Model-Based Availability Evaluation of Composed Web Services

Abstract

Web services composition is an emerging software development paradigm for the implementation of distributed computing systems, the impact of which is very relevant both in research and industry. When a complex functionality has to be delivered on the Internet, a service integrator can produce added value by delivering more abstract and complex services obtained by composition of existing ones. But while isolated services availability can be improved by tuning and reconfiguring their hosting servers, with Composed Web Services (CWS) basic services must be taken as they are. In this case, it is necessary to evaluate the composition effects. The authors propose a high-level analysis methodology, supported by a tool, based on the transformation of BPEL descriptions of CWS into models based on the fault tree availability evaluation formalism that enables a modeler, unfamiliar with the underlying combinatorial probabilistic mathematics, to evaluate the availability of CWS, given components availability and expected execution behavior.