Intelligent edge-based recommender system for internet of energy applications

Abstract

When investigating how people conserve energy, most researchers and decision-makers render a conceptual distinction between prevention (e.g. unplugging devices) and productivity measures. Nevertheless, such a two-dimensional approach is inefficient from both a conceptual and policy standpoint, since it ignores individual differences that influence energy-saving behavior. Preserving electricity in homes and buildings is a big concern, owing to a scarcity of energy resources and the escalation of current environmental issues. Furthermore, the COVID-19 social distancing policies have resulted in a temporary transition of energy demand from industrial and urban centers to residential areas, resulting in greater consumption and higher costs. In order to promote the sustainability and preservation of resources, the use of new technologies to increase energy efficiency in homes or buildings becomes increasingly necessary. Hence, the goal of the project is to provide consumers with evidence-based data on the costs and advantages of ICT-enabled energy conservation approaches, as well as clear, timely, and engaging information and assistance on how to realize the energy savings that are attainable, in order to boost user uptake and effectiveness of such techniques. End-users can visualize their consumption patterns as well as ambient environmental data using the Home-assistant user interface. More notably, explainable energy-saving recommendations are delivered to end-users in form of notifications via the mobile application to facilitate habit change. In this context, to the best of the authors' knowledge, this is the first attempt for developing and implementing an energy-saving recommender system on edge devices. Thus, ensuring better privacy preservation since data are processed locally on the edge, without the need to transmit them to remote servers, as is the case with cloudlet platforms.