SLA Adaptation for Service Overlay Networks

Virtual Network Operators lease bandwidth from different data carriers to offer well managed Virtual Private Networks. By using proprietary algorithms and leased resource diversity they can offer Quality of Service, at competitive prices, which is difficult to attain from traditional data network operators. Since maximizing the profit is a key objective for virtual network operators, in this paper we describe a novel resource management approach, based on an economic model that allows continuous optimizing of the network profit, while keeping network blocking constraints. The approach integrates leased link capacity adaptations with connection admission control and routing policies by using concepts derived from Markov Decision Process theory. Our numerical analysis validates the approach and shows that the profit can be maximized under varying network conditions.