Delay-Optimal Task Offloading for UAV-Enabled Edge-Cloud Computing Systems

doi:10.1109/ACCESS.2022.3174127

Delay-Optimal Task Offloading for UAV-Enabled Edge-Cloud Computing Systems

2022-01-01

25

OA

AI

Jaafar M. H. Elmirghani

DOI：10.1109/ACCESS.2022.3174127

Original

Original request for help

Save

Abstract

En 中文

The emergence of delay-sensitive and computationally-intensive mobile applications and services pose a significant challenge for Unmanned Aerial Vehicles (UAVs) devices due to the scarcity in their resources such as computational power and battery lifetime. Mobile cloud computing has been introduced as a promising solution to overcome these limitations through task offloading. However, high-latency and security issues are considered the main challenges of this paradigm. Subsequently, the edge-cloud computing paradigm has been introduced and widely used to help to mitigate these issues. Nevertheless, the current task offloading models permit UAVs to execute their intensive tasks at the connected edge server, which leads to excessive loads due to the large number of UAVs and thereby increases the delay. Therefore, in this paper, we propose a delay-optimal task offloading approach for multi-tier edge-cloud computing in a multi-user environment. The problem is formulated as an optimization model using Integer Linear Programming (ILP) techniques to minimize the total service time of UAVs. Simulation results demonstrate that the proposed approach not only saves the service time by 33.5% and 55% for edge and cloud execution policies respectively, but also scales well for a large number of UAVs.

Keywords:

Task analysis

Servers

Computational modeling

Delays

Cloud computing

Simulation

Optimization

Computation offloading

edge-cloud computing

mobile edge computing

optimization

Internet of Things

unmanned aerial vehicles

linear programming

Delay-Optimal Task Offloading for UAV-Enabled Edge-Cloud Computing Systems

Abstract

Journal

Organization