Channel estimation method based on deep learning and data pilot assistance

A channel estimation, deep learning technology, applied in channel estimation, baseband systems, digital transmission systems, etc., can solve the problem of not considering the influence of channel time-varying

Active Publication Date: 2021-06-15
ZHEJIANG UNIV
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] However, the AE-based scheme does not take into account the influence of 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
  • Channel estimation method based on deep learning and data pilot assistance
  • Channel estimation method based on deep learning and data pilot assistance
  • Channel estimation method based on deep learning and data pilot assistance

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] In order to describe the present invention more specifically, the technical solutions of the present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0040] The present invention mainly comprises two parts in concrete implementation process: (1) determine the parameter of LSTM-MLP network and off-line training neural network; estimate.

[0041] A data frame of an OFDM system includes L OFDM symbols, and each OFDM symbol utilizes K orthogonal subcarriers to transmit data symbols and pilot symbols in parallel. Let l be the index of OFDM symbols in a frame, l∈[1,2,…,L], k be the subcarrier index, in is the set of subcarrier numbers used to transmit data symbols and pilots, K is The number of elements in the set; let X l (k) represents the symbol sent on the kth subcarrier in the lth OFDM symbol, then all the symbols transmitted on the lth OFDM symbol are Assuming that the channel has quasi-static...

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 based on deep learning and data pilot assistance, an LSTM-MLP network combining an LSTM network and an MLP is designed, and the LSTM-MLP network learns time correlation and frequency correlation of channels through a large number of channel data samples in the offline training process. In order to solve the problem of insufficient pilot frequency, a DPA method is utilized to take a corrected data symbol in a de-mapping process as a pilot frequency to estimate a current channel value, and more useful channel information is provided for an LSTM-MLP network as input; meanwhile, in order to solve errors caused by channel noise and channel time-varying characteristics in the DPA process, an off-line trained LSTM-MLP network is utilized to track a time-varying channel and eliminate noise, the errors caused by the DPA process are compensated, and a reliable channel estimation value is provided for signal demodulation.

Description

technical field [0001] The invention belongs to the technical field of wireless communication, and in particular relates to a channel estimation method based on deep learning and data pilot assistance. Background technique [0002] In recent years, Orthogonal frequency division multiplexing (OFDM) technology has been widely used in communication system design because it can realize parallel transmission of high-speed serial data through frequency division multiplexing. However, in a more complex propagation environment, the wireless channel not only causes frequency selective fading and time selective fading due to multipath and Doppler effects, but also may be a non-stationary wireless fading channel, which makes the traditional channel estimation method in The OFDM system cannot get satisfactory performance under the limited pilot placement. Therefore, it has become a top priority to design an efficient channel estimation method for OFDM systems for dual-selective non-sta...

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): H04L25/02
CPCH04L25/0254H04L25/0204H04L25/021H04L25/022
Inventor 单杭冠潘景李荣鹏
Owner ZHEJIANG 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