AI Digital Pre-Distortion for Envelope-Tracking PA Nonlinearity
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In 6G extreme-MIMO systems, power amplifiers consume a significant portion of the base station's power budget and have low power-added efficiency (PAE), leading to thermal concerns and increased operational costs, with conventional digital pre-distortion failing to address dynamic nonlinearity and time-varying power amplifier characteristics.
Innovation Solution
Implementing an AI-based digital pre-distortion system that uses a neural network structure to compensate for power amplifier nonlinearity by considering dynamic supply voltage levels and signal I/Q components, adjusting nonlinearity compensation based on real-time digital envelope measurements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional digital pre-distortion is used to compensate for PA nonlinearity, then some nonlinearity compensation is achieved, but it fails to address dynamic nonlinearity and time-varying power amplifier characteristics
Solution Approach 1:
The patent applies dynamics by making the pre-distortion system adaptive and time-varying. The neural network model continuously updates its parameters based on real-time feedback from the power amplifier's actual behavior, allowing the system to track and compensate for dynamic nonlinearity and time-varying characteristics rather than relying on fixed conventional DPD parameters.
Solution Approach 2:
The patent implements feedback by using the measured output signal from the power amplifier to update the neural network model parameters. This closed-loop feedback mechanism allows the system to learn from actual PA behavior and continuously improve its nonlinearity compensation accuracy, addressing the limitation of conventional DPD that lacks adaptive feedback.
2Power
If power amplifiers operate at high input power to meet system demands, then output power is sufficient, but power-added efficiency decreases and thermal issues increase
Solution Approach 1:
The patent applies preliminary action by pre-distorting the input signal before it reaches the power amplifier. The neural network model pre-compensates for nonlinearity and optimizes the signal characteristics, allowing the PA to operate more efficiently in its nonlinear region while maintaining desired output power and spectral regrowth performance, thereby improving power-added efficiency.
3Device complexity
If conventional DPD assumes fixed PA nonlinearity, then system complexity is reduced, but it cannot accommodate challenges in PA linearization for envelope tracking
Solution Approach 1:
The patent applies self-service by enabling the DPD system to automatically adapt and optimize itself through the neural network's learning capability. The system self-adjusts its parameters based on real-time PA behavior without requiring manual intervention or complex external calibration, achieving high linearization performance while maintaining practical system complexity through automated adaptation.
Data Source
AI summary
Methods and systems for NN-based digital pre-distortion for digital envelope tracking power amplifiers. A computer-implemented method includes receiving a measure of a digital envelope at a digital pre-distortion module having a neural network (NN)-based digital pre-distortion structure for digital envelope tracking (DET), receiving a transmit signal at the digital pre-distortion module, inputting the measure of the digital envelope and the transmit signal into the NN-based digital pre-distortion structure to produce a pre-distorted transmit signal, adjusting nonlinearity compensation of a power amplifier based on the measure of the digital envelope, and using the adjusted nonlinearity compensation of the power amplifier to produce an output signal.