A large-scale evaluation of automated metadata inference approaches on sensors from air handling units. (August 2018)

• Record Type: Journal Article
• Authors: Gao, Jingkun; Bergés, Mario
• Is Part Of: Advanced engineering informatics. Volume 37(2018)
• Page Start: 14
• Page End: 30
• Publication Date: 2018-08
• Subjects: Sensor metadata -- Building automation system -- FDD application; Computer-aided engineering -- Periodicals; Engineering -- Data processing -- Periodicals; 620.00285
• DOI: 10.1016/j.aei.2018.04.010
• Languages: English
• ISSNs: 1474-0346

Abstract

Graphical abstract: Highlights: Metadata inference approaches are evaluated on sensors from 614 air handling units. For FDD applications, these approaches can infer required metadata with 75% accuracy. Results are particularly sensitive to seasonality effects in training/testing data. Accuracy vs. labeling cost tradeoffs may be mitigated by soft thresholding. Abstract: Building automation systems provide abundant sensor data to enable the potential of using data analytics to, among other things, improve the energy efficiency of the building. However, deployment of these applications for buildings, such as, fault detection and diagnosis (FDD) on multiple buildings remains a challenge due to the non-trivial efforts of organizing, managing and extracting metadata associated with sensors (e.g., information about their location, function, etc.), which is required by applications. One of the reasons leading to the problem is that varying conventions, acronyms, and standards are used to define this metadata. To better understand the nature of the problem, as well as the performance and scalability of existing solutions, we implement and test 6 different time-series based metadata inference approaches on sensors from 614 air handling units (AHU) instrumented in 35 building sites accounting for more than 400 buildings distributed across United States of America. We infer 12 types of sensors and actuators in AHUs required by a rule-based FDD application: AHU performance and assessment rules (APAR). Our results show that: (1) the average performance of these approaches in terms of accuracy is similar across building sites, though there is significant variance; (2) the expected accuracy of classifying the type of points required by APAR for a new unseen building is, on average, 75%; (3) the performance of the model does not decrease as long as training data and testing data are extracted from adjacent months.