J.-S.R. Lee, H.-W. Park (Korea), and H.-D.J. Jeong (New Zealand)
Long-Range Dependent Self-Similar Processes, SteadyState Discrete-Event Simulation, Buffer Overflow Probability, Hurst Parameter, Teletraffic
Recent studies of real teletraffic data in modern telecom munication networks have shown that teletraffic exhibits self-similar (or fractal) properties over a wide range of time scales. The properties of self-similar teletraffic are very different from the traditional models of teletraffic based on Poisson, Markov-modulated Poisson, and related pro cesses. The use of traditional models in networks charac terised by self-similar processes can lead to incorrect con clusions about the performance of analysed networks. In this paper, we investigate the extent to which self-similarity affects the performance of queueing processes in QoS re quirements such as buffer overflow probability. The nu merical results show that the buffer overflow probabilities of queueing systems were much higher, as values increased, than the queueing sys tems, because self-similar traffic resulted in a hyperbolic decrease in buffer overflow probabilities rather than an ex ponential decrease.
Important Links:
Go Back
