As an important device for disaster rescue, unmanned aerial vehicles(UAVs) are usually limited by their batteries and computational power to perform complex computational tasks during the rescue process. In response to the above situation, it is proposed that the disaster rescue makes parked vehicles collaboratively perform the application tasks generated by UAVs. We organize parked vehicles into parking clusters.. Then, a task scheduling model of deep reinforcement learning(DRL) is built, in which multiple vehicles in the parking cluster are chosen to execute task data together to ensure the quality of experience(QoE) of UAVs. The experimental results demonstrate that the proposed strategy achieves a lower execution cost and higher completion rate compared with other offloading strategies.
Unmanned Aerial Vehicle Data Uploading Using Parking Resources After Disaster Rescue
2023-07-14
1703769 byte
Conference paper
Electronic Resource
English
After-disaster rescue unmanned aerial vehicle with search and rescue function
European Patent Office | 2022
|Unmanned aerial vehicle rescue device applied to emergency disaster relief
European Patent Office | 2020
|Unmanned aerial vehicle parking system and unmanned aerial vehicle parking method
European Patent Office | 2021