Key points are not available for this paper at this time.
The major contributor to home energy consumption is home appliances, comprising about two-thirds of the total energy used. Analyzing electricity usage at the appliance level is crucial due to varying energy consumption levels among different appliances. This analysis allows individuals to either upgrade or minimize the use of inefficient appliances. To prioritize energy conservation, reducing the usage of energy-inefficient household appliances is imperative. Smart meters in a smart home scenario record electricity consumption data. The collected and monitored data from smart meters integrate with Big Data, playing a substantial role in this domain. Our proposed model optimizes electricity usage by identifying and categorizing household energy-inefficient appliances with a novel transition detection algorithm and appliance detection model. Furthermore, Utilizing Appliance-Level power consumption data from the UK-DALE dataset and One vs Rest clustering techniques, the proposed model effectively identifies devices with higher energy consumption. Additionally, the result analysis of the proposed model highlights the advantages of transitioning to energy-efficient devices, reducing both power consumption and financial wastage.
Choubey et al. (Wed,) studied this question.