Time-varying OFDM system channel estimation method based on deep learning

A technology of deep learning and channel estimation, applied in neural learning methods, baseband systems, baseband system components, etc., can solve problems such as time-varying channels without consideration, achieve improved channel estimation and signal detection performance, and improve estimation accuracy and Effect

Inactive Publication Date: 2020-09-18
NORTHWESTERN POLYTECHNICAL UNIV
View PDF9 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Document 4 "Ye H, Li G Y, Juang B H F. Power of Deep Learning for Channel Estimation and Signal Detection in OFDM Systems [J]. IEEE Wireless Communications Letters, 2017, 7(1): 114-117." The learning method is used for wireless channel transmission without online training, and demonstrates the potential of deep learning for channel estimation and signal detection in OFDM systems, but it does not consider the time-varying nature of the channel

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
  • Time-varying OFDM system channel estimation method based on deep learning
  • Time-varying OFDM system channel estimation method based on deep learning
  • Time-varying OFDM system channel estimation method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0052] Step 1: Generation of CPR-Net input data

[0053] The present invention can pre-set the parameters in the above-mentioned CPB algorithm to generate required data:

[0054]In the present invention, the number of subcarriers of the OFDM system is set to 64, and the length of the cyclic prefix is ​​set to 16; the special training symbols with repetition characteristics in the time domain are set to where x n / 2 is a pseudo-random noise sequence generated by Matlab, n=1,2,...,64; the number of multipaths is set to 3, and the normalized three-path Doppler frequency shift v={v 1 ,v 2 ,v 3}, where v i (i=1,2,3) is a uniformly distributed random number that obeys the mean interval [0.1,0.2], that is, 0.1≤ν i ≤0.2; complex amplitude h={a 1 +jb 1 ,a 2 +jb 2 ,a 3 +jb 3}, where a i and b i (i=1,2,3) are independent and identically distributed normal random numbers with a mean of 0 and a variance of 0.5.

[0055] The fast time-varying OFDM system model adopted by the p...

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 provides a time-varying OFDM system channel estimation method based on deep learning. The system randomly generates a sending data signal bit stream; forming a sending frame with a training symbol; carrying out binary phase shift keying modulation; performing inverse fast Fourier transform; adding a cyclic prefix to overcome inter-symbol interference, carrying out serial-to-parallelconversion, obtaining a received signal through a fast time-varying OFDM channel and noise addition, constructing and training a CPR-Net model, generating more accurate Doppler frequency shift, and after channel reconstruction response is carried out, recovering a received signal bit stream through signal detection. According to the invention, the deep learning method is introduced into the fast time-varying OFDM system, and the channel estimation and signal detection performance in the fast time-varying OFDM system is improved by using the deep neural network, so that the channel parameter estimation precision and the overall bit error rate performance of the system are improved.

Description

technical field [0001] The invention relates to the field of wireless communication technology, and proposes a channel estimation scheme combined with deep learning technology for OFDM systems under fast time-varying channels, so that the system has better channel estimation and signal detection performance. Background technique [0002] Orthogonal Frequency-Division Multiplexing (OFDM) is a special multi-carrier modulation technology that uses orthogonal subcarriers for parallel transmission and at the same time resists multipath fading by extending the transmission symbol period, so in the fourth Widely used in modern wireless communication systems. However, OFDM is very sensitive to carrier frequency offset. Once the orthogonality between subcarriers is destroyed, the performance of the system will drop sharply. At the same time, in order to ensure high-speed and high-reliability transmission of data, the receiver of the OFDM system often uses coherent demodulation. Ther...

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): H04L25/02G06N3/04G06N3/08
CPCH04L25/0254G06N3/084G06N3/048G06N3/045
Inventor 姚如贵王圣尧秦倩楠左晓亚徐娟
Owner NORTHWESTERN POLYTECHNICAL 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