Rethinking Virtual Network Embedding in Reconfigurable Networks

Abstract

The virtual network embedding (VNE) problem of mapping virtual network (VN) requests to a substrate network is a key component of network virtualization in datacenters. In a bid to improve datacenter network's performance and cost, there has been recent interest in network architectures, wherein the network topology can be changed at runtime to better handle current traffic patterns. Such reconfigurable networks seem naturally well-suited for efficient network virtualization- as networks can be tailored to accommodate the incoming VN requests. Motivated by the above, in this paper, we address the problem of virtual network embedding in reconfigurable networks; to the best of our knowledge, this has not been addressed before. In particular, we address the VNE problem in reconfigurable networks under two different models of VN link demands: fixed-bandwidth and stochastic-bandwidth demands. The former is the traditional model, while we propose the the latter to improve network utilization and leverage the runtime reconfiguration capability of reconfigurable networks. For the stochastic demand model, we employ a novel concept of embedding with runtime-binding, wherein the embedding of a VN link is configured at runtime (via network reconfiguration) depending on the prevailing network state and traffic. We evaluate the efficiency of our proposed models and techniques via simulation using real VN requests and traffic statistics from large datacenters, and show that our proposed models and techniques offer significant performance advantages (up to 30-40%) over traditional models.