IP bandwidth allocation management using agents and neural network approach

Video and LAN traffic can be modeled as self-similar processes, whereas Internet traffic can be modeled by multifractal processes. The Hurst parameter is a measure of the self-similarity of a process. The objective of this work is to use this characteristic of Internet traffic in order to allow future video on demand service providers (VDSPs) to optimize their bandwidth utilization and consequently their communications cost. The work addresses one aspect of a global project that specifies intelligent agent architecture to manage the relationship between VDSP, Internet service providers (ISPs) and end-customers. In this paper, we address the egress traffic aspect of the VDSP and propose a neuronal network approach to allow a VDSP agent to estimate the nature of the future value added service provider (VADP) egress traffic using the Hurst parameter. This approach is evaluated against statistical estimators.