Optimizing service selection and allocation in situational computing applications
DEI - Sala Conferenze
22 Ottobre 2010
Mobile platforms, intelligent sensors, and smart systems surround us throughout our everyday lives and interact with each other and their users. The execution environment includes different types of devices and the infrastructure can dynamically change both its physical and logical architecture. In this continuously evolving environment, the applications interact with their external environment in a situation-aware manner. Each application is composed of various services that provide well-defined functionalities of possible general use and are executed either remotely on the service providers or locally on the nodes of the pervasive environment.
In this scenario, we propose a model for the service selection and allocation process. The model evaluates at run-time the optimal trade-off between the remote execution of the services and their dynamic local deployment in the situational computing environment. The local deployment must take into account the Quality of Service constraints and the characteristics and capabilities of physical devices, including their performance and energy. Moreover, because of the dynamic nature of the scenario, where significant changes can possibly occur at run-time, the final solution must easily accommodate the need for re-optimization. These aspects are taken into account and addressed in the proposed model.
Area di ricerca: