A Predictive Model for the Automated Management of Conditioning Systems in Smart Buildings

The paper describes a technological basis for dynamic actions targeted to an effective, real-time control of air conditioning systems in smart buildings with a focus on energy management. The proposed procedure could be extended to more complex systems, usually including a number of prosumer (producer and consumer) nodes, connected to a smart grid and remotely controlled by a Distributed System Operator (DSO) in distributed control and monitoring systems. Accurate, continuously-recorded local weather data are then used to make decisions aimed at both reducing energy consumption and assuring pre-established comfort levels. The amount of saved energy can be estimated by observing a building's energy performance under the action of different meteorological agents through data mining and machine learning methods. Moreover, some possible advantages from real-time exploitation of a building's thermal inertia are shown. The proposed on-line management was also validated through laboratory experimental tests, whose results are reported and discussed.