Dynamic Performance of Bandwidth Tracking in Preemptive Distributed Heterogeneous Networking Environments
Michael Jurczyk, Craig Sullivan · 2002
This work investigates the dynamic behavior of a bandwidth tracking algorithm in a version of a distributed heterogeneous data dissemination system called the Agile Information Control Environment (AICE). To optimally allocate resources in this environment, the probability of setup or rejection of communication requests has to be derived prior to its setup without any knowledge of the actual topologies of the underlying networks. A bandwidth tracking algorithm is introduced that is able to predict the setup/rejection of a communication request with a high accuracy of up to 95% i n nonpreemptive and preemptive networking environments by tracking the average spare bandwidth of end-to-end communication channels. The tracking algorithm uses elements of exponential adjustment coupled with a binary search. It is shown that these mechanisms enable the tracker to quickly learn about changes in the topology of the underlying networks, changes in the load on the networks, and changes in the preemption mechanism.