How does eco-coaching help to save energy? assessing a recommendation system for energy-efficient thermostat scheduling

Abstract

This paper presents findings from a field deployment that explored a design approach we call eco-coaching: giving personalized suggestions for specific actions that would reduce wasted energy. We studied ThermoCoach, which performs eco-coaching for thermostat scheduling. It senses and models occupancy patterns in a home, and provides occupants alternative suggestions for configuring their thermostat. Our study shows that eco-coaching accomplished four things. First, it made it easier for users to implement an effective thermostat schedule. Second, it supported user agency in negotiating energy savings and comfort goals. Third, it facilitated learning different scheduling strategies as well as weighing different options. Finally, it challenged users' beliefs about how well they were doing. These outcomes, in turn, were successful in getting users to employ and experiment with more efficient setback strategies. Going forward, we propose ways that eco-coaching systems could better support users in customizing and assessing the systems' recommendations.

Learning from the Veg Box

“…This work contributes to the understanding of 'smart' autonomous systems in the home [2,3,4,13,47,48,49] through the study of the veg box as a service that has a digital (the Web and email interface) as well as physical component (the actual delivery of goods), and that supports agency delegation. We also make a contribution to food HCI (e.g.…”

“…gas, wind, solar) could help users to continuously evaluate the system's performance and hence grant or revoke agency. Such an approach has recently been demonstrated by a small variety of research projects [2,3,4,49]. Similarly, for autonomous cars, it may be useful to display information related to the financial cost of each trip (such as in [42]), the fuel efficiency, and how long the trip will take -for all these variables the comparison between autonomous operation and manual mode should be shown.…”

“…As such, the design of interaction mechanisms that enable users to work around this unpredictability is an open challenge in HCI [28,45]. Nascent instantiations of the AIoT focus on the domestic environment and include smart thermostats [47,48,49], domestic appliances [4,13], energy systems [2,3] and cleaning robots [17,43]. With a few exceptions, which have studied off-the-shelf products such as the Nest Thermostat [47,48] and the Roomba [17,43], prior studies around autonomous systems in the home have focused on research prototypes.…”

Washing with the Wind

“…While these studies show a promise of the agents' automatic abilities to sustainably manage energy use, they do also report a loss of engagement over time that leads to missed opportunities for householders to act sustainably. To combat this, studies have explored designs that encourage engagement, such as the proposed recommender system ThermoCoach by Yang et al [28,71], Fischer et al [20] situated sensing technology that tailors energy advice, and Clear et al's [14] study of 'drifting' thermal comfort zones in effort to support heating practices. However, most of these studies also report that when smart technology becomes embodied in people's lives, we as designers are challenged on how to design interactions fitting within the messiness of everyday life [5].…”

Assisted Shifting of Electricity Use

“…They observed that while the Nest manager played an active role in assisting householders to adopt sustainable routines, conflicting user and system objectives dampened the effectiveness of maintaining these. In response, the same authors developed the ThermoCoach prototype [73], promoting eco-coaching (personalized recommendations, eco-forecasting, easy invocation, and user control) assisting users to continuously reconfigure the Nest to reduce consumption.…”