SDN Enhanced Resource Orchestration of Containerized Edge Applications for Industrial IoT
| Autor: | Mika Ylianttila, Juuso Haavisto, Erkki Harjula, Ijaz Ahmad, Jude Okwuibe |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
Computer science
Distributed computing Cloud computing PowerAPI 02 engineering and technology computer.software_genre Automation NFV MongoDB 0202 electrical engineering electronic engineering information engineering cloud General Materials Science Orchestration (computing) Edge computing Docker containerization General Engineering power consumption Virtualization Scalability lcsh:TK1-9971 SDG 9 - Industry Industries InfluxDB HWPC VR MNO IoT General Computer Science Monitoring Platform as a service industry 40 Resource efficiency software defined networking (SDN) Containers Hardware edge computing IIoT Innovation latency business.industry 020208 electrical & electronic engineering 020206 networking & telecommunications SDG 8 - Decent Work and Economic Growth Network management multi-access and Infrastructure lcsh:Electrical engineering. Electronics. Nuclear engineering SDG 9 - Industry Innovation and Infrastructure Software-defined networking business SDG 12 - Responsible Consumption and Production computer Software 5G AR |
| Zdroj: | Okwuibe, J, Haavisto, J, Harjula, E, Ahmad, I & Ylianttila, M 2020, ' SDN Enhanced Resource Orchestration of Containerized Edge Applications for Industrial IoT ', IEEE Access, vol. 8, pp. 229117-229131 . https://doi.org/10.1109/ACCESS.2020.3045563 IEEE Access, Vol 8, Pp 229117-229131 (2020) |
| DOI: | 10.1109/ACCESS.2020.3045563 |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|