Virtual Infrastructure Design for Surviving Physical Link Failures

With the increasingly popular virtualization of both computing and networking resources in a distributed system (called a physical substrate), multiple virtual infrastructures (VIs) can share the physical resources of the underlying substrate, and accordingly even a single failure in the substrate can affect a large number of VIs and the services they offer. Thus, the problem of efficiently mapping a VI to a substrate while guaranteeing the VI's survivability in the event of failures in the substrate becomes important. In this paper, we study the survivable VI mapping problem to protect against link failures in the substrate. We first propose a solution based on traditional shared protection (survivable virtual infrastructure mapping algorithm, P-SVIMA), and then propose a novel VI node migration protection-based algorithm (MP-SVIMA) to minimize the computing and communication resource costs. The MP-SVIMA scheme takes advantage of the flexibility in where VI nodes are mapped in the substrate by migrating a VI node from the originally mapped physical location to a different location after a physical link fails in order to recover from link failures. We compare the efficiency of our solutions using simulations under various performance metrics.

[1]  Raouf Boutaba,et al.  Survivable Virtual Network Embedding , 2010, 2021 IFIP/IEEE International Symposium on Integrated Network Management (IM).

[2]  Wayne D. Grover,et al.  Optimal capacity placement for path restoration in STM or ATM mesh-survivable networks , 1998, TNET.

[3]  Ulas C. Kozat,et al.  Designing and embedding reliable virtual infrastructures , 2011, CCRV.

[4]  Albert G. Greenberg,et al.  The cost of a cloud: research problems in data center networks , 2008, CCRV.

[5]  Randy H. Katz,et al.  A view of cloud computing , 2010, CACM.

[6]  Chunming Qiao,et al.  Migration based protection for virtual infrastructure survivability for link failure , 2011, 2011 Optical Fiber Communication Conference and Exposition and the National Fiber Optic Engineers Conference.

[7]  Ting Wang,et al.  Robust Application Specific and Agile Private (ASAP) networks withstanding multi-layer failures , 2009, 2009 Conference on Optical Fiber Communication - incudes post deadline papers.

[8]  Chunming Qiao,et al.  Cost Efficient Design of Survivable Virtual Infrastructure to Recover from Facility Node Failures , 2011, 2011 IEEE International Conference on Communications (ICC).

[9]  Chunming Qiao,et al.  Novel algorithms for shared segment protection , 2003, IEEE J. Sel. Areas Commun..

[10]  Tao Guo,et al.  Shared Backup Network Provision for Virtual Network Embedding , 2011, 2011 IEEE International Conference on Communications (ICC).

[11]  Rajkumar Buyya,et al.  A taxonomy of scientific workflow systems for grid computing , 2005, SGMD.

[12]  Navendu Jain,et al.  Understanding network failures in data centers: measurement, analysis, and implications , 2011, SIGCOMM.

[13]  Yu Liu,et al.  Approximating optimal spare capacity allocation by successive survivable routing , 2005, TNET.

[14]  Chunming Qiao,et al.  A Cost Efficient Design of Virtual Infrastructures with Joint Node and Link Mapping , 2011, Journal of Network and Systems Management.

[15]  Chunming Qiao,et al.  Survivable Virtual Infrastructure Mapping in a Federated Computing and Networking System under Single Regional Failures , 2010, 2010 IEEE Global Telecommunications Conference GLOBECOM 2010.

[16]  Holger Karl,et al.  A virtual network mapping algorithm based on subgraph isomorphism detection , 2009, VISA '09.

[17]  Ting Wang,et al.  Survivable logical topology design for distributed computing in WDM networks , 2009, 2009 Conference on Optical Fiber Communication - incudes post deadline papers.

[18]  Raouf Boutaba,et al.  Virtual Network Embedding with Coordinated Node and Link Mapping , 2009, IEEE INFOCOM 2009.

[19]  Biswanath Mukherjee,et al.  Survivable WDM mesh networks , 2003 .

[20]  Rajkumar Buyya,et al.  Article in Press Future Generation Computer Systems ( ) – Future Generation Computer Systems Cloud Computing and Emerging It Platforms: Vision, Hype, and Reality for Delivering Computing as the 5th Utility , 2022 .

[21]  Yong Zhu,et al.  Algorithms for Assigning Substrate Network Resources to Virtual Network Components , 2006, Proceedings IEEE INFOCOM 2006. 25TH IEEE International Conference on Computer Communications.