Deep Learning Aided Beamforming for Downlink Non Orthogonal Multiple Access Systems

We investigate the problem of optimal beamformer design for the downlink of Multi Input Single Output (MISO) Non-Orthogonal Multiple Access (NOMA). In more detail, focusing on the two-user scenario, we first derive a closed from expression for the Bit Error Rate (BER) experienced by both user. Using the derived expression, in an effort to introduce fairness in our system design, we introduce the problem of optimal, with respect to minimizing the maximum of the BER values experienced by the two users, beamforming and propose a Machine Learning (ML) based solution for this problem. Finally, we conduct simulations which allow us to verify that our proposed algorithm outperforms other existing benchmarks as well as that in a variety of cases, it may result to BER performance close to the one obtained by the use of time consuming constrained optimization methods, such as to solve the given optimization problem.