Software product line (SPL) engineering has proven to improve software quality and shorten development cycles, cost and time. In product line engineering, product derivation is concerned with the realization of the variability at the implementation level. However, the majority of research works focuses on instantiating the variants selected in the final product, while the derivation at the architecture level has been poorly explored. As product line engineers often customize the product architecture by hand during the application engineering phase, the derivation and customization processes of the product line architecture (PLA) might be in some cases error-prone. Consequently, in this research we present an Ontology-based product Architecture Derivation (OntoAD) framework which automates the derivation of product-specific architectures from an SPL architecture. Our solution uses a language-independent model to specify the product line architecture and a model-driven engineering approach for architecture derivation activities. We use an ontology formalism to reason about the automatic generation of model-to-model transformation rules based on the selection of features and we illustrate our approach using a voice over IP motivating example. Finally, we report results about scalability and performance regarding the size of the variability model.

In a Grid computing environment, resources are shared among a large number of applications. Brokers and schedulers find matching resources and schedule the execution of the applications by monitoring dynamic resource availability and employing policies such as first-come-first-served and back-filling. To support applications with timeliness requirements in such an environment, brokering and scheduling algorithms must address an additional problem - they must be able to estimate the execution time of the application on the currently available resources. In this paper, we present a modeling approach to estimating the execution time of long-running scientific applications. The modeling approach we propose is generic; models can be constructed by merely observing the application execution “externally” without using intrusive techniques such as code inspection or instrumentation. The model is cross-platform; it enables prediction without the need for the application to be profiled first on the target hardware. To show the feasibility and effectiveness of this approach, we developed a resource usage model that estimates the execution time of a weather forecasting application in a multi-cluster Grid computing environment. We validated the model through extensive benchmarking and profiling experiments and observed prediction errors that were within 10% of the measured values. Based on our initial experience, we believe that our approach can be used to model the execution time of other time-sensitive scientific applications; thereby, enabling the development of more intelligent brokering and scheduling algorithms.

The authors introduce a reflective resource management framework that offers facilities for resource awareness and dynamic reallocation of resources for an adaptive middleware architecture. The main emphasis of the paper is the design and implementation of a resource management framework for such an architecture. We are not carrying out research in specific resource management algorithms; rather, we focus on providing a general framework which can accommodate best practice in the area. Such facilities ease the management of resources by providing a complete and consistent model of resources in the system at varying levels of abstractions. In addition, activities in the system are represented in a task model which provides a higher level of resource management.