Modeling of energy efficiency for residential buildings using Artificial Neuronal Networks

Increasing the energy efficiency of buildings is a strategic objective in the European Union, this is the main reason why numerous studies have been carried out to evaluate and reduce energy consumption in the residential sector. In Spain some regulations are being applied, since the end of 2013, to new and existing buildings with the objective of evaluating energy performance of the building and establishing measures to improve its energy efficiency. These energy saving measures are aimed at reducing the CO2 emissions and energy consumption. The process of evaluation and qualification of the energy efficiency in existing buildings should contain an analysis of the thermal behavior of the building envelope. Given the difficulty of intervening in a house with destructive auscultation techniques to determine the composition of the different layers of the enclosure, it is necessary to develop non-destructive methodologies that allow to determine the thermal behavior of an enclosure and its representative parameters. In this work we present a system based on Artificial Neural Networks (ANN) for modeling the thermal behavior of an enclosure and the results of the research carried out on a sample of buildings of different typologies and uses, located in the northern area of Spain. The system created is able to predict the energy performance of a house given some of its characteristics in an non-destructive, fast and cheap manner.