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

Low-rank csi feedback method, storage medium and device for deep iterative neural network

An iterative neural network and deep technology, which is applied in the fields of low-rank CSI feedback, storage media and equipment for deep iterative neural networks. The effect of computational overhead

Active Publication Date: 2022-07-26
杭州勒贝格智能系统有限责任公司
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, most of these methods are data-driven, not very interpretable, and are sensitive to data

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
  • Low-rank csi feedback method, storage medium and device for deep iterative neural network
  • Low-rank csi feedback method, storage medium and device for deep iterative neural network
  • Low-rank csi feedback method, storage medium and device for deep iterative neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0058] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0059] It should also be understood that the terminology used in the present specification is for the purpose of describing particular embodiments only and is not intended to limit the present invention. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural unless the context clearly dictates otherwise.

[0060] It should further be understood that, as used in this s...

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 low-rank CSI feedback method, storage medium and equipment for a deep iterative neural network. FISTA is expanded into a deep iterative neural network; the channel matrix is ​​decomposed based on the low rank of the channel to obtain the linearly independent part of the channel. and the rest; based on the linearly independent part of the channel and the rest of the channel, the linearly independent part of the reconstructed low-rank channel is reconstructed to obtain a better initial value of the rest; based on the sparsity and the rest of the low-rank channel The optimal initial value of , and the FISTA algorithm is used to expand the deep iterative neural network to reconstruct the linearly independent part and the rest of the low-rank channel respectively; use the CSI to compress the feedback information and the measurement matrix to train the network, and use the trained network to reconstruct the The linearly independent part and the rest of the low-rank channel reconstruct the complete low-rank CSI. The present invention reconstructs the linearly independent part and the remaining part of the low-rank channel matrix respectively through the low-rank property of the channel, so as to improve the CSI reconstruction accuracy.

Description

technical field [0001] The present invention belongs to the technical field, and in particular relates to a low-rank CSI feedback method, storage medium and device for a deep iterative neural network. Background technique [0002] Massive MIMO (Multi-input Multi-output) is one of the important technologies for 5G and future wireless communication systems. This technology deploys multiple transmit antennas and receive antennas at the signal receiving end and the transmitting end respectively. On the premise that the base station obtains accurate downlink CSI (Channel State Information), the spectrum efficiency of the communication system is higher and the system capacity is larger. , stronger robustness and so on. [0003] In a TDD (Time Division Duplex) system, according to the reciprocity of uplink and downlink channels, the base station can easily obtain downlink CSI. However, in an FDD (Frequency Division Duplex) system, since the uplink and downlink channels are in dif...

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): H04B7/06H04L1/06G06N3/08G06N3/04
CPCH04B7/0626H04L1/0693G06N3/08G06N3/045
Inventor 薛江郭建华
Owner 杭州勒贝格智能系统有限责任公司
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