With the advent of the new advances and techniques in Information and Communications Technologies, every place, everything and everyone can be connected and communication between them can be non-intrusive but meaningful. This is the technological basis created by the Internet of Things (IoT).
The high volume of data that is generated by today’s high performance commercial buildings can be leveraged to create a new generation of intelligent and efficient building management systems that operate autonomously.
Big data analytics helps us to leverage the large amounts of data produced by the IoT-based ecosystems to provide insights that help explain, expose and predict future building behavior. Specifically, in the field of smart buildings it is increasingly possible to apply machine learning algorithms to generate behavioral building models for solving problems like underperforming energy efficiency initiatives and comfort provisioning.
Prediction of energy use in buildings has received a remarkable amount of attention from researchers, as an approach to reduce energy consumption, which is intended to conserve energy and reduce harmful greenhouse gases.
The prediction of energy usage in buildings and modelling the behavior of the corresponding energy system, are complicated tasks due to influential factors such as weather variables, building construction, thermal properties of the physical materials and occupants’ activities Furthermore, there are several nonlinear inter-relationships among the involved variables, often in a noisy environment, which amplify the difficulty in identifying the precise interaction among them.