Deriving Non-zeno Behavior Models from Goal Models Using ILP

Abstract

This paper addresses the problem of automated derivation of non-zeno behaviour models from goal models. The approach uses a novel combination of model checking and machine learning. We first translate a goal model formalised in linear temporal logic into a (potentially zeno) labelled transition system. We then iteratively identify zeno traces in the model and learn operational requirements in the form of preconditions that prevent the traces from occurring. Identification of zeno traces is acheived by model checking the behaviour model against a time progress property expressed in linear temporal logic, while learning operational requirements is achieved using Inductive Logic Programming. As a result of the iterative process, not only a non-zeno behaviour model is produced but also a set of preconditions that, in conjunction with the known goals, ensure the non-zeno behaviour of the system.