6th International ICST Conference on Broadband Communications, Networks, and Systems

Research Article

A preemptive scheduling scheme for flexible QoS provisioning in OBS networks

Download588 downloads
  • @INPROCEEDINGS{10.4108/ICST.BROADNETS2009.7205,
        author={Kostas Ramantas and Tito Ra\^{u}l Vargas and Juan Carlos Guerri and Kyriakos Vlachos},
        title={A preemptive scheduling scheme for flexible QoS provisioning in OBS networks},
        proceedings={6th International ICST Conference on Broadband Communications, Networks, and Systems},
        publisher={IEEE},
        proceedings_a={BROADNETS},
        year={2009},
        month={11},
        keywords={Optical Burst Switching preemtions Class of Service Burst Scheduling},
        doi={10.4108/ICST.BROADNETS2009.7205}
    }
    
  • Kostas Ramantas
    Tito Raúl Vargas
    Juan Carlos Guerri
    Kyriakos Vlachos
    Year: 2009
    A preemptive scheduling scheme for flexible QoS provisioning in OBS networks
    BROADNETS
    IEEE
    DOI: 10.4108/ICST.BROADNETS2009.7205
Kostas Ramantas1, Tito Raúl Vargas2, Juan Carlos Guerri2, Kyriakos Vlachos1,*
  • 1: Computer Engineering and Informatics Department & Research Academic Computer Technology Institute, University of Patras, Rio, Greece
  • 2: ITEAM, Instituto de Telecomunicaciones y Aplicaciones Multimedia Universidad Politécnica de Valencia, Valencia, Spain
*Contact email: kvlachos@ceid.upatras.gr

Abstract

In Optical Burst Switching (OBS) networks one of the most challenging problems is to provide service differentiation. The lack of buffering in the intermediate nodes, makes QoS provisioning in OBS networks a difficult problem to address. In this work, we propose a scheduling algorithm that supports QoS based on preemptions, which are controlled by a novel preemption policy. Our claims are validated by analytical modelling and experimental analysis through simulations using data belonging to two different classes of service - best effort and video streaming data. Performance evaluation is based on throughput measurements for best effort class, and perceived quality metrics like PSNR and MOS scores for the video streaming class.