Maximization of Achievable Sum Rate and Improvement in Outage Probability in Intelligent Reflecting Surface (IRS) Driven NOMA Networks

In this paper, Deep learning inspired non-orthogonal multiple access (NOMA)founded on intelligent reflecting surface (IRS) with the objective of maximizing achievable sum rate of all users have been explored. In this scheme, the base station serves variable number of users at the same frequency andtime but at different power levels. The conventional NOMA although outperforms orthogonal multiple access (OMA) in terms of spectral efficiency, connection density and user fairness. However, in order to further increase spectral efficiency and sum rate of users, intelligent reflecting surface (IRS) is a cost-operativeresolution to improve the energy and spectral efficiency of future wireless communication networks with less complexity and hardware cost. The efficacy of proposed algorithm is verified through the simulations carried out using MATLAB software. Simulation outcomes are delivered for demonstrating that the proposed algorithm is better than conventional that results in significant improvement in achievable sum rate and reduction of outage probability.