Ricerc@Sapienza

Software-Defined Networking (SDN) is a new networking paradigm that is attracting the attention of the research community due to the flexibility provided by the separation between data and control planes. In particular, the SDN scenario introduces new aspects to be considered when formulating the energy-aware routing problem, such as the reconfiguration cost of flow tables. In this paper we introduce and investigate the problem of minimizing the power consumption of an SDN network while also reducing the number of rules that have to be modified in the flow tables of SDN nodes. An optimization problem formulation and a GA (Genetic Algorithm) based heuristic are presented to tackle this two-fold problem. The performance analysis, carried out over different realistic network topologies, highlights that GA is able to increase the power saving opportunities up to the 20% more than other energy-aware routing solutions proposed in the literature, while reducing the number of rules that have to be modified up to 100 times.