基于人工智能算法的功率域NOMA系统功率分配方法研究

Research on the Power Allocation Method Based on the AI Algorithm for Power-Domain NOMA System

为了满足移动通信快速发展的需求,非正交多址已经成为下一代移动通信中最有前途的技术之一。由于通信系统能量效率和功率之间的密切关系,研究NOMA系统的功率分配策略显得极为迫切。重点研究了功率域NOMA系统下行链路中的功率分配策略,提出用人工智能领域的强化学习算法来解决功率分配问题的方法,以提高系统的能量效率。仿真结果证明了所提算法的收敛性,同时表明使用强化学习算法可以有效地提高整个系统的能量效率。

In order to meet the rapid development of mobile communications, non-orthogonal multiple access（NOMA） has become one of the most promising technologies in the next generation of cellular communications. Due to the close relationship between the energy efficiency and power in communication systems, the research on the power allocation strategy for NOMA systems is highly urgent. The power allocation strategy in the downlink for powerdomain NOMA systems is investigated. The reinforcement learning algorithm in the field of the artificial intelligence is suggested to deal with the power allocation to improve the system energy efficiency. Simulation results verify the convergence of the proposed algorithm and show that the use of reinforcement learning algorithm can effectively improve the energy efficiency of the entire system.