期刊
IEEE COMMUNICATIONS LETTERS
卷 27, 期 1, 页码 190-194出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/LCOMM.2022.3214146
关键词
Relays; Internet of Things; Q-learning; Protocols; Mathematical models; Approximation algorithms; Training; cooperative communication; multiple relay selection; deep reinforcement learning; lifetime
This letter addresses the joint lifetime-outage optimization in relay-enabled IoT networks using a multiple relay selection scheme. The proposed DDQN-MRS scheme achieves superior performance compared to benchmark MRS schemes, as shown by our results.
Network lifetime maximization in Internet of things (IoT) is of paramount importance to ensure uninterrupted data transmission and reduce the frequency of battery replacement. This letter deals with the joint lifetime-outage optimization in relay-enabled IoT networks employing a multiple relay selection (MRS) scheme. The considered MRS problem is essentially a general nonlinear 0-1 programming which is NP-hard. In this work, we use the application of the double deep Q network (DDQN) algorithm to solve the MRS problem. Our results reveal that the proposed DDQN-MRS scheme can achieve superior performance than the benchmark MRS schemes.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据