A review of data mining technologies in building energy systems: Load prediction, pattern identification, fault detection and diagnosis

• Published in: Energy and built environment Vol. 1; no. 2; pp. 149 - 164
• Main Authors: Zhao, Yang, Zhang, Chaobo, Zhang, Yiwen, Wang, Zihao, Li, Junyang
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.04.2020; KeAi Communications Co., Ltd
• Subjects: Big data; Building energy efficiency; Building energy systems; Supervised data mining; Unsupervised data mining; Unsupervised data mining; Building energy systems; Big data; Building energy efficiency; Supervised data mining
• ISSN: 2666-1233; 2666-1233
• DOI: 10.1016/j.enbenv.2019.11.003

•Supervised data mining-based methods for building energy systems are reviewed.•Unsupervised data mining-based methods for building energy systems are reviewed.•Strengths and shortcomings of the existing data mining-based methods are revealed.•Four important research tasks in the future are proposed. With the advent of the era of big data, buildings have become not only energy-intensive but also data-intensive. Data mining technologies have been widely utilized to release the values of massive amounts of building operation data with an aim of improving the operation performance of building energy systems. This paper aims at making a comprehensive literature review of the applications of data mining technologies in this domain. In general, data mining technologies can be classified into two categories, i.e., supervised data mining technologies and unsupervised data mining technologies. In this field, supervised data mining technologies are usually utilized for building energy load prediction and fault detection/diagnosis. And unsupervised data mining technologies are usually utilized for building operation pattern identification and fault detection/diagnosis. Comprehensive discussions are made about the strengths and shortcomings of the data mining-based methods. Based on this review, suggestions for future researches are proposed towards effective and efficient data mining solutions for building energy systems.