This chapter presents a model-driven service engineering (MDSE) methodology that uses OMG MDA specifications such as BMM, BPMN and SoaML to identify and specify services within a service-oriented architecture. The methodology takes advantage of business modelling practices and provides a guide to service modelling with SoaML. The presentation is case-driven and illuminated using the telecommunication example. The chapter focuses in particular on the use of the SoaML modelling language as a means for expressing service specifications that are aligned with business models and can be realized in different platform technologies.

Abstract.Component based design is a new methodology for the construction of distributed systems and applications. In this new setting, a system is built by the assembly of (pre)-existing components. Remains the problem of the compositional verification of such systems. We investigate methods and concepts for the provision of "sound" assemblies. We define an abstract, dynamic, multi-threaded, component model, encompassing both client/server and peer to peer communication patterns. We define a behavioural interface type language endowed with a (decidable) set of interface compatibilty rules. Based on the notion of compliance of components to their interfaces, we define the concepts of "contract" and "contract satisfaction". This leads to the notion of sound assemblies of components, i.e., assemblies made of contracted components interacting through compatible interfaces. Sound assemblies possess interesting properties like "external deadlock freeness" and "message consumption".

No abstract

We consider three kinds of ordering properties provided by a multicast system. The messages can be delivered to the different recipients according to a local order, a causal order or a total order. In this paper, a formal method is proposed to prove the total and causal order of multicast protocols. A generalized formal result for multicast protocols is obtained. Some addressing features for other formal results are considered. This study allows to prove that existing systems have the required property. The results can be used to define new solutions. Moreover, the method makes use of various ordering properties, well fitted to practical systems, to achieve a better understanding of the ordering processing.

No abstract