A Collaborative Learning-Based Algorithm for Task Offloading in UAV-Aided Wireless Sensor Networks

Recently, unmanned aerial vehicles (UAVs) have emerged to enhance data processing, network monitoring, disaster management and other useful applications in many different networks. Due to their flexibility, cost efficiency and powerful capabilities, combining these UAVs with the existing wireless sensor networks (WSNs) could improve network performance and enhance the network lifetime in such networks. In this research, we propose a task offloading mechanism in UAV-aided WSN by implementing a utility-based learning collaborative algorithm that will enhance the service satisfaction rate, taking into account the delay requirements of the submitted tasks. The proposed learning algorithm predicts the queuing delays of all UAVs instead of having a global overview of the system, which reduces the communication overhead in the network. The simulation results showed the effectiveness of our proposed work in terms of service satisfaction ratio compared with the non-collaborative algorithm that only processes the task locally in the WSN cluster.