Volume 39, Number 2, April 2021
|Page(s)||367 - 374|
|Published online||09 June 2021|
Exploring UAV's multi-domain joint anti-jamming intelligent decision algorithm
College of Information and Navigation, Air Force Engineering University, Xi'an 710077, China
2 Key Laboratory of Aerospace Information Applications, China Electronics Technology Group, Shijiazhuang 050081, China
To understand the complex communication environment of a UAV in battlefield, its unknown channel statistics information and poor intelligent jamming and anti-jamming capability, the multi-domain anti-jamming problem is studied, and a multi-domain joint anti-jamming intelligent decision algorithm is proposed. First, the channel selection method is adopted to deal with jamming in the frequency domain. A multi-arm slot machine's channel selection model is established, and the channel interference level is judged. Secondly, the moderate interference channel is suppressed in the power domain, and the model of its Stackelberg game is established. The game equalization is solved to obtain the best transmission power and reduce the overhead caused by channel switching. The simulation results show that the long-term rewards of the intelligent decision algorithm are significantly higher than those of the traditional multi-arm slot machine's algorithm and the random selection algorithm and that the average throughput of the communication system of the UAV is improved, thus proving the superiority of the intelligent decision algorithm.
Key words: multi-domain anti-jamming / multi-arm slot machine / channel selection / Stackelberg game
关键字 : 多域抗干扰 / 多臂老虎机 / 信道选择 / Stackelberg博弈
© 2021 Journal of Northwestern Polytechnical University. All rights reserved.
This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.