Restoration strategies and spare capacity requirements in self-healing ATM networks
IEEE/ACM Transactions on Networking (TON)
Optimal Physical Diversity Algorithms and Survivable Networks
ISCC '97 Proceedings of the 2nd IEEE Symposium on Computers and Communications (ISCC '97)
MapReduce: simplified data processing on large clusters
Communications of the ACM - 50th anniversary issue: 1958 - 2008
Rethinking virtual network embedding: substrate support for path splitting and migration
ACM SIGCOMM Computer Communication Review
A scalable, commodity data center network architecture
Proceedings of the ACM SIGCOMM 2008 conference on Data communication
A virtual network mapping algorithm based on subgraph isomorphism detection
Proceedings of the 1st ACM workshop on Virtualized infrastructure systems and architectures
Network virtualization: state of the art and research challenges
IEEE Communications Magazine
Designing and embedding reliable virtual infrastructures
Proceedings of the second ACM SIGCOMM workshop on Virtualized infrastructure systems and architectures
Application-specific resource provisioning for wide-area distributed computing
IEEE Network: The Magazine of Global Internetworking
Reliability Support in Virtual Infrastructures
CLOUDCOM '10 Proceedings of the 2010 IEEE Second International Conference on Cloud Computing Technology and Science
Survivable virtual network embedding
NETWORKING'10 Proceedings of the 9th IFIP TC 6 international conference on Networking
WDM optical communication networks: progress and challenges
IEEE Journal on Selected Areas in Communications
Hi-index | 0.00 |
Network virtualization technology allows multiple virtual infrastructures (VIs) or virtual networks customized to suit user requirements on a shared substrate network without the need for much additional infrastructure. However, in such a scenario, even a single failure in the substrate can cause large disruptions as it will affect all the VIs mapped onto it. Thus, the problem of guaranteeing survivability and reliability of VI is important, and even more complex than in single layer networks. In this paper, we study the reliable VI mapping problem that enables efficient resource sharing by using the cross sharing scheme that reuses the primary bandwidth for backup VI links. In addition, we also study the sharing of backup resources across multiple different VI requests. We first formulate the reliable VI mapping problem as a mixed integer programming (MIP) problem to minimize the VI mapping cost. We then present our reliable VI mapping (RVIM) algorithm for efficient bandwidth sharing using the cross and backup sharing schemes. Finally, we present the VI combination (ComVI) algorithm to generate shared backup VI nodes and links for multiple VI requests in a cost efficient manner. Through simulation we show that our RVIM algorithm can reduce the mapping costs when compared to other VI mapping algorithms, and backup resource sharing using ComVI can reduce the total mapping cost efficiently.