The project aims at the elaboration of Information Systems able to optimize the energy consumption in a building while preserving human comfort. The main innovation of Green-Mod project is the realization of reliable stochastic data-driven models applied to temporal signals acquired from heterogeneous sources such as distributed sensors, weather web services, calendar information and user-trigerred events.
Smart building, smart home, control algorithm, consumption modelling
Several specific novelties were integrated to the project. These include: global, instead of local, optimization of building automation sub-systems (i.e. heating, ventilation, cooling, solar shadings, electric lightings); generalization to an unseen building configuration or usage through a self-learning data-driven algorithm; and the inclusion of a stochastic state-based modeling to better cope with seasonal and building activity patterns. The Green-Mod project will be applied to existing buildings already equipped with extended networks of sensors, as well as new building technologies, from which we can acquire data in order to validate our research results.
Website of the project
PhD project, extension of the initial Smart Building Ra&D project, financed by Hasler Foundation, duration 3 years (2012 - 2015).