Estimação e intervalo de confiança Bootstrap para a intensidade de trafego em filas M/M/1/K usando o Método do Mínimo Qui-Quadrado

Abstract

Queuing theory is a vast research field. The service process in which queues are formed is the object of study by different researchers. Analyzing the queuing process, service performance and the variables that impact on its arrangement, such as the traffic intensity, defined as the ratio between the arrival rate and the service rate, are of great importance to researchers who analyze efficiency on dimensioning the service structure. However, it is known that in most cases the parameters involved in the process are unknown and need to be estimated. The monography aims to obtain bootstrap confidence interval for the traffic intensity in finite Markovian queues with a single server, known as M / M / 1 / K, in Kendall notation. For this we will use the estimation method of the chi-square minimum. A numerical example illustrates the efficiency of the procedure.