Internet of Things for Green Building Management: Disruptive Innovations Through Low-Cost Sensor Technology and Artificial Intelligence

Wayes Tushar, Nipun Wijerathne, Wen Tai Li, Chau Yuen, H. Vincent Poor, Tapan Kumar Saha, Kristin L. Wood

Research output: Contribution to journalArticle

17 Scopus citations

Abstract

Buildings consume 60% of global electricity. However, current building management systems (BMSs) are highly expensive and difficult to justify for small-to medium-sized buildings. The Internet of Things (IoT), which can collect and monitor a large amount of data on different aspects of a building and feed the data to the BMS's processor, provides a new opportunity to integrate intelligence into the BMS for monitoring and managing a building's energy consumption to reduce costs. Although an extensive literature is available on, separately, IoTbased BMSs and applications of signal processing techniques for some building energy-management tasks, a detailed study of their integration to address the overall BMS is limited. As such, this article will address the current gap by providing an overview of an IoT-based BMS that leverages signal processing and machine-learning techniques. We demonstrate how to extract high-level building occupancy information through simple, low-cost IoT sensors and study how human activities impact a building's energy use-information that can be exploited to design energy conservation measures that reduce the building's energy consumption.

Original languageEnglish (US)
Article number8454403
Pages (from-to)100-110
Number of pages11
JournalIEEE Signal Processing Magazine
Volume35
Issue number5
DOIs
StatePublished - Sep 2018

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Electrical and Electronic Engineering
  • Applied Mathematics

Fingerprint Dive into the research topics of 'Internet of Things for Green Building Management: Disruptive Innovations Through Low-Cost Sensor Technology and Artificial Intelligence'. Together they form a unique fingerprint.

  • Cite this