The QTES/PH/1 queue

In performance analysis of computer and communication systems, the designer is often faced with two challenges: modeling an input process accurately and then solving a resulting queueing problem. In this paper, we present a modeling methodology called QTES (Quantized Transform-Expand-Sample) which can be used to model the interarrivai distribution (histogram) accurately and to capture the effect of autocorrelations approximately. We then show that a difficult queueing problem (using a QTES input with autocorrelations) can be solved. Our method is analytically tractable and numerically robust to the extent of the examples presented (and those tried but not presented).