Reinforcement Learning-Based Task Offloading of MEC-Assisted UAVs in Precision Agriculture

Recently, mobile edge computing (MEC) assisted unmanned aerial vehicles (UAVs) have brought a revolution to the existing precision agriculture (PA). The target UAVs can execute various PA tasks with different heterogeneous resource requirements on the farm. However, due to the stringent service deadline of PA tasks and the battery limitation of UAVs, one of the promising solutions is to offload those computation tasks to MEC servers jointly. This paper explores the MEC-assisted task offloading problem with multi-UAVs under different deadline constraints in uncertain real-world environments. The diverse requirements of PA tasks, the heterogeneous network status, and the dynamic loading of MEC edge servers make the offloading decision an NP-hard problem. Therefore, we propose a reinforcement learning (RL)-based task offloading approach, BANDIT-SCH, to minimize total MEC system costs to achieve online task dispatching and scheduling in uncertain environments without further global information. The experiment results show that the performance of BANDIT-SCH is approximate to the upper bound strategy, which can foresee all edge servers' detailed status.