An opportunistic activity-sensing approach to save energy in office buildings

Abstract

In this work, we recognised office worker activities that are relevant for energy-related control of appliances and building systems using sensors that are commonly installed in new or refurbished office buildings. We considered desk-related activities and people count in office rooms, structured into desk-and room-cells. Recognition was performed using finite state machines (FSMs) and probabilistic layered hidden Markov models (LHMMs).We evaluated our approach in a real living-lab office, including three private and multi-person office rooms. As example devices, we used different ceiling-mounted PIR sensors based on the EnOcean platform and plug-in power meters. In at least five days of study data per office room, including reference sensor data and occupant annotations, we confirmed that activities can be recognised using these sensors. For computer and desk work, an overall recognition accuracy of 95% was achieved. People count was estimated at 87% and 78% for the best-performing two office rooms. We furthermore present building simulation results that compare different control strategies. Compared to modern BEMS, our results show that 21.9% and 19.5% of electrical energy can be saved for controls based on recognised desk activity and estimated people count, respectively. These results confirm the relevance of building energy management based on activity sensing.

Occupancy Detection from Electricity Consumption Data

“…a class of graphical probability models), the authors estimate the number of persons in the offices as well as their location. Similarly, Milenkovic et al equipped three offices with PIR sensors and plug-in power meters, which measured the energy consumption of the computer screens [16]. Using layered hidden Markov models (LHMMs), the authors estimated the number of persons in the office as well as their current activity (e.g.…”

An occupant-participatory approach for thermal comfort enhancement and energy conservation in buildings

“…In addition, there are studies on smart wireless systems for better automation and control of building equipment [11]. Numerous studies have also been proposed on human detection [12][5] [13] of which lighting and air-conditioning can be turned-off in a smarter way. There are also studies on more intelligent arrangement of human activities such as meetings and classes with the objective in minimizing energy or electricity bills [14] [4].…”

Apportioning energy consumption in the workplace: a review of issues in using metering data to motivate staff to save energy

“…Rice, Hay, and Ryder-Cook (2010) demonstrated that their approach allowed long-term electricity consumption predictions for sets of appliances, users and heating, ventilation and air conditioning (HVAC), which were within 10% of the true value. Other researchers have demonstrated how network logs in workplaces can be used to align energy consumption with floors or rooms of a building (Christensen et al 2014), and how data from motion sensors in automated lighting might be used as a proxy for room-level energy consumption (Milenkovic and Amft 2013).…”