Transfert de Charge dans un Réseau de Processeurs Totalement Connectés

Béguin, Maryse. "Transfert de Charge dans un Réseau de Processeurs Totalement Connectés." RAIRO - Operations Research 34.1 (2010): 99-129. <http://eudml.org/doc/197826>.

@article{Béguin2010,
abstract = { In this paper, a model of the load transfer on a fully connected net is presented. Each processor can accept at most K tasks. A load difference of two tasks between two processors is a prohibited situation and when it may appear, an immediat and instantaneous transfer is decided. The performances of the system are evaluated by the following indices: the reject probability, the throughput, the mean response time, the stationary probability distribution for a processor to host i tasks. The aim of this study is to evaluate the load transfer inpact thanks to the comparison between the values of the indices without transfer and with transfer. In particular the asymptotic behaviour for massively parallel systems is studied and interpreted. Calculated with an ideal situation, these comparisons yield upper bounds on the benefits that can be expected from a transferring policy. Beyonds, the opportunity of the transfer according to the values of the parameters can be studied. The mean number of transfers executed within a time unit and the mean number of transfers of a given task are calculated. At last values of the indices when the number of accepted tasks K grows to infinity is studied. },
author = {Béguin, Maryse},
journal = {RAIRO - Operations Research},
keywords = { Performance evaluation; load transfer; massively parallel system; Markov process; death and birth process.; performance evaluation; massively parallel system; death process; birth process},
language = {fre},
month = {3},
number = {1},
pages = {99-129},
publisher = {EDP Sciences},
title = {Transfert de Charge dans un Réseau de Processeurs Totalement Connectés},
url = {http://eudml.org/doc/197826},
volume = {34},
year = {2010},
}

TY - JOUR
AU - Béguin, Maryse
TI - Transfert de Charge dans un Réseau de Processeurs Totalement Connectés
JO - RAIRO - Operations Research
DA - 2010/3//
PB - EDP Sciences
VL - 34
IS - 1
SP - 99
EP - 129
AB - In this paper, a model of the load transfer on a fully connected net is presented. Each processor can accept at most K tasks. A load difference of two tasks between two processors is a prohibited situation and when it may appear, an immediat and instantaneous transfer is decided. The performances of the system are evaluated by the following indices: the reject probability, the throughput, the mean response time, the stationary probability distribution for a processor to host i tasks. The aim of this study is to evaluate the load transfer inpact thanks to the comparison between the values of the indices without transfer and with transfer. In particular the asymptotic behaviour for massively parallel systems is studied and interpreted. Calculated with an ideal situation, these comparisons yield upper bounds on the benefits that can be expected from a transferring policy. Beyonds, the opportunity of the transfer according to the values of the parameters can be studied. The mean number of transfers executed within a time unit and the mean number of transfers of a given task are calculated. At last values of the indices when the number of accepted tasks K grows to infinity is studied.
LA - fre
KW - Performance evaluation; load transfer; massively parallel system; Markov process; death and birth process.; performance evaluation; massively parallel system; death process; birth process
UR - http://eudml.org/doc/197826
ER -