A Cognitive Enabled Edge-Computing Architecture for Future Generation IoT Environments

Nowadays, Smart Environments (SEs) are pervasively deployed in buildings (e.g., houses, schools, and offices) and outdoor environments with the goal of improving the quality of life of their inhabitants. SEs are usually designed and developed by using well-suited architectures and platforms having the aim of simplifying and making straightforward the SE implementation. Up to now, SEs are mostly reactive and, in some ways, proactive. Current research efforts are devoted to making such environments cognitive, i.e., able to automatically adapt and adhere to the possible changes in users' needs and behaviors. Anyway, in this field, the development of SEs is still in its infancy. In this direction, the paper proposes a novel Cognitive-enabled, Edge-based Internet of Things (CEIoT) architecture, purposely designed to develop cognitive IoT-based SEs. Such architecture wants to overcome some limitations arising during the usage of common SE platforms and architectures. CEIoT introduces some abstractions ranging from the "in-platform" implementation of decentralized cognitive algorithms to the realization of smart data aggregations.