• JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
 
  Bookmark and Share
 
 
Master's Dissertation
DOI
https://doi.org/10.11606/D.55.2018.tde-28062018-113035
Document
Author
Full name
Carlos Aparecido dos Santos
Institute/School/College
Knowledge Area
Date of Defense
Published
São Carlos, 1994
Supervisor
Committee
Salles, Maria Creusa Bretas (President)
Barros, Maria Suelena Santiago
Santana, Regina Helena Carlucci
Title in Portuguese
ANALISE DE COMPRIMENTO DE SIMULACAO ATRAVES DO PROCEDIMENTO SEQUENCIAL DE LAW E CARSON
Keywords in Portuguese
Não disponível
Abstract in Portuguese
Usualmente, em simulação de sistemas, fixa-se a priori o tamanho da rodada n, e a partir dos resultados calcula-se a média final da variável aleatória de interesse e seu intervalo de confiança. Law e Carson propõem um procedimento sequencial para determinação do tamanho da rodada, a partir da meia amplitude do intervalo de confiança fixado e da autocorrelação de lag 1 para as médias dos batches. Com o procedimento sequencial de Law e Carson determinamos o comprimento médio das rodadas de simulações da fila M/M/1, com p =0,8 e 0,5; e y, a meia amplitude relativa do intervalo de confiança com valores ∞ ; 0,15 e 0,075; a partir de 100 a 180 rodadas distintas. O desempenho da simulação foi então analisado através da porcentagem de cobertura do valor real do tempo médio de espera na fila, para três modelos. Os resultados obtidos levou-nos a uma cobertura muito próxima de 90%, que é a confiança do intervalo de confiança construido, com correlação entre os batches muito pequena indicando uma quase independência entre eles.
Title in English
Not available
Keywords in English
Not available
Abstract in English
In system simulation, usually we have a run of lenght n fixed, and then we calculate the final mean of the random variable analysed, and its confidence interval. Law and Carson's sequential procedure fix the half width of the confidence interval and the autocorrelation lag 1 for batch means, and determine the run length. With Law and Carson's procedure we determine the run length for severa! M/M/1 queues, with occupation rate p = 0,.8 and 0.5, and y relative half width of the confidence interval, as ∞; 0.15 and 0.075, from 100 to 180 independent runs. The simulation results of 200 runs of some models was analysed by the percentagem of times that the real value of the mean waiting time belong to the 90% confidence interval. The results were very dose to 90%, and the correlations between the batch means as small as to be considered quasi independence.
 
WARNING - Viewing this document is conditioned on your acceptance of the following terms of use:
This document is only for private use for research and teaching activities. Reproduction for commercial use is forbidden. This rights cover the whole data about this document as well as its contents. Any uses or copies of this document in whole or in part must include the author's name.
Publishing Date
2018-06-28
 
WARNING: Learn what derived works are clicking here.
All rights of the thesis/dissertation are from the authors
CeTI-SC/STI
Digital Library of Theses and Dissertations of USP. Copyright © 2001-2024. All rights reserved.