Efficient Task Scheduling and Offloading for UAV Networks using Nash and ML Approach

UAV

With the increasing number of Internet of Things (IoT) devices, effective computing performance has become a critical issue. Strong processing power is required for a multitude of Internet of Things applications, including traffic control, augmented reality, location tracking, and autonomous driving, which all need extensive real-time data processing. The introduction of Mobile Edge Computing (MEC), aims to safely and effectively tackle this issue via the internet. IoT devices may now be used to offload computationally demanding activities by including a MEC server. Delays and transmission cost, however, are significant disadvantages. By serving as MEC servers, Unmanned Aerial Vehicles (UAV), could potentially lessen this problem thanks to their great mobility and inexpensive cost. No matter where a user is, mobile networks offer wireless access. These networks may transmit and receive data utilising neighbour connectivity, and they are self-configurable. Sensors, mobile devices, routers, and many other tiny devices can be used to create this network. However, because these devices are small and unable to perform complex computations, the author of this paper uses 5G enabled UAV based community offloading, in which UAVs move to various positions and mobile devices offload or schedule tasks to the closest freestanding (UAV with less load) UAV. After receiving a job, the UAV will schedule it to be sent to a task processors or base station, which will process it and return the results to the UAV, which will then transmit it to a mobile device.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.