SHAPING AND POLICING OF FRACTAL TRAFFIC

We examine the effectiveness of shaping and policing mechanisms in red ucing the inherent variability of fractal traffic, with the objective of increasing network operating points. Whether a shaper simply spaces a flow or allows small bursts according to a leaky bucket, we show us ing analytical arguments that, i) the Hurst parameter, which describes the asymptotic variability of the traffic, is unaffected; and ii) whi le the traffic can be made smoother over time scales smaller than one corresponding to the shaper's buffer size, fluctuations over longer ti me scales cannot be appreciably altered. We further show that if shapi ng is used to reduce buffer size requirements at a network bottleneck, any savings here are offset by the increased buffer requirements at t he shapers. Perhaps the most significant deficiency of shaping identif ied here is that it is necessary to model individual streams to a leve l of accuracy that is not Feasible in practice. In contrast, statistic al multiplexing can achieve reasonable network efficiencies by only re quiring characterizations of aggregate traffic.