Resource Allocation for Minimizing the Transmit Power in Uplink NOMA IoT Cellular Networks

In this paper, we study algorithms that minimize the total transmit power of all users and the maximum transmit power among all users' transmit power, respectively, while meeting the minimum achievable rate required for all IoT users in uplink non-orthogonal multiple access (NOMA) IoT cellular networks. Specifically, we propose two-step optimization algorithms that sequentially perform sub-band assignment and transmit power control for each IoT user, in which a genetic algorithm (GA) is applied for sub-band assignment whereas unsupervised learning (USL) implemented as fully-connected deep neural network (DNN) models is utilized for transmit power control. Extensive numerical simulations are shown that our proposed two-step algorithm can approach the optimal performance achievable through exhaustive search-based methods with much lower computational complexity.