On fair power optimization in nonorthogonal multiple access multiuser networks

Nonorthogonal multiple access (NOMA) has been recognized as a key solution to fulfill the demands of 5G wireless communication. In this paper, our aim is to maximize the fairness in the data rates of different users in a multiuser NOMA system. We optimize the downlink transmission subject to minimum rate requirement of each user, limited power budget at the transmitter, and the successive interference cancelation constraint. First, we solve the problem for two-user scenario where the nonconvex problem is transformed into a standard convex minimization problem and the duality theory is exploited to find the solution. The optimal power allocation is obtained from the Karush-Kuhn-Tucker (KKT) conditions, whereas the dual problem is solved via subgradient algorithm. As a next step, we consider the general multiuser optimization problem where more than two users can share the same channel under NOMA transmission. We design efficient solution techniques to solve the nonconvex optimization problem with sequential quadratic programming (SQP). Furthermore, two suboptimal low complexity solutions are also presented. We found that, under the proposed schemes, the fairness increases with increasing the available transmit power and decreases with the increasing the number of users. We show a complexity comparison of the dual-based solution and the SQP algorithm. It is observed that power optimization through KKT conditions exhibits much lower computational complexity as compared to the SQP-based solution.