Decentralized Relay Selection for Large-Scale Dynamic UAVs Networks: A Mood-Driven Approach

Xijian ZHONG  Yan GUO  Ning LI  Shanling LI  Aihong LU  

IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences   Vol.E102-A    No.12    pp.2031-2036
Publication Date: 2019/12/01
Online ISSN: 1745-1337
DOI: 10.1587/transfun.E102.A.2031
Type of Manuscript: LETTER
Category: Communication Theory and Signals
cooperative communication,  opportunistic relay selection,  online learning,  dynamic UAVs networks,  

Full Text: PDF>>
Buy this Article

In the large-scale multi-UAV systems, the direct link may be invalid for two remote nodes on account of the constrained power or complex communication environment. Idle UAVs may work as relays between the sources and destinations to enhance communication quality. In this letter, we investigate the opportunistic relay selection for the UAVs dynamic network. On account of the time-varying channel states and the variable numbers of sources and relays, relay selection becomes much more difficult. In addition, information exchange among all nodes may bring much cost and it is difficult to implement in practice. Thus, we propose a decentralized relay selection approach based on mood-driven mechanism to combat the dynamic characteristics, aiming to maximize the total capacity of the network without information exchange. With the proposed approach, the sources can make decisions only according to their own current states and update states according to immediate rewards. Numerical results show that the proposed approach has attractive properties.