A three-stage heuristic task scheduling for optimizing the service level agreement satisfaction in device-edge-cloud cooperative computing

• Published in: PeerJ. Computer science 2022-01, Vol.8, p.e851-e851, Article e851
• Main Authors: Sang, Yongxuan, Cheng, Junqiang, Wang, Bo, Chen, Ming
• Format: Article
• Language: English
• Subjects: Cloud computing; Computer Architecture; Computer Networks and Communications; Deadlines; Devices; Distributed and Parallel Computing; Edge cloud; Edge computing; Embedded Computing; Heuristic; Heuristic methods; Heuristic task scheduling; Internet; Mobile and Ubiquitous Computing; Nonlinear programming; Optimization; Polynomials; Resource scheduling; Response time; Scheduling; Servers; Task offloading; Task scheduling
• ISSN: 2376-5992; 2376-5992
• DOI: 10.7717/PEERJ-CS.851

Device-edge-cloud cooperative computing is increasingly popular as it can effectively address the problem of the resource scarcity of user devices. It is one of the most challenging issues to improve the resource efficiency by task scheduling in such computing environments. Existing works used limited resources of devices and edge servers in preference, which can lead to not full use of the abundance of cloud resources. This article studies the task scheduling problem to optimize the service level agreement satisfaction in terms of the number of tasks whose hard-deadlines are met for device-edge-cloud cooperative computing. This article first formulates the problem into a binary nonlinear programming, and then proposes a heuristic scheduling method with three stages to solve the problem in polynomial time. The first stage is trying to fully exploit the abundant cloud resources, by pre-scheduling user tasks in the resource priority order of clouds, edge servers, and local devices. In the second stage, the proposed heuristic method reschedules some tasks from edges to devices, to provide more available shared edge resources for other tasks cannot be completed locally, and schedules these tasks to edge servers. At the last stage, our method reschedules as many tasks as possible from clouds to edges or devices, to improve the resource cost. Experiment results show that our method has up to 59% better performance in service level agreement satisfaction without decreasing the resource efficiency, compared with eight of classical methods and state-of-the-art methods.