Resource Allocation for NOMA based Heterogeneous IoT with Imperfect SIC: A Deep Learning Method

Abstract

In this paper, an energy efficient resource allocation (RA) problem is introduced for a NOMA based heterogeneous IoT. Particularly, the successive interference cancelation (SIC) is assumed imperfect for implementations. Accordingly, a stepwise scheme is presented with the mutual interference management. Specifically, a deep learning based algorithm is proposed to solve the problem optimally and rapidly. The simulation results verify that the proposed RA scheme provides the optimal results for the NOMA based heterogeneous IoT with fast convergence and low computational complexity. Compared with the OFDMA scheme, the NOMA based scheme yields better performance on the spectrum efficiency (SE) and the scale of connectivity, at the cost of high power consumption and low energy efficiency (EE).