Hot Paper - Learning-based joint UAV trajectory and power allocation optimization for secure IoT networks

Learning-based joint UAV trajectory and power allocation optimization for secure IoT networks

安全物联网网络中基于学习的联合无人机轨迹和功率分配优化
セキュアなIoTネットワークにおける学習に基づく共同無人機の軌跡と電力分配の最適化
보안 사물인터넷 네트워크에서 학습 기반 연합 무인기 궤적 및 전력 분배 최적화
Optimización de la trayectoria y distribución de energía de los vehículos aéreos no tripulados conjuntos basada en el aprendizaje en la red de Internet de las cosas seguras
Optimisation de la trajectoire et de l'allocation de puissance de l'UAV basée sur l'apprentissage dans le réseau sécurisé d'Internet des objets
оптимизация распределения мощности и траекторий на основе обучения

Dan Deng 邓单 ¹, Xingwang Li 李兴旺 ², Varun Menon ³, Md Jalil Piran ⁴, Hui Chen 陈慧 ², Mian Ahmad Jan ⁵

¹ School of Information Engineering, Guangzhou Panyu Polytechnic, Guangzhou, 410630, China
中国广州广州番禺职业技术学院信息工程学院
² School of Physics and Electronic Information Engineering, Henan Polytechnic University, Jiaozuo, 454150, China
中国焦作河南理工大学信息科学与工程学院
³ Department of Computer Science and Engineering, SCMS School of Engineering and Technology, India
⁴ Department of Computer Science and Engineering, Sejong University, South Korea
⁵ Department of Computer Science, Abdul Wali Khan University Mardan, Pakistan

https://doi.org/10.1016/j.dcan.2021.07.007

http://journal2.cqupt.edu.cn/DCN/dcn/ch/reader/view_abstract.aspx?file_no=20220402&flag=1

Digital Communications and Networks, 24 August 2022

Abstract

Non-Orthogonal Multiplex Access (NOMA) can be deployed in Unmanned Aerial Vehicle (UAV) networks to improve spectrum efficiency. Due to the broadcasting feature of NOMA-UAV networks, it is essential to focus on the security of the wireless system. This paper focuses on maximizing the secrecy sum rate under the constraint of the achievable rate of the legitimate channels. To tackle the non-convexity optimization problem, a reinforcement learning-based alternative optimization algorithm is proposed.

Firstly, with the help of successive convex approximations, the optimal power allocation scheme with a given UAV trajectory is obtained by using convex optimization tools. Afterwards, through plenty of explorations of the wireless environment, the Q-learning networks approach the optimal location transition strategy of the UAV, even without the wireless channel state information.

Reviews and Discussions