Research on User Pairing and Power Allocation in Multiuser CRN-NOMA Networks Based on Reinforcement Learning

This paper studies the challenge of efficient resource allocation in wireless networks by investigating the potential benefits of cognitive radio networks (CRN) and non-orthogonal multiple access (NOMA) techniques. Specifically, the purpose of this paper is to explore user pairing and power allocation in a multiuser cooperative CRN-NOMA network. To achieve the goal, a novel user pairing algorithm with reinforcement learning (RL) is proposed to adaptively select the optimal group for pairing according to the factors such as channel gain, distances, and angles. A user group is consisted of a primary user (PU) and up to three secondary users (SUs). The key findings of this paper highlight the effectiveness of RL in optimizing power allocation while considering various constraints. As a result, significant improvements in network throughput and user fairness are achieved. Compared with the classical power allocation algorithms (i.e., equal power allocation, proportional power allocation, iterative power allocation, and iterative water-filling power allocation), the proposed power allocation based on RL algorithm and iterative water-filling power allocation algorithm have better performance in terms of throughput, fairness, spectrum efficiency, and energy efficiency. In addition, compared with the iterative water-filling power algorithm, the proposed algorithm improves the throughput by 31.71% and obtains twice the spectrum efficiency and energy efficiency. The simulation results consistently show that the proposed method has advantages in enhancing PU capacity. Further advancements in this field of research are encouraged based on the promising outcomes of this study.