Reinforcement Learning-Based Dynamic Anti-Jamming Power Control in UAV Networks: An Effective Jamming Signal Strength Based Approach

Unmanned aerial vehicle (UAV) assisted air-to-ground (A2G) communication is vulnerable to malicious jamming due to the broadcast nature of wireless communications. In this letter, an anti-jamming power control framework with an unknown jamming model and unknown transmission power is proposed. In particular, the probability density function (PDF) of the effective jamming signal strength (EJSS) is first estimated via kernel density estimation (KDE). Then, utilizing the EJSS, a deep deterministic policy gradient (DDPG) based framework is proposed to acquire the power control strategy in real time. Moreover, a trajectory design scheme based on K-means++ is proposed to track the location of users. The simulation results show that the proposed framework yields an improved sum rate and energy efficiency over the reference schemes.

Automated summary

This paper proposes an anti-jamming power control framework that improves the sum rate and energy efficiency of UAV-assisted air-to-ground communication. It also tracks user locations through a trajectory design scheme.