Unmanned Aerial Vehicle Computation Task Scheduling Based on Parking Resources in Post-Disaster Rescue

Natural disasters bring huge loss of life and property to human beings. Unmanned aerial vehicles (UAVs) own the advantages high mobility, flexibility, rapid deployment, are important equipment during post-disaster rescue. However, UAVs usually have restricted battery computing power. They not fit for performing compute-intensive tasks Since there widespread parking resources in a city, multiple parked working together compute applications from rescue is investigated ensure quality experience (QoE) UAVs. To execute uploaded task effectively, surviving within monitoring range an UAV arranged into cluster as much possible. Then, execution cost analyzed. Furthermore, deep reinforcement learning (DRL)-based offloading policy constructed, which interacts with environment intelligent way achieve optimization goals. The simulation experiments show that proposed scheme has higher completion rate lower than other baselines schemes.