Learning to Compensate: A Deep Neural Network Framework for 5G Power Amplifier Compensation

TL;DR

This paper introduces a deep learning framework for modeling and compensating 5G power amplifiers, significantly reducing nonlinear effects and outperforming traditional mathematical models in various distortion scenarios.

Contribution

The paper presents a novel deep neural network-based framework with frequency domain loss functions for PA compensation, replacing conventional mathematical modeling methods.

Findings

56.7% reduction in nonlinear and memory effects

16.3% average improvement over mathematical models

34% enhancement in severe distortion scenarios

Abstract

Owing to the complicated characteristics of 5G communication system, designing RF components through mathematical modeling becomes a challenging obstacle. Moreover, such mathematical models need numerous manual adjustments for various specification requirements. In this paper, we present a learning-based framework to model and compensate Power Amplifiers (PAs) in 5G communication. In the proposed framework, Deep Neural Networks (DNNs) are used to learn the characteristics of the PAs, while, correspondent Digital Pre-Distortions (DPDs) are also learned to compensate for the nonlinear and memory effects of PAs. On top of the framework, we further propose two frequency domain losses to guide the learning process to better optimize the target, compared to naive time domain Mean Square Error (MSE). The proposed framework serves as a drop-in replacement for the conventional approach. The proposed approach achieves an average of 56.7% reduction of nonlinear and memory effects, which converts to an average of 16.3% improvement over a carefully-designed mathematical model, and even reaches 34% enhancement in severe distortion scenarios.