Efficient estimation of buffer occupancy in ATM systems loaded by self-similar traffic

B-ISDN networks based on asynchronous transfer mode (ATM) are characterized by very low cell loss probability. This results in an enormous computational burden when determining the system's performance via Monte Carlo simulation. To improve the computational efficiency different methods (for example Restart and GEVT) have been proposed in literature to evaluate the occurrence of rare events. We show how importance sampling (IS) allows one to obtain useful results in this field. While IS techniques have been largely exploited in the evaluation of bit error rate in digital communication systems and of false alarm rate in radar devices very little has been done to develop efficient IS-based schemes to simulate a queueing system fed with self-similar traffic. With this work we show how IS may be applied to simulate a queue fed both with fractional Gaussian noise (FGN) and with synthetic traces with characteristics close to the ones of real traffic, resulting from videoconferencing sessions.