F2R501C: Performance evaluation


Coordinator:  Patrick MAILLE   

Presentation

This course introduces the techniques that can be used to predict the performance of a computer system in general, and of networks in particular.
These techniques enable the evaluation of response time, transfer rates, transmission delays, using models of the considered systems.
This may be crucial, for example, for the dimensioning of a new network, or to compare two protocols, to study the effects of a future change in traffic characteristics, ...

In this course, we introduce some different means of studying the performance of a system, mainly focusing on the use of simulators and of analytic techniques. The pros and cons of each approach are evoked, and among them their applicability to different communication systems.

Objectives

- description of the different performance criteria for a network
- description of the main techniques for performance evaluation
- the objective is that the student be able to determine and apply the most appropriate technique to a given problem

Duration: 20h


Organization

Scheduled activities

  • C0 (2h30)   Rappels de probabilités
  • C1 (2h30)   Introduction à la simulation à événements discrets (1/2)
  • C2 (2h30)   Introduction à la simulation à événements discrets (2/2)
  • C3 (2h30)   Rappels de dimensionnement : lois d'Erlang, d'Engset (pour étudiants mastère)
  • TP0 (2h30)   TP dimensionnement sur applet Java (auto-apprentissage)
  • C4 (2h30)   Présentation du logiciel de simulation NS
  • TP1 (2h30)   TP sur NS
  • C5 (2h30)   Métrologie
  • C6 (2h30)   Introduction au Network Calculus
  • CC1 (2h30)   Contrôle de connaissances

Team


  C0
  2h30
  C1
  2h30
  C2
  2h30
  C3
  2h30
  TP0
  2h30
  C4
  2h30
  TP1
  2h30
  C5
  2h30
  C6
  2h30
  CC1
  2h30
 Patrick MAILLE        x x   x   x  
 David ROS SANCHEZ            x x      
 Gerardo RUBINO  x x x              
 Géraldine TEXIER                x    


Recommended reading

- G. Doyon, Systèmes et réseaux de télécommunications en régime stochastique,
Ed. Masson et CNET-ENST, 1989
- R. Jain, The art of computer systems performance analysis, Ed. Wiley 1991
- D. Bertsekas et R. Gallager, Data Networks, Prentice-Hall, 1992


  Year 2006/2007
Last update: 05-FEB-07
Last validation:

IMT Atlantique
Campus de Brest
Technopôle Brest-Iroise
CS 83818
29238 Brest Cedex 3
France

Tél  +33 (0)2 29 00 11 11
Fax +33 (0)2 29 00 10 00