摘要
以接收端的平均接收信噪比(SNR)最大化为目标,两跳放大转发中继网络多中继选择策略问题被规划为0-1非线性整数规划问题,其最优解只可以利用穷举法得到.提出基于深度学习多中继选择策略,降低时间复杂度.仿真结果表明:与穷举法相比,该方法能够达到几乎相同的平均接收SNR,且其时间复杂度明显低于穷举法.
The problem of multi-relay selection in a two-hop amplify-and-forward relay network was studied in this paper.Aiming at maximizing the average receiving signal-to-noise ratio(SNR)of the receiver,the problem was firstly considered as 0-1 nonlinear integer programming problem which was an NP-hard problem and the optimal solution could only be obtained by exhaustive method.In this paper,we proposed one kind of multi-relay selection strategyin a two-hop amplify-and-forward relay network based on deep learning to reduce the time complexity.Simulation results showed that the method achieved the same average receiving SNR as the exhaustive method,and the time complexity was significantly reduced compared with the exhaustive method.
作者
方国杏
贾楠楠
张逸凡
王龙龙
王淑贤
杨茹
彭张节
FANG Guoxing;JIA Nannan;ZHANG Yifan;WANG Longlong;WANG Shuxian;YANG Ru;PENG Zhangjie(College of Information,Mechanical and Electrical Engineering,Shanghai Normal University,Shanghai 201418,China;National Mobile Communications Research Laboratory,School of Information Science and Engineering,Southeast University,Nanjing 211189,Jiangsu,China)
出处
《上海师范大学学报（自然科学版）》
2020年第1期56-61,共6页
Journal of Shanghai Normal University(Natural Sciences)
基金
国家自然科学基金(61701307)
东南大学信息科学与工程学院移动通信国家重点实验室开放研究基金(2018D14)。
关键词
两跳放大转发中继网络
多中继选择
深度学习
平均接收信噪比(SNR)
时间复杂度
two-hop amplify-and-forward relay network
multi-relay selection
deep learning
average receiving signal-to-noise ratio(SNR)
time complexity
