10th EAI International Conference on Performance Evaluation Methodologies and Tools

Research Article

Performability Evaluation of Software Defined Networking Infrastructures

  • @INPROCEEDINGS{10.4108/eai.25-10-2016.2266605,
        author={Mario Di Mauro and Maurizio Longo and Fabio Postiglione},
        title={Performability Evaluation of Software Defined Networking Infrastructures},
        proceedings={10th EAI International Conference on Performance Evaluation Methodologies and Tools},
        keywords={software defined networking performability evaluation multivariate universal generating function},
  • Mario Di Mauro
    Maurizio Longo
    Fabio Postiglione
    Year: 2017
    Performability Evaluation of Software Defined Networking Infrastructures
    DOI: 10.4108/eai.25-10-2016.2266605
Mario Di Mauro1,*, Maurizio Longo1, Fabio Postiglione1
  • 1: University of Salerno
*Contact email: mdimauro@unisa.it


Software Defined Networking (SDN) has been introduced as a novel paradigm in traffic engineering, aiming to simplify network management and control through programmability concepts. This emerging strategy addresses the recent network challenges by decoupling the packet forwarding features, namely, the data plane, from the decision system, namely, the control plane, through a dedicated protocol named OpenFlow. The controller element of an SDN infrastructure represents the core entity in charge of managing the whole service logic and, being this module failure-prone, its performance and its availability are crucial issues for an accurate plan of an SDN-based network. The approaches considering both performance and availability assessment in data and telecommunication networks are frequently referred to as the performability evaluations. A performability evaluation is presented in this work to the aim of selecting the most convenient redundancy scheme of the SDN controller, where the controller has been modeled by a finite number of virtual operator instances serving different network zones. By assuming that the SDN controlling unit is described by a Continuous-Time Markov Chain with a vector state, the steady-state availability of the SDN controller in parallel redundancy configuration is computed by an approach based on the Universal Generating Function tailored for the vector case, and a redundancy optimization problem for the architecture of the SDN controller is solved.