NetQuest: A Flexible Framework for Large-Scale Network Measurement

In this paper, the authors present NetQuest, a flexible framework for large-scale network measurement. They apply Bayesian experimental design to select active measurements that maximize the amount of information the authors gain about the network path properties subject to given resource constraints. They then apply network inference techniques to reconstruct the properties of interest based on the partial, indirect observations people get through these measurements. By casting network measurement in a general Bayesian decision theoretic framework, the authors achieve flexibility.