Deadline-aware and energy-efficient IoT task scheduling in fog computing systems: A semi-greedy approach

With the rapid advancement of Internet of Things (IoT) devices, a variety of IoT applications that require a real-time response and low latency have emerged. Fog computing has become a viable platform for processing emerging IoT applications. However, fog computing devices tend to be highly distribu...

Full description

Saved in:
Bibliographic Details
Published in:Journal of network and computer applications Vol. 201; p. 103333
Main Authors: Azizi, Sadoon, Shojafar, Mohammad, Abawajy, Jemal, Buyya, Rajkumar
Format: Journal Article
Language:English
Published: Elsevier Ltd 01.05.2022
Subjects:
Cloud computing
Deadline-aware
Energy consumption
Fog computing
Internet of Things
Semi-greedy algorithm
Task scheduling
Fog computing
Cloud computing
Energy consumption
Deadline-aware
Task scheduling
Internet of Things
Semi-greedy algorithm
ISSN:1084-8045, 1095-8592
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:With the rapid advancement of Internet of Things (IoT) devices, a variety of IoT applications that require a real-time response and low latency have emerged. Fog computing has become a viable platform for processing emerging IoT applications. However, fog computing devices tend to be highly distributed, dynamic, and resource-constrained, so deploying fog computing resources effectively for executing heterogeneous and delay-sensitive IoT tasks is a fundamental challenge. In this paper, we mathematically formulate the task scheduling problem to minimize the total energy consumption of fog nodes (FNs) while meeting the quality of service (QoS) requirements of IoT tasks. We also consider the minimization of the deadline violation time in our model. Next, we propose two semi-greedy based algorithms, namely priority-aware semi-greedy (PSG) and PSG with multistart procedure (PSG-M), to efficiently map IoT tasks to FNs. We evaluate the performance of the proposed task scheduling approaches with respect to the percentage of IoT tasks that meet their deadline requirement, total energy consumption, total deadline violation time, and the system’s makespan. Compared with existing algorithms, the experiment results confirm that the proposed algorithms improve the percentage of tasks meeting their deadline requirement up to 1.35x and decrease the total deadline violation time up to 97.6% compared to the second-best results, respectively, while the energy consumption of fog resources and makespan of the system are optimized.
ISSN:1084-8045
1095-8592
DOI:10.1016/j.jnca.2022.103333