Apparatus and method for self-interference signal cancellation

Patent metadata

Field	Value
Publication number	US-11528049-B2
Application number	US-202017073148-A
Country	US
Kind code	B2
Filing date	Oct 16, 2020
Priority date	Oct 18, 2019
Publication date	Dec 13, 2022
Grant date	Dec 13, 2022

Abstract

The disclosure relates to a communication technique and a system for combining a 5G communication system with IoT technology to support a higher data rate after a 4G system. Based on 5G communication and IoT-related technologies, the disclosure may be applied to intelligent services such as smart homes, smart buildings, smart cities, smart or connected cars, healthcare, digital education, retail, and security and safety related services. The disclosure provides a method and apparatus that enable a communication device supporting full duplex to cancel the self-interference signal in the digital domain.

First claim

What is claimed is:

1. A method of a communication device for self-interference signal cancellation supporting a full duplex (FD) operation, the method comprising:
identifying channel estimation information for a self-interference signal;
generating input data for estimating a nonlinear component of the self-interference signal based on a digital transmission signal associated with the self-interference signal and the channel estimation information, the input data representing a linear component for each path of the self-interference signal; and
estimating the nonlinear component of the self-interference signal with a preset neural network-based self-interference signal cancelation technique, using the digital transmission signal and the input data as inputs by a pre-trained fully connected multilayer perceptron (FC-MLP) module including an output layer,
wherein the output layer includes 2 nodes, which output a real part value and an imaginary part value, respectively, of the nonlinear component of the self-interference signal.

2. The method of claim 1 , wherein the generating the input data comprises generating the input data by multiplying the digital transmission signal and the channel estimation information.

3. The method of claim 1 , wherein the preset neural network-based self-interference signal cancellation technique is a multilayer neural network-based self-interference signal cancellation technique.

4. The method of claim 1 , further comprising removing a linear component of the self-interference signal based on the channel estimation information.

5. The method of claim 4 , further comprising removing the nonlinear component of the self-interference signal by subtracting the estimated nonlinear component from the self-interference signal from which the linear component has been removed.

6. The method of claim 1 , wherein the communication device is a communication device of a terminal or a communication device of a base station.

7. A communication device supporting a full duplex (FD) operation, comprising:
a transceiver; and
at least one processor connected to the transceiver,
wherein the at least one processor is configured to:
identify channel estimation information for a self-interference signal;
generate input data for estimating a nonlinear component of the self-interference signal based on a digital transmission signal associated with the self-interference signal and the channel estimation information, the input data representing a linear component for each path of the self-interference signal; and
estimate the nonlinear component of the self-interference signal with a preset neural network-based self-interference signal cancelation technique, using the digital transmission signal and the input data as inputs by a pre-trained fully connected multilayer perceptron (FC-MLP) module including an output layer,

wherein the output layer includes 2 nodes, which output a real part value and an imaginary part value, respectively, of the nonlinear component of the self-interference signal.

8. The communication device of claim 7 , wherein the at least one processor is configured to generate the input data by multiplying the digital transmission signal and the channel estimation information.

9. The communication device of claim 7 , wherein the preset neural network-based self-interference signal cancellation technique is a multilayer neural network-based self-interference signal cancellation technique.

10. The communication device of claim 7 , wherein the at least one processor is further configured to remove a linear component of the self-interference signal based on the channel estimation information.

11. The communication device of claim 10 , wherein the at least one processor is further configured to remove the nonlinear component of the self-interference signal by subtracting the estimated nonlinear component from the self-interference signal from which the linear component has been removed.

12. The communication device of claim 7 , wherein the communication device is a communication device of a terminal or a communication device of a base station.

Assignees

• Samsung Electronics Co Ltd
• Sungkyunkwan Univ Research & Business Foundation

Inventors

• Lee Kwonjong
• Kim Sang-Hyo
• Lee Hyojin
• Kil Yong-Sung
• Kong Dong Hyun

Classifications

• G06N3/048

  Activation functions · CPC title

• H04B1/123

  using adaptive balancing or compensation means (adaptive filter circuits and algorithms H03H) · CPC title

• G06N3/084

  Backpropagation, e.g. using gradient descent · CPC title

• G06N3/02

  Neural networks · CPC title

• H04L5/1423

  for simultaneous baseband signals · CPC title