Version 1
: Received: 25 May 2023 / Approved: 26 May 2023 / Online: 26 May 2023 (05:26:11 CEST)
How to cite:
Lv, P.; Wang, K.; Zhang, Z. A Server Deployment and Task Scheduling Framework in Multi-Edge Collaborative Computing. Preprints2023, 2023051863. https://doi.org/10.20944/preprints202305.1863.v1
Lv, P.; Wang, K.; Zhang, Z. A Server Deployment and Task Scheduling Framework in Multi-Edge Collaborative Computing. Preprints 2023, 2023051863. https://doi.org/10.20944/preprints202305.1863.v1
Lv, P.; Wang, K.; Zhang, Z. A Server Deployment and Task Scheduling Framework in Multi-Edge Collaborative Computing. Preprints2023, 2023051863. https://doi.org/10.20944/preprints202305.1863.v1
APA Style
Lv, P., Wang, K., & Zhang, Z. (2023). A Server Deployment and Task Scheduling Framework in Multi-Edge Collaborative Computing. Preprints. https://doi.org/10.20944/preprints202305.1863.v1
Chicago/Turabian Style
Lv, P., KaiFan Wang and Zhen Zhang. 2023 "A Server Deployment and Task Scheduling Framework in Multi-Edge Collaborative Computing" Preprints. https://doi.org/10.20944/preprints202305.1863.v1
Abstract
With the rapid development of the Internet of Things, massive amounts of data will be generated at the network edge, resulting in increased latency of the traditional cloud computing model. Cloud service providers deploy edge servers near the users to improve the quality of service. Due to the large scale of networks, the inefficiency of edge server deployment and task scheduling will result in excessive latency and severe workload imbalance among edge servers. In this paper, we propose a Server Deployment and Task Scheduling (SDTS) framework in multi-edge collaborative computing, which can effectively reduce latency and ensure workload balancing. First, a metropolitan area network (MAN) is divided into dense candidate regions (DCRs) based on the density characteristics of mobile end devices, and then servers are deployed independently in each sub-region. Then, a two-step clustering algorithm is designed to deploy servers as close as possible to the mobile devices. Finally, a task scheduling algorithm is presented based on an edge scheduling layer in DCRs, which can leverage collaboration between edge servers to improve the performance of the entire edge computing system. The experimental results based on the Cellular Base Station (CBS) dataset of Shanghai Telecom indicate that the proposed approach outperforms several representative strategies in terms of latency and workload balancing.
Keywords
Mobile edge computing; Task scheduling; Edge server deployment; Edge server placement; Workload balancing; Latency
Subject
Computer Science and Mathematics, Computer Networks and Communications
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.