Discovering gradual patterns in building operations for improving building energy efficiency. (15th August 2018)

• Record Type: Journal Article
• Authors: Fan, Cheng; Sun, Yongjun; Shan, Kui; Xiao, Fu; Wang, Jiayuan
• Is Part Of: Applied energy. Volume 224(2018)
• Page Start: 116
• Page End: 123
• Publication Date: 2018-08-15
• Subjects: Gradual pattern mining -- Motif discovery -- Data mining -- Building operational performance -- Building energy efficiency; Power (Mechanics) -- Periodicals; Energy conservation -- Periodicals; Energy conversion -- Periodicals; 621.042
• DOI: 10.1016/j.apenergy.2018.04.118
• Languages: English
• ISSNs: 0306-2619

Abstract

Highlights: Gradual pattern mining was applied for analyzing building data for the first time. A generic methodology was developed to analyzing big building operational data. A log ratio method was proposed to improve efficiency in post-mining. Gradual patterns are capable of describing co-variations among variables. Useful knowledge has been extracted for building energy management. Abstract: The development of information technologies has enabled real-time monitoring and controls over building operations. Massive amounts of building operational data are being collected and available for knowledge discovery. Advanced data analytics are urgently needed to fully realize the potentials of big building operational data in enhancing building energy efficiency. The rapid development of data mining has provided powerful tools for extracting insights in various knowledge representations. Gradual pattern mining is a promising technique for discovering useful patterns from building operational data. The knowledge discovered is represented as gradual relationships, i.e., " the more/less A, the more/less B ". It can bring special interests to building energy management by highlighting co-variations among numerical building variables. This study investigated the usefulness of gradual pattern mining for building energy management. A generic methodology was proposed to ensure the quality and applicability of the knowledge discovered. The methodology was validated through a case study. The results showed that the methodology could successfully extract valuable insights on building operation characteristics and provide opportunities for building energy efficiency enhancement.