Search

Excessive domestic energy usage is an impediment towards energy efficiency. Developing countries are expected to witness an unprecedented rise in domestic electricity in the forthcoming decades. A large amount of research has been directed towards behavioral change for energy efficiency. Thus, it is prudent to develop an intelligent system that combines the proper use of technology with behavior change research in order to sustainably transform end-user behavior at a large scale. This paper presents an overview of our AI-based energy efficiency framework for domestic applications and explains how micro-moments can provide an accurate understanding of user behavior and lead to more effective recommendations. Micro-moments are short-term events at which an energy-saving recommendation is presented to the consumer. They are detected using a variety of sensing modules placed at prominent locations in the household. A supervised machine learning classifier is then used to analyze the acquired micro-moments, identify abnormalities, and formulate a list of energy-saving recommendations. Each recommendation is presented through the end-user mobile application. The results so far include a mobile application in the front-end and a set of sensing modules in the backend that comprise, an ensemble bagging-trees micro-moment classifier (achieving up to 99.64% accuracy and 98.8% F-score), and a recommendation engine.

Domestic user behavior is a crucial factor guiding overall power consumption, necessitating the development of systems that analyze and help shape energy-efficient behavior. Therefore, the most important step in the process is the collection and understanding of highly detailed domestic consumption data. This article presents an appliance-based energy data collection and analysis system for energy efficiency applications. It leverages the concept of micro-moments, which are short-timed and energy-based events that form the overall energy behavior of the end user. The system comprises sensing modules for recording energy consumption, occupancy, temperature, humidity, and luminosity storing recordings on a database server. Sensing parameters were tested in terms of connection stability and measurement accuracy. A four-week contextual appliance-level dataset has been collected from research cubicles. Collected data were also classified into corresponding micro-moments with a variety of classifiers including ensemble decision trees and deep learning, achieving high stability and accuracy of 99%. Further, the micro-moment usage efficiency is calculated to quantify the efficiency of usage at the appliance level. [ABSTRACT FROM AUTHOR]

Among the large number of efforts that study the role of technology in energy saving, there exists, first, frameworks for monitoring and controlling energy consumption in households, second, systems that suggest best practices to users and energy providers, and third, findings that focus on the motivations that trigger a behavioral change toward energy efficiency. However, there is still no work that builds on the habitual behavior change of individuals and the use of technology for this purpose. In this paper, we survey the literature that aims at understanding the behavior of energy consumers and then changing it by recommending energy-saving activities. We build on the concept of “micro-moments” and the “habit loop” theory to explain how we can gradually change user routines by targeting those specific moments where the proper recommendation and a small but instant reward can be more effective in shaping a better energy-efficient profile. [ABSTRACT FROM AUTHOR]