A Measure of Robustness Against Multiple Kinds of Perturbations

摘要

Parallel and distributed heterogeneous computing systems may operate in an environment that undergoes unpredictable changes causing certain system performance features to degrade. Such systems need robustness to guarantee limited degradation despite fluctuations in the behavior of its component parts or environment. Our previous work in this area presented a method for generating a measure of robustness for a given system. However, the focus of that approach was on a scenario where all perturbations were of the same kind, e.g., all perturbations were in message sizes or computation times, but not both message sizes and computation times. This paper gives an extended discussion of the case where perturbations could be of different kinds, and presents some new insights.