A big data association rule mining based approach for energy building behaviour analysis in an IoT environment

• Published in: Scientific reports Vol. 13; no. 1; p. 19810
• Main Authors: Dolores, M., Fernandez-Basso, Carlos, Gómez-Romero, Juan, Martin-Bautista, Maria J.
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 13-11-2023; Nature Publishing Group; Nature Portfolio
• Subjects: 639/705/1042; 639/705/1046; 639/705/117; 639/705/258; Air conditioning; Algorithms; Artificial intelligence; Associations; Big Data; Building management systems; Data mining; Energy consumption; Energy efficiency; Humanities and Social Sciences; Internet of Things; multidisciplinary; Science; Science (multidisciplinary); Sensors; Weather forecasting
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-023-47056-1

The enormous amount of data generated by sensors and other data sources in modern grid management systems requires new infrastructures, such as IoT (Internet of Things) and Big Data architectures. This, in combination with Data Mining techniques, allows the management and processing of all these heterogeneous massive data in order to discover new insights that can help to reduce the energy consumption of the building. In this paper, we describe a developed methodology for an Internet of Things (IoT) system based on a robust big data architecture. This innovative approach, combined with the power of Spark algorithms, has been proven to uncover rules representing hidden connections and patterns in the data extracted from a building in Bucharest. These uncovered patterns were essential for improving the building’s energy efficiency.