A Virtualized Network Architecture for Improving QoS

Recently, researches have shown that today's best-effort Internet with "one fits all" principle comes to an impasse. Addressed to the different QoS requirements of today's network services, we propose a new network architecture based on network virtualization technology for improving Internet QoS. It divides a "thick" network into multiple "thin" virtual networks deploying on the same substrate, each is customized with a special designing goal and runs a customized protocol. Then the traffic with different QoS requirements is classified at the ingress router, and distributed to different virtual networks, which are the most suitable for carrying the special traffic. Also, we can deploy a service on multiple virtual networks, and making them working collaboratively to achieve a better QoS. To verify this idea, a prototype is implemented in LAN-scale network. By some simply designed experiments for comparison, we observe that, by use of our network architecture, service provider with specific QoS requirement can take its choice to choose appropriate virtual networks to achieve better QoS performance.

[1]  Jennifer Rexford,et al.  Accountability in hosted virtual networks , 2009, VISA '09.

[2]  Jennifer Rexford,et al.  Cabernet: connectivity architecture for better network services , 2008, CoNEXT '08.

[3]  David L. Black,et al.  An Architecture for Differentiated Service , 1998 .

[4]  EDDIE KOHLER,et al.  The click modular router , 2000, TOCS.

[5]  Nick Feamster,et al.  In VINI veritas: realistic and controlled network experimentation , 2006, SIGCOMM.

[6]  Scott Shenker,et al.  Overcoming the Internet impasse through virtualization , 2005, Computer.

[7]  Yi Wang,et al.  Virtual routers on the move: live router migration as a network-management primitive , 2008, SIGCOMM '08.

[8]  Minlan Yu,et al.  Rethinking virtual network embedding: substrate support for path splitting and migration , 2008, CCRV.

[9]  Jennifer Rexford,et al.  Building bug-tolerant routers with virtualization , 2008, PRESTO '08.

[10]  Pascal Frossard,et al.  Media Flow Rate Allocation in Multipath Networks , 2007, IEEE Transactions on Multimedia.

[11]  Nick Feamster,et al.  In VINI veritas: realistic and controlled network experimentation , 2006, SIGCOMM 2006.

[12]  Pascal Frossard,et al.  Media Streaming With Network Diversity , 2008, Proceedings of the IEEE.

[13]  Satish K. Tripathi,et al.  Intradomain QoS routing in IP networks: a feasibility and cost/benefit analysis , 1999, IEEE Netw..

[14]  Jing Fu,et al.  Efficient IP-address lookup with a shared forwarding table for multiple virtual routers , 2008, CoNEXT '08.

[15]  Satoshi Ohzahata,et al.  A Study on Traffic Characteristics Evaluation for a Pure P2P Application , 2008, 16th Euromicro Conference on Parallel, Distributed and Network-Based Processing (PDP 2008).

[16]  Ying Li,et al.  DaVinci: dynamically adaptive virtual networks for a customized internet , 2008, CoNEXT '08.

[17]  Eric Keller,et al.  Virtualizing the data plane through source code merging , 2008, PRESTO '08.

[18]  Lixin Gao,et al.  How to lease the internet in your spare time , 2007, CCRV.

[19]  Deborah Estrin,et al.  GENI Design Principles , 2006, Computer.

[20]  Jennifer Rexford,et al.  Toward internet-wide multipath routing , 2008, IEEE Network.