Measurement-based admission control: what is the research agenda?

Measurement-based admission control algorithms (MBACs) have been shown to achieve much higher utilization than parameter-based admission control algorithms (Jamin et al, 1997). There has been much research interest in MBACs, and several new MBACs have been proposed in the literature. This research has typically focused on the equations (and, to a lesser extent, the measurement algorithms) used to decide whether or not to accept an incoming flow. These proposals range from the simple and ad hoc to the complicated and principled, derived from detailed mathematical analysis. Recent empirical examination of the relative performance of these algorithms, however, has shown that they all achieve almost identical levels of performance. That is, for a given level of QoS they all achieve very similar levels of utilization. Thus, regardless of whether the MBAC equation is ad hoc or principled, it produces essentially the same performance. Given this result, the authors claim that further research on different MBAC equations is largely irrelevant. Thus, the authors take the following position with regard to research on MBACs. Further research on better admission control equations will likely be a fruitless endeavour. Rather, research should focus on the development of mechanisms that would enable MBACs to support a range of policy beyond the single policy implicit in current algorithms.