Cookietalk

Referentin: Alona Zharova (Wirtschaftswissenschaftliche Fakultät)

Recommendation Systems for Energy Efficiency in Residential Buildings

Household energy consumption accounts for approximately 20% of total global energy consumption, leading to a significant proportion of CO2 emissions from energy production. Increasing energy efficiency through demand management, such as load shifting, is a viable strategy for reducing CO2 emissions. To nudge changes in energy consumption behavior, simple but powerful architectures are vital.

In this talk, we presents our recent research on recommendation systems that provide personalized and generalized recommendations. First, we show an architecture for a utility-based context-aware multi-agent recommendation system that generates personalized appliance usage recommendations. Second, we present an explainable multi-agent recommendation system that provides explainable recommendations for optimal device scheduling in a textual and visual manner. Transparent, understandable, and persuasive recommendations support the electricity consumers’ behavioral change while opening up the “black box” of recommendations. Third, we propose an activity-based recommendation system that provides personalized, actionable recommendations requiring minimal user input. By shifting household activities rather than individual appliance usage, we suggest a more intuitive approach to energy efficiency grounded in the social practices of domestic life. Fourth, we introduce a generalized recommendation system that utilizes local renewable energy generation data and does not require sensible electricity consumption data. Recommending time slots rather than exact hours for adjusting energy use and avoiding electricity usage provides households with more flexibility. We also propose several performance evaluation frameworks for the suggested recommendation systems and show the empirical results.