Abstract
The integration of semantic communication with mobile edge computing (MEC) has become a prominent research area. In this work, we explore a scenario where unmanned aerial vehicles (UAVs) are integrated with semantic communication to enhance MEC, particularly under the jamming attacks. Our research focuses on addressing a joint resource management problem, in order to minimize both the communication and computing delay while adhering to quality of service requirements and resource constraints. Given the non-convexity of this problem and the dynamic behavior of jamming attacks, this paper proposes a deep reinforcement learning (DRL) algorithm to jointly UAV trajectories, and user associations against jamming. In detail, the DRL-based resource management and anti-jamming approach in our work can effectively capture the jammer's behavior, and learn to adjust semantic task and resource scheduling strategies with the objective to minimize the negative effect of jamming attacks on task offloading and semantic communication. Simulation outcomes show that the proposed approach surpasses the baseline algorithms in terms of task completion time and total semantic spectral efficiency under different real-world settings.