NN-Based Joint Mitigation of IQ Imbalance and PA Nonlinearity With Multiple States

TL;DR

This paper introduces a neural network model for joint digital pre-distortion of IQ imbalance and PA nonlinearity in RF transmitters, utilizing multi-task learning to adapt across multiple operating states and outperform existing methods.

Contribution

A novel neural network architecture employing multi-task learning for joint mitigation of IQ imbalance and PA nonlinearity across multiple transmitter states.

Findings

Effective joint DPD achieved for IQ-PA systems.

Outperforms existing methods in multiple signal states.

Dynamic adaptation of output layer weights improves performance.

Abstract

Joint mitigation of IQ imbalance and PA nonlinearity is important for improving the performance of radio frequency (RF) transmitters. In this paper, we propose a new neural network (NN) model, which can be used for joint digital pre-distortion (DPD) of non-ideal IQ modulators and PAs in a transmitter with multiple operating states. The model is based on the methodology of multi-task learning (MTL). In this model, the hidden layers of the main NN are shared by all signal states, and the output layer's weights and biases are dynamically generated by another NN. The experimental results show that the proposed model can effectively perform joint DPD for IQ-PA systems, and it achieves better overall performance within multiple signal states than the existing methods.