Deep Reinforcement Learning Based Dynamic Trajectory Control for UAV-Assisted Mobile Edge Computing

In this paper, we consider a platform of flying mobile edge computing (F-MEC), where unmanned aerial vehicles (UAVs) serve as equipment providing computation resource, and they enable task offloading from user (UE). We aim to minimize energy consumption all UEs via optimizing association, resource allocation the trajectory UAVs. To end, first propose Convex optimizAtion based Trajectory control algorithm (CAT), which solves problem in an iterative way by using block coordinate descent (BCD) method. Then, make real-time decision while taking into account dynamics environment (i.e., UAV may take off different locations), deep Reinforcement leArning (RAT). RAT, apply Prioritized Experience Replay (PER) improve convergence training procedure. Different convex optimization be susceptible initial points requires iterations, RAT can adapted any UAVs obtain solution more rapidly than CAT once process has been completed. Simulation results show that proposed achieve considerable performance both outperform traditional algorithms.