Data-driven assessment of room air conditioner efficiency for saving energy

Room air conditioners (RACs) are one of the high energy-consuming home appliances. Developing a smart solution to evaluate and track the efficiency of RACs is essentially useful for residents to make necessary maintenance or replacement decisions. While smart meters are increasingly installed to monitor electricity use, the application of smart meter data to evaluate the RAC efficiency remains inadequate. In this paper, we present a data-driven framework to identify non-inverter window RACs with low energy efficiency by analyzing smart meter data from the university student hall rooms. In this framework, we first applied the extreme gradient boosting (XGBoost) method to predict a RAC's hourly electricity consumption. Then we measured the effect of outdoor temperature on the XGBoost prediction of hourly RAC electricity consumption using the Shapley Additive Explanation method to interpret the RAC's efficiency. We conjectured that the RAC efficiency is normal if the predicted hourly electricity consumption is significantly correlated with the outdoor temperature. In contrast, the RAC efficiency is low if the outdoor temperature changes have little impact on the predicted electricity consumption. Finally, we applied the K-Means clustering algorithm to separate the RACs into the low efficiency and normal efficiency categories based on each's pattern of outdoor temperature's impact on electricity consumption. Our cross-validation result showed that the XGBoost model can achieve an average R-2 score of 0.50 and an average root mean squared error of 0.20 kWh. We used RAC replacement records to validate our framework of interpreting the RAC's efficiency. On average, RACs having low efficiency consumed 25.69% more electricity per hour. Overall, our data-driven framework can contribute to extending the value of smart meters for RAC efficiency evaluation. Meanwhile, the smart meter data-driven framework can be improved, and more validation is needed in the future.

Automated summary

Room air conditioners (RACs) are high energy-consuming home appliances. Developing a smart solution to evaluate and track the efficiency of RACs is essential. The data-driven framework proposed in this study identifies non-inverter window RACs with low efficiency by analyzing smart meter data and uses XGBoost to predict hourly electricity consumption. The framework separates RACs into low efficiency and normal efficiency categories based on the impact of outdoor temperature on electricity consumption, with promising validation results.