Dimensionality reduction techniques to analyze heating systems in buildings

The highest cause of energy consumption in buildings is due to Heating, Ventilation, and Air Conditioning (HVAC) systems. A large number of interconnected variables are involved in the control of these systems, so conventional analysis approaches are often difficult. For that reason, data analysis by means of dimensionality reduction techniques can be a useful approach to address energy efficiency in buildings. In this paper, a method is proposed to visualize the relevant features of a heating system and its behavior and to help finding correlations between temporal, production and distribution variables. For that purpose, a modification of the self-organizing map is used. The energy consumption of HVAC systems is also analyzed using a dimensionality reduction technique (t-Distributed Stochastic Neighbor Embedding, t-SNE). The proposed approach is applied to a real building at the University of León.