Fast Uplink Grant for NOMA: A Federated Learning Based Approach

Recently, non-orthogonal multiple access (NOMA) technique has emerged and is being considered as a building block of 5G systems and beyond. In this paper, we focus on the resource allocation for NOMA-based systems and we investigate how Machine Type Devices (MTDs) can be arranged into clusters. Specifically, we propose two allocation techniques to enable the integration of massive NOMA-based MTD in the 5G. Firstly, we propose a low-complexity schema where the base station (BS) assigns an MTD to a cluster based on its Channel State Information (CSI) and transmit power in order to ensure that the Successive Interference Cancellation (SIC) can be performed in the uplink as well as the downlink. The proposed technique enable us to allocate an optimal number of MTDs without inter-NOMA-interference (INI), while being of low complexity and communication overhead. In the second framework, we propose a Federated Learning (FL) based-technique using traffic model estimation at the MTD side in order to extend the capacity of the system. In fact, the BS take into account the traffic model of the MTDs in order to use time multiplexing in addition to the power multiplexing to separate MTDs. Then, we propose a synchronization method to allow contending MTDs synchronize their transmissions. Simulation results show that the proposed techniques outperform existing schemes in the literature.