Big data analytics for the virtual network topology reconfiguration use case

Conference object English OPEN
Gifre Renom, Lluís ; Morales Alcaide, Fernando ; Velasco Esteban, Luis Domingo ; Ruiz Ramírez, Marc (2016)
  • Publisher: Institute of Electrical and Electronics Engineers (IEEE)
  • Related identifiers: doi: 10.1109/ICTON.2016.7550519
  • Subject: Heuristic algorithms | Data analytics | Optimal topologies | Topology | :Enginyeria de la telecomunicació::Telecomunicació òptica [Àrees temàtiques de la UPC] | Fiber optic networks | Optical communications | VNT reconfiguration | Matrix algebra | ABNO | Traffic monitoring | Virtual network topology | Comunicacions òptiques | Transparent optical networks | Optimization | Reconfigurable hardware | Experimental assessment | Virtual topologies | Telecommunication traffic
    arxiv: Computer Science::Networking and Internet Architecture

ABNO's OAM Handler is extended with big data analytics capabilities to anticipate traffic changes in volume and direction. Predicted traffic is used to trigger virtual network topology re-optimization. When the virtual topology needs to be reconfigured, predicted and current traffic matrices are used to find the optimal topology. A heuristic algorithm to adapt current virtual topology to meet both actual demands and expected traffic matrix is proposed. Experimental assessment is carried out on UPC's SYNERGY testbed. Peer Reviewed
Share - Bookmark