Research on transmission strategy of non-orthogonal multiple access networks based on DDPG algorithm

• 1、Electronic and Information Engineering School,Liaoning Technical University.Huludao 125100

Abstract：As one of the key technologies in the next generation wireless network, machine learning has been applied to various wireless communication problems. This paper aims to maximize the long-term throughput of sub-users by optimizing their transmit power and time-sharing coefficient. In view of the limitations of traditional optimization tools, the deep deterministic strategy gradient (DDPG) algorithm is used to simulate this complex process. Using data rate as the evaluation index, the simulation results show that compared with greedy algorithm and random algorithm, the proposed DDPG algorithm assisted non-orthogonal multiple access (NOMA) transmission scheme has achieved significant improvement in performance. This result effectively realizes the objective of this paper, namely, applying machine learning to optimize the cognitive radio (CR) -inspired non-orthogonal multiple access (NOMA) network transport strategy, and provides a new idea and method for the field of decision simulation.

Keywords： Cognitive radio Non-orthogonal multiple access Deep deterministic policy gradient