Dynamic control of NFV forwarding graphs with end-to-end deadline constraints

Victor Millnert; Johan Eker; Enrico Bini

doi:10.1109/ICC.2017.7996596

Dynamic control of NFV forwarding graphs with end-to-end deadline constraints

Victor Millnert, Johan Eker, Enrico Bini

University of Turin

Research output: Chapter in Book/Report/Conference proceeding › Paper in conference proceeding › peer-review

Abstract

There is a strong industrial drive to use cloud computing technologies and concepts for providing timing sensitive services in the networking domain since it would provide the means to share the physical resources among multiple users and thus increase the elasticity and reduce the costs. In this work, we develop a mathematical model for user-stateless virtual network functions forming a forwarding graph. The model captures uncertainties of the performance of these virtual resources as well as the time-overhead needed to instantiate them. The model is used to derive a service controller for horizontal scaling of the virtual resources as well as an admission controller that guarantees that packets exiting the forwarding graph meet their end-to-end deadline. The Automatic Service and Admission Controller (AutoSAC) developed in this work uses feedback and feedforward making it robust against uncertainties of the underlying infrastructure. Also, it has a fast reaction time to changes in the input.

Original language	English
Title of host publication	2017 IEEE International Conference on Communications (ICC)
Number of pages	7
ISBN (Electronic)	978-146738999-0
DOIs	https://doi.org/10.1109/ICC.2017.7996596
Publication status	Published - 2017 Jul 31
Event	IEEE International Conference on Communications 2017: IEEE ICC 2017 - Paris, France Duration: 2017 May 21 → 2017 Aug 25 http://icc2017.ieee-icc.org

Conference

Conference	IEEE International Conference on Communications 2017
Country/Territory	France
City	Paris
Period	2017/05/21 → 2017/08/25
Internet address	http://icc2017.ieee-icc.org

Subject classification (UKÄ)

Control Engineering

Free keywords

uncertainty
cloud computing
hardware
fabrics
mathematical model
admission control
virtual machines
network function virtualization

Access to Document

10.1109/ICC.2017.7996596

Cite this

@inproceedings{02216f13b861416a821e2f16228acaff,

title = "Dynamic control of NFV forwarding graphs with end-to-end deadline constraints",

abstract = "There is a strong industrial drive to use cloud computing technologies and concepts for providing timing sensitive services in the networking domain since it would provide the means to share the physical resources among multiple users and thus increase the elasticity and reduce the costs. In this work, we develop a mathematical model for user-stateless virtual network functions forming a forwarding graph. The model captures uncertainties of the performance of these virtual resources as well as the time-overhead needed to instantiate them. The model is used to derive a service controller for horizontal scaling of the virtual resources as well as an admission controller that guarantees that packets exiting the forwarding graph meet their end-to-end deadline. The Automatic Service and Admission Controller (AutoSAC) developed in this work uses feedback and feedforward making it robust against uncertainties of the underlying infrastructure. Also, it has a fast reaction time to changes in the input.",

keywords = "uncertainty, cloud computing, hardware, fabrics, mathematical model, admission control, virtual machines, network function virtualization",

author = "Victor Millnert and Johan Eker and Enrico Bini",

year = "2017",

month = jul,

day = "31",

doi = "10.1109/ICC.2017.7996596",

language = "English",

booktitle = "2017 IEEE International Conference on Communications (ICC)",

note = "IEEE International Conference on Communications 2017 : IEEE ICC 2017 ; Conference date: 21-05-2017 Through 25-08-2017",

url = "http://icc2017.ieee-icc.org",

}

TY - GEN

T1 - Dynamic control of NFV forwarding graphs with end-to-end deadline constraints

AU - Millnert, Victor

AU - Eker, Johan

AU - Bini, Enrico

PY - 2017/7/31

Y1 - 2017/7/31

N2 - There is a strong industrial drive to use cloud computing technologies and concepts for providing timing sensitive services in the networking domain since it would provide the means to share the physical resources among multiple users and thus increase the elasticity and reduce the costs. In this work, we develop a mathematical model for user-stateless virtual network functions forming a forwarding graph. The model captures uncertainties of the performance of these virtual resources as well as the time-overhead needed to instantiate them. The model is used to derive a service controller for horizontal scaling of the virtual resources as well as an admission controller that guarantees that packets exiting the forwarding graph meet their end-to-end deadline. The Automatic Service and Admission Controller (AutoSAC) developed in this work uses feedback and feedforward making it robust against uncertainties of the underlying infrastructure. Also, it has a fast reaction time to changes in the input.

AB - There is a strong industrial drive to use cloud computing technologies and concepts for providing timing sensitive services in the networking domain since it would provide the means to share the physical resources among multiple users and thus increase the elasticity and reduce the costs. In this work, we develop a mathematical model for user-stateless virtual network functions forming a forwarding graph. The model captures uncertainties of the performance of these virtual resources as well as the time-overhead needed to instantiate them. The model is used to derive a service controller for horizontal scaling of the virtual resources as well as an admission controller that guarantees that packets exiting the forwarding graph meet their end-to-end deadline. The Automatic Service and Admission Controller (AutoSAC) developed in this work uses feedback and feedforward making it robust against uncertainties of the underlying infrastructure. Also, it has a fast reaction time to changes in the input.

KW - uncertainty

KW - cloud computing

KW - hardware

KW - fabrics

KW - mathematical model

KW - admission control

KW - virtual machines

KW - network function virtualization

UR - https://www.scopus.com/pages/publications/85028360219

U2 - 10.1109/ICC.2017.7996596

DO - 10.1109/ICC.2017.7996596

M3 - Paper in conference proceeding

BT - 2017 IEEE International Conference on Communications (ICC)

T2 - IEEE International Conference on Communications 2017

Y2 - 21 May 2017 through 25 August 2017

ER -

Dynamic control of NFV forwarding graphs with end-to-end deadline constraints

Abstract

Conference

Subject classification (UKÄ)

Free keywords

Access to Document

Other files and links

Fingerprint

WASP: Autonomous Cloud

Feedback Computing in Cyber-Physical Systems

LCCC

Best Paper Award

Cite this

Dynamic control of NFV forwarding graphs with end-to-end deadline constraints

Abstract

Conference

Subject classification (UKÄ)

Free keywords

Access to Document

Other files and links

Fingerprint

Projects

WASP: Autonomous Cloud

Feedback Computing in Cyber-Physical Systems

LCCC

Prizes

Best Paper Award

Cite this