AUTHOR=Eirinaki Magdalini , Varlamis Iraklis , Dahihande Janhavi , Jaiswal Akshay , Pagar Akshay Anil , Thakare Ajinkya TITLE=Real-time recommendations for energy-efficient appliance usage in households JOURNAL=Frontiers in Big Data VOLUME=Volume 5 - 2022 YEAR=2022 URL=https://www.frontiersin.org/journals/big-data/articles/10.3389/fdata.2022.972206 DOI=10.3389/fdata.2022.972206 ISSN=2624-909X ABSTRACT=Research has shown that user behavior is the most influential factor in the energy consumption of a household. Changing user behavior to improve energy usage leads to efficient energy consumption, saving money for the consumer and being more friendly for the environment. In this work we propose a framework that aims at assisting households in improving their energy usage by providing real-time recommendations for efficient appliance use. The framework allows for the creation of household-specific and appliance-specific energy consumption profiles by analyzing appliance usage patterns. Based on the household profile and the actual power demand, the system generates real-time recommendations on which appliances should be turned off at that moment. For instance, if a consumer forgets their A/C on at a time that it’s usually off (e.g. when there’s no one at home), the system will detect this as an outlier and notify the consumer. In the ideal scenario, a household has a smart meter monitoring system installed, that records energy consumption at the appliance level. This is also reflected in the datasets available for evaluating such systems. However, in a more realistic scenario there exists only one main meter reading for the entire house. In the absence of a smart home system with separate consumption meters for every appliance, non-intrusive load monitoring (NILM) techniques can be used, which employ a single monitor for the total energy consumption of a household and data mining algorithms to disaggregate the consumption into appliance level. In this paper we propose an end-to-end solution to this problem, starting with the energy disaggregation process, and the creation of user profiles that are then fed to the pattern mining and recommendation process, that through an intuitive UI allows users to further refine their energy consumption preferences and set goals. For our experimental evaluations and the proof-of-concept implementation, we employ the UK-DALE (UK Domestic Appliance-Level Electricity) dataset. The results show that the proposed framework accurately captures the energy consumption profiles of each household and thus the generated recommendations recommendations are matching the actual household energy habits and can help reduce their energy consumption by 2 to 17%.