VNET: Towards End-to-End Network Cloudification

Abstract : To address the needs for future network services, existing network architecture should evolve significantly to provide a higher level of flexibility, resilience and quality of service. This challenge was also the one of computing which has found with " virtualization " a breakthrough approach to bring a high flexibility in existing computing architecture which makes today the success of cloud computing. The next obvious following step is therefore to " cloudify " the networks. We introduce the VNET project, which proposes to study some of the most complex network cloudification problems from a global point of view i.e at radio access networks and the core networks to the service hosting data centers. It will identify the challenges and address the problems related to the visualization of RAN (Radio Access Networks), the problems of service composition and dependability related to the deployment of SDN and NFV, and finally the design a NaaS platform with the associated tools to allow the specification, validation, deployment and management of on-demand end-to-end services. In addition, the project will address the manageability of this " cloudified " architecture using autonomic concepts based on the MAPE framework.
Document type :
Conference papers
Complete list of metadatas

Cited literature [15 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01775507
Contributor : Frédéric Davesne <>
Submitted on : Tuesday, April 24, 2018 - 3:34:43 PM
Last modification on : Monday, October 28, 2019 - 10:50:22 AM
Long-term archiving on: Wednesday, September 19, 2018 - 1:05:09 PM

File

ADVANCE2017-paper4.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01775507, version 1

Citation

Elie Rachkidi, Nazim Agoulmine, Javier Baliosian, Javier Bustos. VNET: Towards End-to-End Network Cloudification. 5th International Workshop on ADVANCEs in ICT Infrastructures and Services (ADVANCE 2017), Jan 2017, Evry, France. ⟨hal-01775507⟩

Share

Metrics

Record views

152

Files downloads

146