3rd International ICST Conference on Performance Evaluation Methodologies and Tools

Research Article

Estimating the Worst-case Delay in FIFO Tandems Using Network Calculus

Download568 downloads
  • @INPROCEEDINGS{10.4108/ICST.VALUETOOLS2008.4388,
        author={Luca Bisti and Luciano Lenzini and Enzo Mingozzi and Giovanni Stea},
        title={Estimating the Worst-case Delay in FIFO Tandems Using Network Calculus},
        proceedings={3rd International ICST Conference on Performance Evaluation Methodologies and Tools},
        publisher={ICST},
        proceedings_a={VALUETOOLS},
        year={2010},
        month={5},
        keywords={Network Calculus FIFO-multiplexing Delay Bound.},
        doi={10.4108/ICST.VALUETOOLS2008.4388}
    }
    
  • Luca Bisti
    Luciano Lenzini
    Enzo Mingozzi
    Giovanni Stea
    Year: 2010
    Estimating the Worst-case Delay in FIFO Tandems Using Network Calculus
    VALUETOOLS
    ICST
    DOI: 10.4108/ICST.VALUETOOLS2008.4388
Luca Bisti1,*, Luciano Lenzini1,*, Enzo Mingozzi1,*, Giovanni Stea1,*
  • 1: Dipartimento di Ingegneria dell’Informazione, University of Pisa, Italy, Via Diotisalvi, 2, 56122 Pisa, Italy - Ph. +39 050 2217599
*Contact email: l.bisti@iet.unipi.it, l.lenzini@iet.unipi.it, e.mingozzi@iet.unipi.it, g.stea@iet.unipi.it

Abstract

This paper addresses the problem of estimating the worst-case end-to-end delay for a flow in a tandem of FIFO multiplexing nodes, following up our previous work [12]. We show that, contrary to the expectations, the state-of-the-art method for computing delay bounds, i.e. upper bounds on the worst-case delay, called the Least Upper Delay Bound (LUDB) methodology, may actually be larger than the worst-case delay even in simple cases. Thus, we first devise a method to compute improved delay bounds. Then, in order to assess how close the derived bounds are to the actual, still unknown, worst-case delays, we devise a method to compute lower bounds on the worst-case delay. Our analysis shows that the gap between the upper and lower bounds is quite small in many practical cases, which implicitly validates the upper bounds themselves.