AI-Based Home Energy Management System Considering Energy Efficiency and Resident Satisfaction

Abstract

Demand-side energy management is becoming increasingly important owing to concerns related to global warming and energy shortages. In particular, as the development of Internet of Things (IoT) enables the precise control of home appliances, the demand for home energy management systems (HEMSs) is expected to increase. This article proposes an artificial intelligence-based HEMS (AI-HEMS) that provides both energy efficiency and resident satisfaction. To this end, we implemented three prediction mechanisms: 1) derivation of comfort temperature; 2) device-free sleep prediction; and 3) occupancy-probability-based outing prediction. Based on these mechanisms, we present four intelligent heater control strategies: 1) outing; 2) occupancy; 3) comfort; and 4) sleep-based control. For evaluation, an experimental testbed was constructed and measurements were taken. To increase the reliability of the evaluation by excluding natural energy fluctuation factors, a treatment group (100 households) and a control group (2281 households) were recruited to measure the energy savings of the treatment group compared to the control group. In a 48-day evaluation, AI-HEMS was found to provide an energy-saving rate of approximately 14% and resident satisfaction of approximately 91%. These results imply that the proposed system can save energy while maintaining a high level of satisfaction.