Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Intelligent digital predistortion system and method for dynamic transmission

A digital predistortion and dynamic technology, applied in synchronization/start-stop system, biological neural network model, neural architecture, etc., can solve problems such as inefficiency, reduce the number of coefficients, improve stability and convergence speed, and reduce the amount of calculation. Effect

Active Publication Date: 2022-07-22
SOUTHEAST UNIV
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The nonlinear characteristics of the power amplifier will change as the input signal changes. The traditional digital pre-distortion method needs to store a set of digital pre-distortion coefficients for each input signal, which is very inefficient

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
  • Intelligent digital predistortion system and method for dynamic transmission
  • Intelligent digital predistortion system and method for dynamic transmission
  • Intelligent digital predistortion system and method for dynamic transmission

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0061] see Figure 1-Figure 4 , this embodiment provides a dynamic transmission-oriented intelligent digital predistortion system, including: a polynomial auxiliary module, a signal feature estimation module, and a neural network module; wherein,

[0062] The polynomial auxiliary module uses the prior information of the power amplifier to eliminate the static nonlinearity of the power amplifier in the dynamic transmission scenario;

[0063] The signal feature estimation module estimates the signal feature of the dynamic transmission signal, and inputs the estimated signal feature together with the input signal into the neural network module;

[0064] The neural network module compensates the dynamic nonlinearity of the power amplifier caused by the change of the input signal according to the acquired signal characteristics and the input signal.

[0065] Specifically, in this embodiment, the signal feature estimation module extracts a recent input signal by using a finite impu...

Embodiment 2

[0096] This embodiment provides a dynamic transmission-oriented intelligent digital predistortion method on the basis of Embodiment 1, including:

[0097] Step S1: Input multiple sets of input signals with different characteristics required for dynamic transmission into the power amplifier, and the input signal is defined as the original input signal, then obtain multiple sets of first output signals from the output end of the power amplifier, and then extract All the features of the original input signal, and construct a data set based on the original input signal, the first output signal and the feature, and then divide the data set into a training set and a verification set in a certain proportion;

[0098] Step S2, select the size of the finite impulse response window in the signal feature extraction module and the traditional model that needs to be embedded in the polynomial auxiliary module, and set the hyperparameters of the modeling system;

[0099] Specifically, in th...

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 dynamic transmission-oriented intelligent digital predistortion system and method, comprising: a polynomial auxiliary module, a signal feature estimation module, and a neural network module; the polynomial auxiliary module utilizes the prior information of the power amplifier to eliminate the power amplifier in dynamic transmission scenarios The signal characteristic estimation module estimates the signal characteristics of the dynamic transmission signal, and inputs the estimated signal characteristics together with the input signal into the neural network module; the neural network module compensates the power amplifier according to the acquired signal characteristics and the input signal Dynamic nonlinearity due to changes in the input signal. The invention meets the intelligent digital pre-distortion requirements of the power amplifier in the dynamic transmission scenario by estimating the characteristics of the input signal and inputting it into the model, and uses the prior information of the power amplifier to embed into the traditional polynomial behavior model, The complexity of the system is greatly reduced.

Description

technical field [0001] The invention relates to the technical field of digital predistortion, in particular to a dynamic transmission-oriented intelligent digital predistortion system and method. Background technique [0002] In the fifth generation mobile communication system (5G), in order to make full use of the communication resources, the input signal of the transmitter will change dynamically according to the change of the channel environment. For example, when the channel environment is poor, use a low-order modulation method to ensure that the received signal can be correctly demodulated; when the spectrum resources are not fully utilized, increase the signal bandwidth to transmit more information and so on. In this way, 5G can greatly improve communication flexibility. However, like the traditional mobile communication system, in order to ensure the efficiency of the whole system, the power amplifier needs to work in a high-efficiency mode with strong nonlinear cha...

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 Patents(China)
IPC IPC(8): H04L25/49G06N3/04
CPCH04L25/49G06N3/048G06N3/045
Inventor 余超郁煜铖
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
Eureka Blog
Learn More
PatSnap group products