Model of a self-similar traffic generator and evaluation of buffer storage for classical and fractal queuing systems

Research over the past decade and a half show that network traffic is inherently self-similar and, therefore, the traditional analysis of queues based on the assumption of a Poisson flow, cannot accurately predict the performance of the node and the network in general. The lack of common analytical results of the queues study at the self-similar traffic dictates to seek ways of its adequate description and modeling. Revenue model in the self-similar traffic model and the calculation of buffer storage can be applied in solving the problems of network traffic management and network planning resources.