Improving energy efficiency through activity-aware control of office appliances using proximity sensing - A real-life study

Energy efficiency is a key operational characteristic of today's office environments. In this paper, we present a system architecture to control desk appliances such as computer screens based on recognised desk and computer work activities. In a real-life intervention study at seven desks, we use screen-attached ultrasound sensors and explore a proximity-based activity recognition approach for saving energy by automatically turing computer screens off when not using them. We analyse online performance of our approach regarding recognition rate and screen resume delay. Furthermore, we present a comparative analysis of our proximity-controlled approach against the computer-controlled power management and a non-controlled baseline to quantify energy saving benefits. Our results show energy savings of up to 43% and 55% for proximity-controlled computer screens compared to computer-controlled and non-controlled scenarios respectively.