Optical orthogonal frequency division multiplexing modulation method and system based on deep learning

An orthogonal frequency division and deep learning technology, applied in the field of visible light communication, can solve problems such as ineffective technical effects, PAPR method cannot be used directly, and high complexity

Active Publication Date: 2020-04-24
SUN YAT SEN UNIV
View PDF3 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention provides an optical orthogonal frequency division multiplexing modulation method and system based on deep learning in order to overcome

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
  • Optical orthogonal frequency division multiplexing modulation method and system based on deep learning
  • Optical orthogonal frequency division multiplexing modulation method and system based on deep learning
  • Optical orthogonal frequency division multiplexing modulation method and system based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0094] Such as figure 1 As shown, the optical orthogonal frequency division multiplexing modulation method DL-OOFDM based on deep learning includes the signal transmission process and the signal reception process, including the following steps:

[0095] S1: Construct and train an autoencoder (AE) with a neural network (NN) structure, including the autoencoder transmitter AE-TX and the autoencoder receiver AE-RX;

[0096] S2: The signal transmitter inputs the signal to be sent into the autoencoder transmitter AE-TX for signal preprocessing to obtain the preprocessed signal;

[0097] S3: Perform OFDM modulation on the preprocessed signal, and transmit the obtained positive real modulated signal through the VLC channel to complete the signal transmission process;

[0098] S4: The signal receiving end receives the modulated signal through the VLC channel and performs OFDM demodulation to obtain the OFDM demodulated signal;

[0099] S5: Input the OFDM demodulated signal into the au...

Embodiment 2

[0138] More specifically, on the basis of Example 1, such as image 3 As shown, the optical OFDM modulation system based on deep learning includes the autoencoder transmitter AE-TX, the autoencoder receiver AE-RX and the equivalent channel module; where:

[0139] The automatic encoder transmitting end AE-TX has a neural network structure, which is used for preprocessing the signal to be sent to obtain the preprocessed signal, which can make the OFDM modulated signal have non-negative characteristics;

[0140] After the equivalent channel module receives the preprocessing signal sent by the autoencoder transmitter AE-TX, it performs OFDM modulation, VLC signal transmission and OFDM demodulation processing to obtain an OFDM demodulation signal;

[0141] The receiving end AE-RX of the automatic encoder has a neural network structure, demodulates the OFDM demodulated signal, and restores the signal to be sent.

[0142] More specifically, the autoencoder transmitting end and the aut...

Embodiment 3

[0170] In the specific implementation process, fully connected neural network (Fully Connected Neural Network, FCNN) and convolutional neural network (Convolution Neural Network, CNN) structures are often used in deep learning models. FCNN is a network mainly composed of multi-layer fully connected layers cascaded, and is the simplest and most typical neural network structure. CNN is a network mainly composed of convolutional layers, pooling layers, and fully connected layers. It has a large number of applications in image recognition, object detection, and other fields [15]. CNN can be used to extract signal features, or correlation characteristics between adjacent signals. Therefore, in OFDM modulation, CNN can be used to extract the connection between each subcarrier, and through learning to coordinate the input of each subcarrier, the output OFDM signal can meet certain constraints we need. At the same time, due to the characteristic of sparse connection, CNN can greatly ...

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

An optical orthogonal frequency division multiplexing modulation method based on deep learning provided by the invention comprises a signal transmitting process and a signal receiving process, and comprises the following steps: training and constructing an automatic encoder with a neural network structure, including an automatic encoder transmitting end and an automatic encoder receiving end; inputting a to-be-sent signal into the transmitting end of the automatic encoder for signal preprocessing to obtain a preprocessed signal; performing OFDM modulation on the preprocessed signal to obtain apositive real signal, and transmitting the positive real signal through a VLC channel; enabling the signal receiving end to receive the modulation signal through a VLC channel and performing OFDM demodulation to obtain an OFDM demodulation signal; inputting the OFDM demodulation signal into the receiving end of the automatic encoder for demodulation, and restoring the to-be-sent signal. Accordingto the invention, by constructing the automatic encoder with the neural network structure, high system performance gain is obtained with low complexity while positive real number limitation of a VLCsystem is met, and the signal peak-to-average power ratio PAPR is greatly reduced.

Description

technical field [0001] The present invention relates to the technical field of visible light communication, and more specifically, to an optical OFDM modulation method and system based on deep learning. Background technique [0002] In recent years, as an important supplement to traditional wireless communication technology, visible light communication (Visible Light Communication, VLC) technology has attracted extensive attention from academia and industry. VLC technology uses white light LED configuration, which can realize lighting and communication at the same time, and has many advantages such as high speed, high bandwidth, no spectrum authorization, green environmental protection, and low price [1][2]. The VLC system generally uses Intensity Modulation / Direct Detection (IM / DD) technology, and its signal is modulated on the instantaneous intensity of the optical carrier, so it only supports the transmission of positive real number signals[1][3]. [0003] In addition, O...

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): H04B10/116H04L27/26
CPCH04B10/116H04L27/2615
Inventor 江明徐建勋
Owner SUN YAT SEN 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