Résumé
Energy consumption has increased drastically atglobal scale due to the growing urbanization in cities. Energyefficiency in smart buildings can be achieved by introducing acontext-aware Internet of Things (IoT) approach, where sensorscan learn from their surrounding environment to control theactuators in a coordinated network. However, the IoT networkrequirements are constantly changing in unpredictable fashion,which needs faster and frequent on-demand network reconfigu-ration. Software Defined Network (SDN) has been envisionedas a new approach to enable a flexible and agile networkprogrammability in diverse IoT scenarios. However, the focus hasprimarily been on the design of the SDN computation logic, i.e.controllers, while the dynamic delivery and operations service-inferred IoT resource allocation has been postponed.To fill this gap, this paper proposes a comprehensive architec-tural design that is devised to empower SDN-enabled Context-Aware IoT systems and networks to create efficient energymanagement in smart buildings. We investigate the provisionof NFV IoT functions to support distributed automation andorchestration on IoT devices, and we present a context-awareapproach to gather, filter and process data from sensing data incampus buildings. We provide a proof of concept to demonstratesuccessful deployment and provisioning of virtualized services inthe context of Smart Campus research project.