Neutrality of Internet of future is a main concern for both scientific and technical communities and for Internet users. New architectures are characterized by an increase of intelligence inside the network (more computing power and more storage capacity). While Internet is supposed to serve everybody, everywhere and always with the same Quality of Service (QoS), the Software Defined Networking (SDN) paradigm gives ISPs flexibility and agility to segregate between flows and to deploy a different routing strategy and traffic engineering policy per category of flows. Flows can be classified by the identity of their sources, destinations, or by protocols and applications, which they carry. In this paper, we study neutrality of SDN from both theoretical and practical aspects. Our approach is to design a cooperative user-to-user neutrality measurement framework, to consider different ISP's routing and traffic engineering policies, and to infer network neutrality as perceived by users. Intensive NS-3 simulations are used to experiment with different SDN control plane strategies and to detect differentiation from end-users perspective.
[1]
Nick McKeown,et al.
OpenFlow: enabling innovation in campus networks
,
2008,
CCRV.
[2]
Katerina J. Argyraki,et al.
Network neutrality inference
,
2014,
SIGCOMM.
[3]
Richard van den Berg,et al.
Over-Zealous Security Administrators Are Breaking the Internet
,
2002,
LISA.
[4]
Nick Feamster,et al.
Detecting network neutrality violations with causal inference
,
2009,
CoNEXT '09.
[5]
Ming Zhang,et al.
Detecting traffic differentiation in backbone ISPs with NetPolice
,
2009,
IMC '09.
[6]
Nick Feamster,et al.
The road to SDN: an intellectual history of programmable networks
,
2014,
CCRV.
[7]
Guillaume Urvoy-Keller,et al.
Towards a General Solution for Detecting Traffic Differentiation at the Internet Access
,
2015,
2015 27th International Teletraffic Congress.