Neural Network DPD Coefficient Estimation for Adaptive PA Linearity

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing power amplifiers face challenges in maintaining transmission performance due to an inability to respond to various power amplification scenarios, leading to deteriorated linearity and efficiency when using fixed digital pre-distortion coefficients or bias voltage adjustments.

Innovation Solution

A digital pre-distortion coefficient estimating device utilizing a neural network that learns and infers optimal coefficients based on system parameters, adapting to different power amplification scenarios to enhance linearity and efficiency.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If fixed digital pre-distortion coefficients are used, then device complexity is reduced, but transmission performance and linearity deteriorate in varying power amplification scenarios

Engineering Contradiction:
Improvecomplexity of DPD coefficient managementVSAvoidtransmission performance
Core Design Contradiction:
Device complexityVSReliability

Solution Approach 1:

The patent implements dynamic DPD coefficients that automatically adapt to different power amplification scenarios. The system transitions from static fixed coefficients to dynamic coefficients that change based on real-time operating conditions such as frequency, power level, and temperature, thereby maintaining transmission performance without requiring complex manual reconfiguration

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The patent changes the parameters of DPD coefficients based on system operating conditions. By monitoring parameters like frequency, power level, and temperature, the system adjusts DPD coefficients accordingly to optimize transmission performance across varying scenarios while maintaining manageable device complexity

Inventive Principle:
Principle #35Parameter changes

2Reliability

If bias voltage is adjusted to improve linearity, then transmission performance improves, but power consumption increases

Engineering Contradiction:
Improvelinearity of PAVSAvoidpower consumption of PA
Core Design Contradiction:
ReliabilityVSUse of energy by moving object

Solution Approach 1:

The patent optimizes the bias voltage parameter dynamically based on operating conditions. Instead of maintaining a constantly high bias voltage to ensure linearity, the system adjusts the bias voltage parameter to the minimum necessary level for each specific scenario, thereby improving linearity when needed while reducing power consumption during normal operation

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

The patent applies partial action by using bias voltage adjustment only when and where needed to improve linearity, rather than continuously applying maximum bias voltage. The system selectively activates bias voltage optimization in specific power amplification scenarios where linearity improvement is necessary, avoiding unnecessary power consumption in other scenarios

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentEP4693896A1Digital pre-distortion coefficient estimating device and operating method thereof
Publication Date: 2026.02.11 SAMSUNG ELECTRONICS CO LTD
  • EP4693896A1 patent drawingFigure 1
  • EP4693896A1 patent drawingFigure 2
  • EP4693896A1 patent drawingFigure 3

AI summary

An adaptive digital pre-distortion device includes a legacy digital pre-distortion (DPD) device, one or more processors including processing circuitry, and a memory storing instructions. The instructions, when executed by the one or more processors individually or collectively, cause the adaptive DPD device to receive a plurality of system parameters, estimate, using a neural network, one or more coefficients of the legacy DPD device, and apply the one or more coefficients to the legacy DPD device. The neural network is configured to generate, as outputs, the one or more coefficients based on the plurality of system parameters.