Serveur d'exploration sur la recherche en informatique en Lorraine

Attention, ce site est en cours de développement !
Attention, site généré par des moyens informatiques à partir de corpus bruts.
Les informations ne sont donc pas validées.

Queueing Analysis of Message Exchange in Field Bus Fip

Identifieur interne : 00E097 ( Main/Merge ); précédent : 00E096; suivant : 00E098

Queueing Analysis of Message Exchange in Field Bus Fip

Auteurs : F. Simonot ; Y. Q. Song ; Jean-Pierre Thomesse [France]

Source :

RBID : CRIN:simonot91a

English descriptors

Abstract

This paper proposes an approximate method for the performance evaluation of the message exchange service supported by FIP (Factory Instrumentation Protocol), a french national standard for field bus. We represent the message exchange service of FIP as a two stage parallel-series queueing system. The first stage is composed of N homogeneous queues in parallel representing N stations connected to the bus. The output flow issued from each queue of this stage are superposed and form the input flow entering into the second stage which is modeled by a single queue to represent the bus arbitrator. We evaluate the performance of the message exchange service in low load case. Our contribution resides in the study of the input flow entering into the second stage. Assuming a constant messag{e}'s length and a deterministic service time distribution (with server's vacation predetermined by FIP configuration) for the queue of the second stage, we derive a two folds approximation\, : at first, by using robustness theorem, we proved that the output flow issued from one queue of the first stage is weakly dependent if the average number of messages in the queue is small. This allows to consider the output flow issued from any queue of the first stage as a sequence of i.i.d. (independent and identically distributed) random variables. Then, the superposition of N output flows of the first stage is approached by a sequence of i.i.d random variables following a Poisson distribution. The ``quantitative robustness'' theorem provides only an upper bound of errors. So, the study is completed by a computer simulation permitting to appreciate the real approximation realized. Following this approach, the distribution of the number of messages in the second stage can then be derived easily by using the same methods as for the TDMA.

Links toward previous steps (curation, corpus...)


Links to Exploration step

CRIN:simonot91a

Le document en format XML

<record>
<TEI>
<teiHeader>
<fileDesc>
<titleStmt>
<title xml:lang="en" wicri:score="71">Queueing Analysis of Message Exchange in Field Bus Fip</title>
</titleStmt>
<publicationStmt>
<idno type="RBID">CRIN:simonot91a</idno>
<date when="1991" year="1991">1991</date>
<idno type="wicri:Area/Crin/Corpus">000D01</idno>
<idno type="wicri:Area/Crin/Curation">000D01</idno>
<idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Curation">000D01</idno>
<idno type="wicri:Area/Crin/Checkpoint">003896</idno>
<idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Checkpoint">003896</idno>
<idno type="wicri:Area/Main/Merge">00E097</idno>
</publicationStmt>
<sourceDesc>
<biblStruct>
<analytic>
<title xml:lang="en">Queueing Analysis of Message Exchange in Field Bus Fip</title>
<author>
<name sortKey="Simonot, F" sort="Simonot, F" uniqKey="Simonot F" first="F" last="Simonot">F. Simonot</name>
</author>
<author>
<name sortKey="Song, Y Q" sort="Song, Y Q" uniqKey="Song Y" first="Y. Q." last="Song">Y. Q. Song</name>
</author>
<author>
<name sortKey="Thomesse, J P" sort="Thomesse, J P" uniqKey="Thomesse J" first="J.-P." last="Thomesse">Jean-Pierre Thomesse</name>
<affiliation>
<country>France</country>
<placeName>
<settlement type="city">Nancy</settlement>
<region type="region" nuts="2">Grand Est</region>
<region type="region" nuts="2">Lorraine (région)</region>
</placeName>
<orgName type="laboratoire" n="5">Laboratoire lorrain de recherche en informatique et ses applications</orgName>
<orgName type="university">Université de Lorraine</orgName>
<orgName type="institution">Centre national de la recherche scientifique</orgName>
<orgName type="institution">Institut national de recherche en informatique et en automatique</orgName>
</affiliation>
</author>
</analytic>
</biblStruct>
</sourceDesc>
</fileDesc>
<profileDesc>
<textClass>
<keywords scheme="KwdEn" xml:lang="en">
<term>FIP</term>
<term>field bus</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front>
<div type="abstract" xml:lang="en" wicri:score="2171">This paper proposes an approximate method for the performance evaluation of the message exchange service supported by FIP (Factory Instrumentation Protocol), a french national standard for field bus. We represent the message exchange service of FIP as a two stage parallel-series queueing system. The first stage is composed of N homogeneous queues in parallel representing N stations connected to the bus. The output flow issued from each queue of this stage are superposed and form the input flow entering into the second stage which is modeled by a single queue to represent the bus arbitrator. We evaluate the performance of the message exchange service in low load case. Our contribution resides in the study of the input flow entering into the second stage. Assuming a constant messag{e}'s length and a deterministic service time distribution (with server's vacation predetermined by FIP configuration) for the queue of the second stage, we derive a two folds approximation\, : at first, by using robustness theorem, we proved that the output flow issued from one queue of the first stage is weakly dependent if the average number of messages in the queue is small. This allows to consider the output flow issued from any queue of the first stage as a sequence of i.i.d. (independent and identically distributed) random variables. Then, the superposition of N output flows of the first stage is approached by a sequence of i.i.d random variables following a Poisson distribution. The ``quantitative robustness'' theorem provides only an upper bound of errors. So, the study is completed by a computer simulation permitting to appreciate the real approximation realized. Following this approach, the distribution of the number of messages in the second stage can then be derived easily by using the same methods as for the TDMA.</div>
</front>
</TEI>
</record>

Pour manipuler ce document sous Unix (Dilib)

EXPLOR_STEP=$WICRI_ROOT/Wicri/Lorraine/explor/InforLorV4/Data/Main/Merge
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 00E097 | SxmlIndent | more

Ou

HfdSelect -h $EXPLOR_AREA/Data/Main/Merge/biblio.hfd -nk 00E097 | SxmlIndent | more

Pour mettre un lien sur cette page dans le réseau Wicri

{{Explor lien
   |wiki=    Wicri/Lorraine
   |area=    InforLorV4
   |flux=    Main
   |étape=   Merge
   |type=    RBID
   |clé=     CRIN:simonot91a
   |texte=   Queueing Analysis of Message Exchange in Field Bus Fip
}}

Wicri

This area was generated with Dilib version V0.6.33.
Data generation: Mon Jun 10 21:56:28 2019. Site generation: Fri Feb 25 15:29:27 2022