A Time Series Approach to Queueing Systems with Applications for Modeling Job-Shop In-Process Inventories

The behavior of a uniformly sampled queueing system is characterized and interpreted using a time series approach. The advantages of employing time series to obtain a model of the queue's behavior are shown to be simplicity, flexibility and reliability. An analysis of actual queue data shows that the queue behavior of a uniformly sampled queueing system with a single server and Poisson-exponential activities is adequately described by a first order autoregressive model. The autocorrelation function is used to relate queueing theory and the time series model to obtain the commonly required parameters for a queueing system, in a manner independent of the mean level of the queue.