ABSTRACT
Network virtualization has been considered a promising approach for promoting heterogeneous services and mechanisms toward the next-generation network architectures, which can greatly improve the global utilization efficiency of network and computing resources and hence the capacity of service delivery. The proper allocation of network resources from a shared physical substrate to a set of virtual networks (VNs) is one of the key aspects for the application of network virtualization techniques. While a variety of state-of-the-art algorithms have been proposed and attempted to address this issue from different facets, the challenge still remains in the context of large-scale networks as the existing solutions mainly perform in a centralized manner, which requires maintaining overall and up-to-date information of the underlying substrate network. This implies restricted scalability and computational efficiency when the network scale becomes large. This chapter exploits the VN mapping problem and proposes a novel hierarchical algorithm in conjunction with a substrate network decomposition approach. By appropriately transforming the underlying substrate network into a collection of subnetworks, the hierarchical VN mapping algorithm can be carried out through a global VN mapping algorithm (GVNMA) and a local VN mapping algorithm (LVNMA) operated in the network's central server and within individual subnetworks, respectively, with cooperation and coordination between them when necessary. The proposed algorithm is assessed against the centralized approaches through a set of numerical simulation experiments for a range of network scenarios. The results show that the proposed hierarchical approach can be about 5 to 20 times faster for VN mapping tasks than conventional centralized approaches with acceptable communication overhead between GVNCA and LVNCA for all experimented networks while performing almost as well as the centralized solutions.
In addition, VN invulnerability has long been ignored, and little research effort has been made. In this chapter, we present a novel VN restoration approach, MFP-VNMH, which could enhance the VN mapping and service restoration subject to the physical-link failure in the physical substrate while avoiding the remapping of the overall VNs. The performance of the proposed MFP-VNMH is assessed through extensive numerical experiments for a range of network scenarios in comparison with the overall VN remapping approach and the end-to-end link remapping approach. The result is encouraging and demonstrates its effectiveness and efficiency for VN mapping update and service restoration upon physical substrate failures.
