/025H04L27/2695
Inventor 石琦刘杨雨张舜卿徐树公曹姗
Owner SHANGHAI UNIV
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