Please use this identifier to cite or link to this item:
https://ruomo.lib.uom.gr/handle/7000/1036
Title: | The NECOS Approach to End-to-End Cloud-Network Slicing as a Service |
Authors: | Clayman, Stuart Neto, Augusto Venancio Verdi, Fabio L. Correa, Sand L. Sampaio, Silvio Sakellariou, Ilias Mamatas, Lefteris Pasquini, Rafael Cardoso, Kleber V. Tusa, Francesco Rothenberg, Christian Serrat, Joan |
Type: | Article |
Subjects: | FRASCATI::Natural sciences::Computer and information sciences |
Keywords: | Network slicing Cloud computing Data centers Runtime Machine learning Elasticity |
Issue Date: | Mar-2021 |
Source: | IEEE Communications Magazine |
Volume: | 59 |
Issue: | 3 |
First Page: | 91 |
Last Page: | 97 |
Abstract: | Cloud-network slicing is a promising approach to serve vertical industries delivering their services over multiple administrative and technological domains. However, there are numerous open challenges to provide end-to-end slices due to complex business and engineering requirements from service and resource providers. This article presents a reference architecture for the cloud-network slicing concept and the practical realization of the slice-as-a-service paradigm, which are key results from the Novel Enablers in Cloud Slicing (NECOS) project. The NECOS platform has been designed to consider modularity, separation of concerns, and multi-domain dynamic operation as prime attributes. The architecture comprises a set of interworking components to automatically create, manage, and decommission end-to-end cloud-network slice instances in a lightweight manner. NECOS orchestrates slices at runtime, spanning across core/edge data centers and wired/wireless network infrastructures. The novelties of the multi-domain NECOS platform are validated through three proof-of-concept experiments: (i) a touristic content delivery service slice deployment featuring on-demand virtual infrastructure management across three countries on different continents to meet particular slice requirements; (ii) intelligent slice elasticity driven by machine learning techniques; and (iii) market-place-based resource discovery capabilities. |
URI: | https://doi.org/10.1109/MCOM.001.2000702 https://ruomo.lib.uom.gr/handle/7000/1036 |
ISSN: | 0163-6804 1558-1896 |
Other Identifiers: | 10.1109/MCOM.001.2000702 |
Appears in Collections: | Department of Applied Informatics |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
NECOS_Approach_to_End_to_EndCloud_Network_Slicing_as_a_Service_COMMAG_20_00702-preprint1.pdf | 2,54 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.