A family of measurement-based admission control algorithms
Zoltán Richárd Turányi, András Veres, András Oláh · 1998
In this paper we identify a set of the requirements for an efficient admission control algorithm and propose new algorithms. These methods need only aggregate traffic measurements, work with simple FIFO scheduling and take only minimal assumptions on the pattern of the traffic. The requirements define a family of measurement based admission control algorithms of which three key members are discussed. We give effective bandwidth formulae for buffered and bufferless systems with token bucket and peak rate limited sources. It is also shown how the utilization can be improved by measuring the variance of the traffic rate while avoiding the limitations of MBAC methods based on the Central-limit theorem.The theoretical background of this work is the effective bandwidth definition introduced by Gibbens and Kelly which has its roots in the Chernoff bounds.