A Dynamic Context-Aware Architecture for Ambient Intelligence

Ambient Intelligence (AmI) deals with scenarios where users receive services according to their state. This is possible thanks to environments populated with multiple sensors and actuators. The contextaware features focus on considering a rich knowledge about users, including the current events but also preferences, activities or social context. The effective availability of this information demands mechanisms that seamlessly gather and propagate it between different settings, and react dynamically to changes in the needs and the environment. Their design is one of the key difficulties in AmI. Our work addresses this problem with an architecture for the context subsystem of AmI applications. It specifies several layers of abstraction for information, the relevant components to provide their storage, management and distribution, and the automated lifecycle and binding of components to support the previous functionality. A case study on path guidance illustrates the architecture and is the basis to discuss the related work.