On the Optimization of UAV-enabled Task Offloading Services

Given the high mobility and flexible deployment of UAVs, this technology has evolved as a key enabler of several applications such as aerial cargo delivery and precision agriculture. However, with the advancement of its payload, including storage and computing capabilities, UAVs can handle critical services such as road traffic monitoring, accident prediction, and vehicular traffic/task offloading. Specifically, the edge computing-enabled UAVs can support critical intelligent transportation services (ITS) in both remote areas and traffic jammed events. However, how to efficiently offload task to the UAVs with respect to the latter’s intrinsic characteristics, is an under-investigated problem. In this project, we aim to develop novel and intelligent (machine-learning based) energy-efficient task offloading strategies, to maximize the rate of satisfied tasks while saving the UAVs’ energy. The outcome of this work will stimulate the development of UAV-enabled industrial platforms dedicated to ITS and broadly to public safety services.

Faculty Supervisor:

Wael Jaafar

Student:

Partner:

École supérieure de communications de Tunis (SUP'COM)

Discipline:

Engineering

Sector:

Technology; Aerospace; Transportation (excluding aerospace)

University:

École de technologie supérieure

Program: