Semantic prediction assistant approach applied to energy efficiency in Tertiary buildings

Issue title: Special Issue on Semantic Technologies and Interoperability in the Build Environment

Guest editors: Álvaro Sicilia, Pieter Pauwels, Leandro Madrazo, María Poveda-Villalón and Jérôme Euzenat

Article type: Research Article

Authors: Esnaola-Gonzalez, Iker^{a; b; *} | Bermúdez, Jesús^b | Fernandez, Izaskun^a | Arnaiz, Aitor^a

Affiliations: [a] IK4-TEKNIKER, Iñaki Goenaga 5, 20600 Eibar, Spain. E-mails: iker.esnaola@tekniker.es, izaskun.fernandez@tekniker.es, aitor.arnaiz@tekniker.es | [b] University of the Basque Country (UPV/EHU), Paseo Manuel Lardizabal 1, 20018 Donostia-San Sebastián, Spain. E-mail: jesus.bermudez@ehu.eus

Correspondence: [*] Corresponding author. E-mail: iker.esnaola@tekniker.es.

Abstract: Fulfilling occupants’ comfort whilst reducing energy consumption is still an unsolved problem in most of tertiary buildings. However, the expansion of the Internet of Things (IoT) and Knowledge Discovery in Databases (KDD) techniques lead to research this matter. In this paper the EEPSA (Energy Efficiency Prediction Semantic Assistant) process is presented, which leverages the Semantic Web Technologies (SWT) to enhance the KDD process for achieving energy efficiency in tertiary buildings while maintaining comfort levels. This process guides the data analyst through the different KDD phases in a semi-automatic manner and supports prescriptive HVAC control strategies. That is, temperature of a space is predicted simulating the activation of HVAC systems at different times and intensities, so that the facility manager can choose the strategy that best fits both the user’s comfort needs and energy efficiency. Furthermore, results show that the proposed solution improves the accuracy of predictions.

Keywords: Semantic Web Technologies, Knowledge Discovery in Databases, energy efficiency, buildings

DOI: 10.3233/SW-180296

Journal: Semantic Web, vol. 9, no. 6, pp. 735-762, 2018