Análisis de datos en edificios inteligentes - Análisis de grupos e identificación de patrones

Abstract

[EN] The transition towards a more sustainable environment requires the development of new control systems to integrate renewable energy sources into the energy systems and also to model the customer’s behaviour and its energy use. The objective of this paper is to give insights about the data quality and the effects produced on the viability of sustainable and efficiency measures that could be applied to smart-homes. This paper used the heating consumption data, provided by EnergyLab Nordhavn, to study two apartments and a district heating substation, performing two clustering approaches using the K-means algorithm to group similar heating daily profiles and relate it with the weather conditions data. Using the clustering results, different classification algorithms such as logistic regression and random forest were applied to predict the heating consumption level with regards to the ambient conditions. The evaluation of these algorithms pointed out the logistic regression as the best performing algorithm, which was used to predict the heating power. The previous process showed that the aggregated heating consumption data of the substation is more reliable and valid for energy prediction than the individual households data.

[ES] En este proyecto, se analizarán las mediciones de temperatura interior y consumo energético realizadas en edificios inteligentes en Nordhavn. Los datos se obtendrán de 20 apartamentos situados en Sundmolen, y se analizará el consumo eléctrico y de calefaccion, temperatura exterior e interior, irradiación solar, CO2 y ocupación de la vivienda con el objetivo de identificar patrones en las diferentes habitaciones y apartamentos. Esto dará información sobre el uso de la energia, el clima interior de la vivienda y cómo las tecnologías inteligentes pueden mejorar las condiciones interiores de la vivienda y el bien estar de las personas.