ABSTRACT:

We tend to tend to develop a stochastic foundation for bandwidth estimation of networks with random service, where bandwidth availability is expressed in terms of bounding functions with a printed violation probability. Exploiting properties of a stochastic max-plus algebra and system theory, the task of bandwidth estimation is formulated as inferring an unknown bounding perform from measurements of probing traffic. We have a tendency to derive an estimation methodology that is primarily based largely on iterative constant rate probes. Our answer provides proof for the utility of packet trains for bandwidth estimation within the presence of variable cross traffic. Taking advantage of statistical strategies, we have a tendency to tend to show how our estimation technique will be realized in observe, with adaptive train lengths of probe packets, probing rates, and replicated measurements required to achieve every high accuracy and confidence levels. We tend to generally tend to evaluate our methodology in an exceedingly terribly controlled testbed network, where we tend to tend to point out the impact of cross traffic variability on the time-scales of service availability, and give a comparison with existing bandwidth estimation tools.