Performance Analysis of a Single Server Queue Loaded by Long Range Dependent Traffic

Recent studies on broadband networks show that real traffics exhibit Long Range Dependence (LRD). Because of its dramatic consequences on queueing performances this property has to be taken into account in network design and management. To these aims we analysed the behaviour of a single server queueing system loaded by an LRD arrival process modelled by fractional Gaussian noise. Our goal was to obtain an analytical estimation of the complementary probability, that represents an upper bound for Cell Loss Ratio. The approach is based on the Large Deviations Theory and we successfully validated the results by means of simulation studies