FAST AND ACCURATE ESTIMATION OF ATM QUALITY-OF-SERVICE PARAMETERS WITH APPLICATIONS TO CALL ADMISSION CONTROL

It is demonstrated how fast and accurate estimates of quality-of-servi ce (QOS) parameters can be obtained for an ATM multiplexer queueing mo del fed by multiple Markovian traffic sources. This has been achieved by constructing a simple approximation of the buffer overflow probabil ity, which involves computation of two parameters based on the theory of large deviations. Upper bounds on other QOS parameters, such as cel l loss ratio, mean cell delay and cell delay variance, can all be deri ved from this estimate. It is shown that this approximation is much mo re accurate than the pure effective bandwidth one, which ignores the s tatistical multiplexing gain due to a large number of sources. One att raction of the proposed method is that the speed of computation of thi s approach is independent of the size of the system. Thus the authors' analytical techniques can be implemented fast enough for real-time ad mission control in ATM networks.