Resource competition in virtual network embedding

Abstract

We consider a virtual network (VN) embedding problem on a large-scale substrate physical network. We permit varying capacities and cost rates, and reservation of resources (physical links and nodes) for more profitable later VN requests. Our aim is to maximize the long-run average revenue by controlling the allocation of physical components to arriving VN requests. We propose an index policy that selects, according to state-dependent indices, a set of available physical components for each arrival. The indices are calculated in closed form requiring only intrinsic off-line information about physical components and physical resource requirements. Under reasonable assumptions related to rapidly increasing demands for VNs and resource competition, we show that this proposed policy is asymptotically optimal when the lifespans of embedded virtual components are exponentially distributed. Extensive numerical results demonstrate that the long-run average revenue earned by the proposed index policy rapidly approaches optimality: performance deviations between the index policy and the optimal solution are less than 5% in most of our simulations even for relatively small systems. Our numerical results also indicate that the long-run performance of this policy is relatively insensitive to the form of the lifespan distributions.