Abstract
Model finders are very popular for exploring scenarios, helping users validate specifications by navigating through conforming model instances. To be practical, the semantics of such scenario exploration operations should be formally defined and, ideally, controlled by the users, so that they are able to quickly reach interesting scenarios. This paper explores the landscape of scenario exploration operations, by formalizing them with a relational model finder. Several scenario exploration operations provided by existing tools are formalized, and new ones are proposed, namely to allow the user to easily explore very similar (or different) scenarios, by attaching preferences to model elements. As a proof-of-concept, such operations were implemented in the popular Alloy Analyzer, further increasing its usefulness for (user-guided) scenario exploration.

Abstract

Abstract
Model-driven engineering (MDE) is a software engineering approach based on model transformations at different abstraction levels. It prescribes the development of software by successively transforming the models from abstract (specifications) to more concrete ones (code). Alloy is an increasingly popular lightweight formal specification language that supports automatic verification. Unfortunately, its widespread industrial adoption is hampered by the lack of an ecosystem of MDE tools, namely code generators. This paper presents a model transformation from Alloy to UML class diagrams annotated with OCL (UML+OCL) and shows how an existing transformation from UML+OCL to Alloy can be improved to handle dynamic issues. The proposed bidirectional transformation enables a smooth integration of Alloy in the current MDE contexts, by allowing UML+OCL specifications to be transformed to Alloy for validation and verification, to correct and possibly refine them inside Alloy, and to translate them back to UML+OCL for sharing with stakeholders or to reuse current model-driven architecture tools to refine them toward code.

Abstract

Abstract

Abstract
In cloud environments, resources should be acquired and released automatically and quickly at runtime. Therefore, ensuring the desired QoS is a great challenge for the cloud service provider. Moreover, it increases when we have large amount of data to be manipulated in this environment. Considering that, performance is an important requirement for most customers when they migrate their applications to the cloud. In this paper, we propose a model for measuring a Service Response Time estimated for different request types on large databases available in a cloud environment. This work allows the cloud service provider and its customers establish an appropriate SLA relative to performance expected of services available in the cloud. Finally, the model was evaluated in Amazon EC2 cloud infrastructure and the TPC-DS like benchmark was used for generating a database of structured data, considering that some cloud computing platforms support SQL queries directly or indirectly. This makes the proposed solution relevant for these kind of problems.