Graph-Neural-Network-Precoding-for-Mitigating-Non-Linear-PA-Distortion

This repository contains the code for the paper 'Toward Energy-Efficient Massive MIMO: Graph Neural Network Precoding for Mitigating Non-Linear PA Distortion'

In the GNN repo the code to train and evaluate the GNN for linear precoding to mitigate non-linear PA distortion can be found. Note that the parameters in 'training.py' can be adjusted as desired (number of antennas M, number of users K, input backo-off IBO, etc.).