Channel estimation method of hybrid quantization system based on deep neural network

A deep neural network and channel estimation technology, which is applied in the field of wireless communication and can solve problems such as the inability to obtain better performance

Active Publication Date: 2019-08-06
SOUTHEAST UNIV
View PDF5 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the optimization results based on this approximate model cannot achieve better performance

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
  • Channel estimation method of hybrid quantization system based on deep neural network
  • Channel estimation method of hybrid quantization system based on deep neural network
  • Channel estimation method of hybrid quantization system based on deep neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0053] Embodiment 1: see Figure 1-Figure 2 , a method for channel estimation of a large-scale MIMO system assisted by a hybrid ADC based on a deep neural network, the channel estimation method comprising the following steps:

[0054] The first step: use and Represent the collection of high-precision and low-precision ADC antennas, respectively, and design neural network 1 and neural network 2 to estimate and The channel of the antenna.

[0055] Firstly, training samples are generated in the simulation environment for offline training of neural networks 1 and 2, and the channel model used to generate training samples is

[0056]

[0057] where h represents the channel from the user to the base station, L represents the number of channel multipaths, α l Indicates the gain of the lth propagation path, Indicates the angle of arrival of the lth propagation path, Indicates the steering vector of the lth propagation path.

[0058] For neural networks 1 and 2, genera...

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 hybrid quantization system based on a deep neural network. The method comprises the following steps: firstly, dividing a base station antenna into a high-precision ADC antenna set and a low-precision ADC antenna set, and generating a real channel and a received and quantized pilot signal as training data according to a system transmission model and a channel model in a simulation environment; then, sending training data to the designed deep neural network 1 and the designed deep neural network 2 for offline training, and ending the training by adjusting a neural network weight matrix until the performance is converged; and finally, assembling the trained neural networks 1 and 2 at a base station end, wherein the trained neural networks 1 and 2 are respectively used for estimating channels corresponding to the high-precision ADC antenna and the low-precision ADC antenna. According to the estimation method, the powerful learning capability of the deep neural network is fully utilized; through offline training based on a large amount of data, the deep neural network can explore spatial correlation between different antennas in alarge-scale antenna system, so that accurate mapping from a high-precision ADC antenna corresponding channel to a low-precision ADC antenna corresponding channel is realized.

Description

technical field [0001] The invention relates to a channel estimation method of a hybrid quantization system based on a deep neural network, belonging to the technical field of wireless communication. Background technique [0002] The large-scale antenna system configures an antenna array with tens or even hundreds of antennas at the base station, and the base station uses a large-scale antenna array to communicate with multiple users simultaneously on the same time-frequency resource. Utilize the spatial freedom provided by the large-scale antenna array of the base station to improve the multiplexing capability of spectrum resources between multiple users, the spectrum efficiency of each user, and the ability to resist inter-cell interference, thereby greatly improving the overall utilization of spectrum resources. At the same time, the overall power efficiency is further improved by utilizing the array gain provided by the large-scale antenna array. Compared with tradition...

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): H04L25/02H04B7/0413
CPCH04B7/0413H04L25/0202H04L25/0254
Inventor 潘志文高深刘楠尤肖虎
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