Abstract

[EN] Increasing power consumption and CO2 emissions generated by large data networks have become a major concern over the last decade. For this problem, the emerging paradigm of Software-Defined Networks (SDN) can be seen as an attractive solution. In these networks an energy-aware routing model could be easily implemented leveraging the control and data plane separation. This paper investigates the impact of energy-aware routing on SDN performance. To that end, we propose a novel energy- aware mechanism that reduces the number of active links in SDN with multiple controllers, considering in-band control traffic, i.e. links are shared between data and control plane traffic. The proposed strategy exploits knowledge of the network topology combined with traffic engineering techniques to reduce the overall power consumption. Therefore, two heuristic algorithms are designed: a static network configuration and a dynamic energy-aware routing. Significant values of switched-off links are reached in the simulations using real topologies and demands data. Moreover, obtained results confirm that crucial network parameters such as control traffic delay, data path latency, link utilization and TCAM occupation are affected by the performance-agnostic energy-aware model. This work has been supported by the Ministerio de Econom´ıa y Competitividad of the Spanish Government under project TEC2016-76795-C6-1-R and AEI/FEDER, UE and through a predoctoral FPI scholarship. Fernández-Fernández, A.; Cervelló-Pastor, C.; Ochoa-Aday, L. (2018). Evaluating the Impact of Energy-Aware Routing on Software-Defined Networking Performance. En XIII Jornadas de Ingeniería telemática (JITEL 2017). Libro de actas. Editorial Universitat Politècnica de València. 241-248. https://doi.org/10.4995/JITEL2017.2017.6489 OCS 241 248

Abstract

Recently, saving energy for backbone networks has raised an increasing concern for network operators. Since traffic load has a small influence on power consumption, the most common approach is to put unused links into sleep mode to save energy. To guarantee QoS, all traffic demands should be routed without violating capacity constraints. In this work, we consider to save energy with Open Shortest Path First (OSPF) protocol. From the perspective of traffic engineering, we argue that stability in routing configuration also plays an important role in QoS. In details, frequent changes in network configuration (link weights, slept and activated links) to adapt with traffic fluctuation in daily time cause network oscillation. We propose a novel optimization method of link weight so as to limit the changes in network configurations in multi-period traffic matrices. We formally define the problem and model it as Mixed Integer Linear Program (MILP). We then propose efficient heuristic algorithm that is suitable for large networks. Simulation results with real traffic traces on three different networks show that our approach achieves high energy savings and less pain for QoS (in term of less changes in network configuration).