User Presence Estimation in Multi-Occupancy Rooms Using Plug-Load Meters and PIR Sensors

Abstract

In the built environment, the paradigm is shifting from providing uniform environment for all occupants to accommodating individual preferences through decentralised comfort devices enabled by IoT (Internet of Things) and ubiquitous computing. The effective implementation of localised and personalised comfort-enhancing and energy-saving strategies depends critically on the ability to detect the occupant presence in the immediate local environment. In this paper, estimating individual user presence in a shared office-space room using plug-load meters monitoring the power consumption of users' desktop computers and PIR (passive infrared) sensors at every user's desk is investigated. By extracting informative features from the data obtained and simple k-means clustering analysis, best-case presence accuracies of 89-99% and absence accuracies of 87-96% are achieved as validated by comparing with the ground-truth data for 4 different users.Index Terms-occupancy monitoring; smart buildings; data driven buildings; clustering; building energy efficiency; presence detection 978-1-5090-5019-2/17/$31.00 ©2017 IEEE

Office Low-Intrusive Occupancy Detection Based on Power Consumption

“…Other research has addressed occupancy inference in offices with extensive measurement units (i.e., one power meter per device) [10], [11]. Shetty et al observed the presence of four workers by monitoring the consumption of monitor screens and PCs, any by using a PIR sensor in each workplace [10]. To assign presence and absence states, they performed a kmeans clustering analysis on the measurement data.…”

“…The authors reported that .90 accuracy and .69 Kappa could be reached using their proposed approach. Shetty et al reported .94 averaged accuracy of three people, but they failed to detect the absence states of another person [10].…”

“…The finer granular methods increase the amount of energy that can be saved by personalizing the heating, ventilation, and air conditioning (HVAC) system based occupants' profiles. To attach more details, however, more power meters are required to observe specific persons or particular devices [7], [10]- [12]. Deploying a power meter for each device or for every person is most often unfeasible due to deployment-and maintenance-costs, in addition to being privacy intruding.…”

Office Occupancy Detection based on Power Meters and BLE Beaconing

“…Researchers have studied the occupancy detection in offices by mining power consumption. Yet, they mostly utilize intrusive power meter, either per appliance or per work desk, as clustered in the top right of Figure 2 They employ a clustering approach of PIR sensor data and the power consumption of a PC and monitor during one-week observation [119]. Similarly, Zhao et al deploy power meter per appliance in more varied appliances, including fans, chargers, lights, and printers [139].…”

“…In a cubicle office environment, binary occupancy detection has been approached by deploying power meters for each computer-related device (e.g., PCs and monitors) and a PIR sensor in each workspace [119]. Unsupervised k-means clustering is applied to interpret the absent and present state for each of four users.…”