University of Oulu

J. Okwuibe, J. Haavisto, E. Harjula, I. Ahmad and M. Ylianttila, "SDN Enhanced Resource Orchestration of Containerized Edge Applications for Industrial IoT," in IEEE Access, vol. 8, pp. 229117-229131, 2020, doi: 10.1109/ACCESS.2020.3045563

SDN enhanced resource orchestration of containerized edge applications for ondustrial IoT

Saved in:
Author: Okwuibe, Jude1; Haavisto, Juuso2; Harjula, Erkki1;
Organizations: 1Center for Wireless Communication, University of Oulu, 90014 Oulu, Finland
2Center for Ubiquitous Computing, University of Oulu, 90014 Oulu, Finland
3VTT Technical Research Center of Finland, 02044 Espoo, Finland
Format: article
Version: published version
Access: open
Online Access: PDF Full Text (PDF, 2.8 MB)
Persistent link: http://urn.fi/urn:nbn:fi-fe202101283010
Language: English
Published: Institute of Electrical and Electronics Engineers, 2020
Publish Date: 2021-01-28
Description:

Abstract

With the rise of the Industrial Internet of Things (IIoT), there is an intense pressure on resource and performance optimization leveraging on existing technologies, such as Software Defined Networking (SDN), edge computing, and container orchestration. Industry 4.0 emphasizes the importance of lean and efficient operations for sustainable manufacturing. Achieving this goal would require engineers to consider all layers of the system, from hardware to software, and optimizing for resource efficiency at all levels. This emphasizes the need for container-based virtualization tools such as Docker and Kubernetes, offering Platform as a Service (PaaS), while simultaneously leveraging on edge technologies to reduce related latencies. For network management, SDN is poised to offer a cost-effective and dynamic scalability solution by customizing packet handling for various edge applications and services. In this paper, we investigate the energy and latency trade-offs involved in combining these technologies for industrial applications. As a use case, we emulate a 3D-drone-based monitoring system aimed at providing real-time visual monitoring of industrial automation. We compare a native implementation to a containerized implementation where video processing is orchestrated while streaming is handled by an external UE representing the IIoT device. We compare these two scenarios for energy utilization, latency, and responsiveness. Our test results show that only roughly 16 percent of the total power consumption happens on the mobile node when orchestrated. Virtualization adds up about 4.5 percent of the total power consumption while the latency difference between the two approaches becomes negligible after the streaming session is initialized.

see all

Series: IEEE access
ISSN: 2169-3536
ISSN-E: 2169-3536
ISSN-L: 2169-3536
Volume: 8
Pages: 229117 - 229131
DOI: 10.1109/ACCESS.2020.3045563
OADOI: https://oadoi.org/10.1109/ACCESS.2020.3045563
Type of Publication: A1 Journal article – refereed
Field of Science: 213 Electronic, automation and communications engineering, electronics
Subjects:
5G
AR
IoT
MNO
NFV
VR
Funding: This work was supported in part by the Academy of Finland 6Genesis Flagship under Grant 318927, and in part by the AI Enhanced Mobile Edge Computing project, funded by the Future Makers program of Jane and Aatos Erkko Foundation and Technology Industries of Finland Centennial Foundation. The work of Ijaz Ahmad was supported by the Jorma Ollila Grant.
Academy of Finland Grant Number: 318927
Detailed Information: 318927 (Academy of Finland Funding decision)
Copyright information: © The Authors 2020. This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/.
  https://creativecommons.org/licenses/by/4.0/