Framework for the Performance Assessment of Architectural Options on Intelligent Distributed Applications

摘要

This position paper brings together the evaluation of ambient intelligence architectures in context-awareness systems with performance modeling. Thus, firstly appropriate description methods for distributed intelligent applications are summarized. Derived from the system characterization, typical software performance engineering techniques are based on the augmented description of the model regarding performance annotations. However, these annotations are only related with the syntactical view of the architecture. In the next generation of performance assessment tools for intelligent context-awareness systems, the description of the system would be capable of reasoning and acquiring knowledge about performance. Having an appropriate architectural description including performance aspects, any possible design options for intelligent distributed applications can be evaluated according to their performance impact. Therefore, we propose the use of an ontology with performance-related information - not only to evaluate the architecture off-line - but also building a context broker that assesses the performance during execution.