Self-Interference Noise Calculator for Full Duplex Wireless Systems

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current 5G wireless communication systems face challenges in achieving full duplex transmission due to self-interference noise, which limits spectrum efficiency and data transmission capacity, especially in systems using multiple-input multiple-output (MIMO) techniques.

Innovation Solution

The implementation of a self-interference noise calculator using a neural network or recurrent neural network to generate adjusted signals that compensate for self-interference, allowing for simultaneous transmission and reception in the same frequency band by processing signals through layers of multiplication/accumulation units and memory look-up units.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If full duplex transmission is implemented in 5G wireless communication systems, then spectrum efficiency and data transmission capacity are improved, but self-interference noise increases and limits transmission quality

Engineering Contradiction:
Improvespectrum efficiencyVSAvoidself-interference noise
Core Design Contradiction:
ProductivityVSObject-generated harmful factors

Solution Approach 1:

The patent applies the principle of converting harm into benefit by using the self-interference noise generated during full duplex transmission as training data for neural networks. The neural network learns to model and cancel self-interference patterns by processing the noise signals, thereby transforming the harmful self-interference into useful training information that enables effective interference cancellation and improves overall transmission quality.

Inventive Principle:
Principle #22Blessing in disguise (Convert harm into benefit)

Solution Approach 2:

The patent introduces neural networks as intermediary components between the transmitter and receiver. These neural networks act as mediators that process self-interference signals, generate cancellation estimates, and provide adjusted signals to compensate for self-interference. The intermediary neural network processing enables full duplex transmission while managing the harmful self-interference effects.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Speed

If multiple-input multiple-output (MIMO) techniques are used to increase transmission capacity, then data transmission speed is improved, but self-interference noise and system complexity increase

Engineering Contradiction:
Improvedata transmission speedVSAvoidsystem complexity
Core Design Contradiction:
SpeedVSDevice complexity

Solution Approach 1:

The patent replaces traditional mechanical signal processing methods with neural network-based digital signal processing. Instead of using complex analog interference cancellation circuits, the system employs neural networks that can be trained to model and cancel self-interference through software algorithms, thereby reducing hardware complexity while maintaining high data transmission speeds enabled by MIMO techniques.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

3Reliability

If neural networks are used to calculate self-interference noise, then self-interference compensation is improved, but processing time and computational requirements increase

Engineering Contradiction:
Improveself-interference compensationVSAvoidprocessing time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent applies preliminary action by training neural networks in advance using self-interference data collected during system operation. Once trained, the neural networks can quickly process new self-interference signals without requiring time-consuming training during real-time transmission. This pre-training approach enables fast inference and effective self-interference compensation with minimal processing delay during actual communication.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP4026250B1Wireless devices and systems including examples of full duplex transmission using neural networks or recurrent neural networks
Publication Date: 2024.10.23 MICRON TECHNOLOGY INC
  • EP4026250B1 patent drawingFigure 1
  • EP4026250B1 patent drawingFigure 2
  • EP4026250B1 patent drawingFigure 3

AI summary

Examples described herein include systems and methods which include wireless devices and systems with examples of Ml duplex compensation with a self-interference noise calculator. The self-interference noise calculator may be coupled to antennas of a wireless device and configured to generate adjusted signals that compensate self-interference. The self-interference noise calculator may include a network of processing elements configured to combine transmission signals into intermediate results according to input data and delayed versions of the intermediate results. Each set of intermediate results may be combined in the self-interference noise calculator to generate a corresponding adjusted signal. The adjusted signal is received by a corresponding wireless receiver to compensate for the self-interference noise generated by a wireless transmitter transmitting on the same frequency band as the wireless receiver is receiving.