Deep learning analysis of smart meter data from a small sample of room air conditioners facilitates routine assessment of their operational efficiency

Abstract

Room air conditioners (RACs) are crucial household appliances that consume substantial amounts of electricity. Their efficiency tends to deteriorate over time, resulting in unnecessary energy wastage. Smart meters have become popular to monitor electricity use of home appliances, offering underexplored opportunities to evaluate RAC operational efficiency. Traditional supervised data-driven analysis methods necessitate a large sample size of RACs and their efficiency, which can be challenging to acquire. Additionally, the prevalence of zero values when RACs are off can skew training. To overcome these challenges, we assembled a dataset comprising a limited number of window-type RACs with measured operational efficiencies from 2021. We devised an intuitive zero filter and resampling protocol to process smart meter data and increase training samples. A deep learning-based encoder–decoder model was developed to evaluate RAC efficiency. Our findings suggest that our protocol and model accurately classify and regress RAC operational efficiency. We verified the usefulness of our approach by evaluating the RACs replaced in 2022 using 2022 smart meter data. Our case study demonstrates that repairing or replacing an inefficient RAC can save electricity by up to 17 %. Overall, our study offers a potential energy conservation solution by leveraging smart meters for regularly assessing RAC operational efficiency and facilitating smart preventive maintenance.

Keywords

• Room air conditioning
• Operational energy efficiency
• Smart meter
• Deep learning
• Smart preventive maintenance