Cooperative beam forming method based on integrated deep learning

A beamforming and deep learning technology, applied in the field of collaborative beamforming based on integrated deep learning, can solve problems such as a lot of overhead

Pending Publication Date: 2021-08-10
SOUTHEAST UNIV
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to overcome the problem of a large amount of overhead consumed by the prior art, and to achieve the optimal achievable rate of the base station with the minimum overhead

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
  • Cooperative beam forming method based on integrated deep learning
  • Cooperative beam forming method based on integrated deep learning
  • Cooperative beam forming method based on integrated deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] Below in conjunction with accompanying drawing, technical scheme of the present invention is described in further detail:

[0041] This invention may be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.

[0042] Such as figure 1 As shown, the cooperative beamforming method based on integrated deep learning proposed by the present invention adopts an algorithm combining dense neural network and deep learning integration, which specifically includes the following steps:

[0043] Step 1, the user sends to each base station the same pilot sequence, where stands for codebook, N tr Indicates the number of codebooks in the codebook. The pilot sequence starts with , where K is the subcarrier limit, if K=64 is set, it means that the pilot sequ...

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 cooperative beam forming method based on integrated deep learning, and the method comprises the following steps: connecting a base station adopting beam forming to a cloud / central processing unit applying baseband processing, and simultaneously providing services for mobile users; for the system, formulating the training and design problems of the RF beam forming vectors of the central baseband and the base station, so that the effective achievable rate of the system is improved to the maximum extent; enabling the base station to learn a mapping from the omni-received uplink pilot and beam training results to predict an optimal RF beamforming vector for the base station; enabling the base station to select its beamforming vector from a predefined codebook; and enabling the central processor to design its baseband beamforming to ensure coherent combination of users. According to the method for integrating the dense neural network and the deep learning, the characteristics of different models and the strength of the model fitting degree and the prediction data effect are analyzed.

Description

technical field [0001] The invention relates to the field of beamforming, in particular to a cooperative beamforming method based on integrated deep learning in millimeter wave massive MIMO communication. Background technique [0002] mmWave and massive MIMO are key enabling technologies for current and future wireless systems due to their extremely high data rates and multiplexing gains. However, to support highly mobile users to ensure reliability and achieve low-complexity collaboration, a large number of antennas are required, which poses significant challenges for mmWave systems. One of the main reasons for these challenges is the large training, feedback and coordination overhead associated with large channel matrices. However, these channels are intuitively some function of the environment geometry, building materials, transmitter / receiver locations, etc., which can be exploited by exploiting the low-overhead nature of the environment and user settings and learning ...

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
IPC IPC(8): H04B7/06H04B7/0456G06N3/02G06N3/08
CPCG06N3/02G06N3/08H04B7/0456H04B7/0617H04B7/063H04B7/0695
Inventor 杨绿溪徐佩钦张天怡周京鹏李春国黄永明
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