ETH Zurich : Computer Science : Pervasive Computing : Distributed Systems : Education : Student Projects : Abstract

The Comfstat – Automatically sensing thermal comfort for smart heating (M)

Status: Abgeschlossen

Background

Global warming, the lack of fossil fuels and the resulting increase in energy prices induce an urgent need for sustainable buildings. Heating accounts for 70% of the domestic energy consumption in Switzerland. Some of this energy may be saved using “smart” thermostats like Google’s Nest, which allows the temperature to drop when the occupants are not present. However, the user acceptance of these systems is still quite low. The reason is that while being smart with respect to energy savings, these smart thermostats neglect to address thermal comfort sufficiently.

Thermal comfort is influenced by many factors including the clothing and activity level of the occupants. Whether an occupant is feeling hot or cold is thereby related to the heat balance of the human body. If the metabolic rate is equal to the heat loss to the environment, thermal balance is obtained. At lower and higher metabolic rates, occupants feel cold and hot, respectively. Thus, to measure thermal comfort, a smart thermostat should be able to measure the metabolic rate of occupants.

Objectives

Our goal is to develop a set of algorithms to deduce the metabolic rates of individual occupants from heart rate sensors as featured by current smart watches and smart phones. Combined with occupancy information, we will then use this information to determine an appropriate heating schedule for a smart thermostat.

Requirements

This project requires interest in machine learning, pattern recognition and data mining. Students are expected to be highly motivated and to meet with their supervisors regularly to discuss current progress and next steps.