Clustering-based Active Learning on Sensor Type Classification in Buildings

Dezhi Hong, Hongning Wang, Kamin Whitehouse

Abstract: Commercial and industrial buildings account for a considerable portion of all energy consumed in the U.S., and thus reducing this energy consumption is a national grand challenge. Based on the large deployment of sensors in modern commercial buildings, many organizations are applying data analytic solutions to the thousands of sensing and control points to detect wasteful and incorrect operations for energy savings. Scaling this approach is challenging, however, because the metadata about these sensing and control points is inconsistent between buildings, or even missing altogether. Moreover, normalizing the metadata requires significant integration effort.In this work, we demonstrate a first step towards an automatic metadata normalization solution that requires minimal human intervention. We propose a clustering-based active learning algorithm to differentiate sensors in buildings by type, e.g., temperature v.s. humidity. Our algorithm exploits data clustering structure and propagates labels to their nearby unlabeled neighbors to accelerate the learning process. We perform a comprehensive study on metadata collected from over 20 different sensor types and 2,500 sensor streams in three commercial buildings. Our approach is able to achieve more than 92% accuracy for type classification with much less labeled examples than baselines. As a proof-of-concept, we also demonstrate a typical analytic application enabled by the normalized metadata.