1st International ICST Workshop on Utility computing enhanced with high bit rate networks: Opportunity and requirements

Research Article

On the traffic modeling of burst aggregation algorithms using video and data traces

Download471 downloads
  • @INPROCEEDINGS{10.4108/gridnets.2007.2263,
        author={Xenia Mountrouidou and Harry G. Perros},
        title={On the traffic modeling of burst aggregation algorithms using video and data traces},
        proceedings={1st International ICST Workshop on Utility computing enhanced with high bit rate networks: Opportunity and requirements},
        publisher={ICST},
        proceedings_a={UTILITYCOMPUTING},
        year={2007},
        month={10},
        keywords={burst aggregation algorithms Internet traces statistical convolution Interrupted Poisson Process},
        doi={10.4108/gridnets.2007.2263}
    }
    
  • Xenia Mountrouidou
    Harry G. Perros
    Year: 2007
    On the traffic modeling of burst aggregation algorithms using video and data traces
    UTILITYCOMPUTING
    ICST
    DOI: 10.4108/gridnets.2007.2263
Xenia Mountrouidou1,*, Harry G. Perros2,*
  • 1: IBM Software Group, Building 503, 4205 S. Miami Blvd. Durham, NC 27703
  • 2: Computer Science Department, North Carolina State University, Raleigh, NC 27695, USA
*Contact email: xenia.mountrouidou@gmail.com, hp@csc.ncsu.edu

Abstract

We obtain analytically the delay per packet in a burst for the three burst aggregation algorithms: Time based, Burst Length based and mixed Time and Burst Length based, assuming real video and aggregated Internet traces, as well as the IPP arrivals. For video traces we also obtain the probability that a playback machine will pause due to lack of frames when streaming video. The accuracy of the analytic results was established by comparing them to simulation data.