基于非正交多址接入的B5G双向全双工中继系统中功率控制的设计  

DESIGN OF POWER CONTROL IN B5G TWO-WAY FULL-DUPLEX RELAY SYSTEMS BASED ON NON-ORTHOGONAL MULTIPLE ACCESS

作　　者：唐睿 朱通 张睿智 何金璞 Tang Rui;Zhu Tong;Zhang Ruizhi;He Jinpu(School of Electronic Information Engineering,China West Normal University,Nanchong 637002,Sichuan,China;College of Mechanical and Electrical Engineering,Chengdu University of Technology,Chengdu 610059,Sichuan,China;Pan-Asia Business School,Yunnan Normal University,Kunming 650092,Yunnan,China)

机构地区：[1]西华师范大学电子信息工程学院,四川南充637002 [2]成都理工大学机电工程学院,四川成都610059 [3]云南师范大学泛亚商学院,云南昆明650092

出　　处：《计算机应用与软件》2025年第4期92-99,共8页Computer Applications and Software

基　　金：国家自然科学基金项目(62301450);四川省科技厅自然科学基金项目(24NSFSC5070)。

摘　　要：在基于非正交多址接入的后五代(Beyond the Fifth Generation,B5G)双向全双工中继系统中,为协调同频干扰并提升频谱效率,首先提出一种基于连续凸逼近(Successive Convex Approximation,SCA)算法的功率控制机制,保证多项式时间内得到原非凸问题的高效次优解。为满足B5G移动网络的低时延需求,进一步提出一种基于深度神经网络(Deep Neural Network,DNN)的在线功率控制机制。仿真结果验证了所提机制的有效性,发现相比于基于SCA算法的机制,基于DNN的机制能获得相近性能且大幅度降低在线运算时间。In two-way full-duplex relay systems based on non-orthogonal multiple access(NOMA)for Beyond the Fifth Generation(B5G)networks,we propose a power control mechanism using successive convex approximation(SCA)to coordinate co-channel interference and improve spectral efficiency,which efficiently obtains suboptimal solutions for the original non-convex problem within polynomial time.To satisfy the low-latency requirements of B5G mobile networks,we further design a deep neural network(DNN)-based online power control mechanism.Simulations verify the effectiveness of both mechanisms,showing that the DNN-based approach achieves comparable performance to the SCA-based method while significantly reducing online computational time.

关 键 词：B5G移动网络 非正交多址接入 全双工中继 功率控制 连续凸逼近 深度神经网络 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]