Ensemble Reinforcement Learning Framework for Sum Rate Optimization in NOMA-UAV Network

In this work we present an ensemble reinforcement learning (ERL) framework comprising of deep-Q networks (DQNs). The aim is to optimize sum rate for non orthogonal multiple access unmanned aerial network (NOMA-UAV) network. Power in downlink (DL) and bandwidth allotment for a NOMA cluster is managed over fixed UAV trajectory. The environment is dynamic and quality of service (QoS) requirements are varying for each node on ground. A comparative analysis between conventional reinforcement learning (CRL) framework and proposed ensemble of ERL yields a performance gain in undermentioned metrics. The ERL achieves 20 percent performance gain in average sum rate and the gain in spectral efficiency is 2 percent, over conventional reinforcement learning framework with single DQN. It also achieves high performance over different UAV speeds in cumulative sum rate and device coverage.