Towards a multi-scale modeling approach for software architectures

Abstract

In this paper, we propose a multi-scale modeling approach for software architecture oriented to facilitate adaptability management. The proposed design approach is founded on UML notations and uses component diagrams. The diagrams are submitted to vertical and horizontal transformations for refinement; this is done to reach a fine-grain description that contains necessary details that characterize the architectural style. The intermediate models provide a description with a given abstraction that allow the validation to be conducted significantly while remaining tractable w.r.t. complexity. The validation scope can involve intrinsic properties ensuring the model correctness w.r.t. UML description. To achieve this, we propose a set of model refinement rules. The rules manage the refinement and abstraction process (vertical and horizontal) as a model transformation from a coarse-grain description to a fine-grain description. Finally, we experimented our approach by modeling an Emergency Response and Crisis Management System (ERCMS) as a case of study.

Autonomic dynamically reconfigurable architectures for future communication systems

“…The challenge here is to generalize and extend this work to different levels of communication. Mastering the complexity of reconfiguration solutions is a challenge that we address by the formal compositional design and the multi-scale modeling [8]. Scaling up is another challenge that is best addressed by the rule-oriented characterization and the multi-scale modeling approach in general and our technique of management of dynamic architectures by of graph grammars, more particularly [7].…”