A self-healing framework for QoS-aware web service composition via case-based reasoning

Abstract

The self-healing ability is very important for service-oriented systems in a highly dynamic environment. Case-based reasoning is adopted to cope with the component services failing to meet with the functional and nonfunctional requirements in this paper. We take previous failure instances as cases which are stored in a case base. When a new fault occurs, its symptoms are extracted and matched against the case base to look for the most similar case. A case representation and a similarity function are proposed. Meanwhile, a novel reuse approach is designed to find the solutions satisfying the symptoms. Moreover we present a self-healing framework and conduct experiments with real QoS dataset. Experimental results show that case-based reasoning improves the self-healing ability encouragingly. © 2013 Springer-Verlag.