Integer particle swarm optimization based task scheduling for device-edge-cloud cooperative computing to improve SLA satisfaction

Task scheduling helps to improve the resource efficiency and the user satisfaction for Device-Edge-Cloud Cooperative Computing (DE3C), by properly mapping requested tasks to hybrid device-edge-cloud resources. In this paper, we focused on the task scheduling problem for optimizing the Service-Level...

Full description

Saved in:
Bibliographic Details
Published in:PeerJ. Computer science 2022-02, Vol.8, p.e893-e893, Article e893
Main Authors: Wang, Bo, Cheng, Junqiang, Cao, Jie, Wang, Changhai, Huang, Wanwei
Format: Article
Language:English
Subjects:
Cloud computing
Computer Architecture
Deadlines
Distributed and Parallel Computing
Edge cloud
Efficiency
Genetic algorithms
Heuristic
Integers
Internet of Things
Nonlinear programming
Optimization
Particle swarm optimization
Scheduling
Task offloading
Task scheduling
User satisfaction
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Task scheduling helps to improve the resource efficiency and the user satisfaction for Device-Edge-Cloud Cooperative Computing (DE3C), by properly mapping requested tasks to hybrid device-edge-cloud resources. In this paper, we focused on the task scheduling problem for optimizing the Service-Level Agreement (SLA) satisfaction and the resource efficiency in DE3C environments. Existing works only focused on one or two of three sub-problems (offloading decision, task assignment and task ordering), leading to a sub-optimal solution. To address this issue, we first formulated the problem as a binary nonlinear programming, and proposed an integer particle swarm optimization method (IPSO) to solve the problem in a reasonable time. With integer coding of task assignment to computing cores, our proposed method exploited IPSO to jointly solve the problems of offloading decision and task assignment, and integrated earliest deadline first scheme into the IPSO to solve the task ordering problem for each core. Extensive experimental results showed that our method achieved upto 953% and 964% better performance than that of several classical and state-of-the-art task scheduling methods in SLA satisfaction and resource efficiency, respectively.
ISSN:2376-5992
2376-5992
DOI:10.7717/peerj-cs.893