A Software-Defined Networking Approach for Disaster-Resilient WANs

The current technology of Internet provides an acceptable level of resilience in normal operation. However, the Internet may get catastrophic impacts when unexpected disasters such as earthquakes, tsunami, etc. happen. Specifically, the Internet infrastructure including Wide Area Networks (WANs) face many challenges to normal operation including power outage, link, device failures, rerouting packets, traffic engineering, etc. In this paper, we follow a systematic approach for realizing disaster-resilient WANs using Software-Defined Networking (SDN) technology. SDN enables the network control plane to be decoupled from the network forwarding hardware, and moves the control plane to a programmable component, i.e., the network controller. The network management and operation therefore increase flexibility. To confirm the feasibility of SDN-based resilient network towards fast disaster recovery, we have constructed two evaluations under the real large scale network topology. One is to investigate the latencies between controllers and switches in order to find the appropriate number and locations of controllers. Another one is to simulate a reactive switch-over from a faulty link to an alternative link, assuming a realistic scenario. The results show that the switch-over time depends on the latencies between networking devices and a controller. Additionally, even those latency values equal the worst-case latency, the fast rerouting of TCP traffic is achievable.

[1]  Nick McKeown,et al.  OpenFlow: enabling innovation in campus networks , 2008, CCRV.

[2]  Leon Gommans,et al.  Seamless live migration of virtual machines over the MAN/WAN , 2006, Future Gener. Comput. Syst..

[3]  Ioannis Lambadaris,et al.  Source routed forwarding with software defined control, considerations and implications , 2012, CoNEXT Student '12.

[4]  Matthew Roughan,et al.  The Internet Topology Zoo , 2011, IEEE Journal on Selected Areas in Communications.

[5]  Martín Casado,et al.  NOX: towards an operating system for networks , 2008, CCRV.

[6]  Jennifer Rexford,et al.  Live migration of an entire network (and its hosts) , 2012, HotNets-XI.

[7]  Amin Vahdat,et al.  PortLand: a scalable fault-tolerant layer 2 data center network fabric , 2009, SIGCOMM '09.

[8]  Nick McKeown,et al.  Reproducible network experiments using container-based emulation , 2012, CoNEXT '12.

[9]  Gordon T. Wilfong,et al.  An analysis of BGP convergence properties , 1999, SIGCOMM '99.

[10]  Youngseok Lee,et al.  Experience with Restoration of Asia Pacific Network Failures from Taiwan Earthquake , 2007, IEICE Trans. Commun..

[11]  Ying Zhang,et al.  On Resilience of Split-Architecture Networks , 2011, 2011 IEEE Global Telecommunications Conference - GLOBECOM 2011.

[12]  Martín Casado,et al.  Software-defined internet architecture: decoupling architecture from infrastructure , 2012, HotNets-XI.

[13]  Rob Sherwood,et al.  On Controller Performance in Software-Defined Networks , 2012, Hot-ICE.

[14]  David Hutchison,et al.  Resilience and survivability in communication networks: Strategies, principles, and survey of disciplines , 2010, Comput. Networks.

[15]  Ankit Singla,et al.  Jellyfish: Networking Data Centers Randomly , 2011, NSDI.

[16]  Martín Casado,et al.  Onix: A Distributed Control Platform for Large-scale Production Networks , 2010, OSDI.

[17]  Lei Shi,et al.  Dcell: a scalable and fault-tolerant network structure for data centers , 2008, SIGCOMM '08.

[18]  Rob Sherwood,et al.  The controller placement problem , 2012, HotSDN '12.