Prediksi Pelabelan Rating AC Efisiensi Energi Menggunakan Pemodelan Machine Learning

Abstrak

The purpose of this research is to analyze data and perform machine learning modeling to predict the energy efficiency rating of air conditioning (AC) units using a labeled AC dataset from the Directorate General of New, Renewable and Energy Conservation (EBTKE). The data consists of Power, Cooling Capacity, Efficiency, Annual Energy Consumption, and Electricity Cost. The data is visualized using box plots and linear regression to examine the relationship between the dependent variable (Rating) and the independent variables. The analysis shows that the Efficiency variable has the greatest impact on the Rating, with a linear regression coefficient value of 0.75. Then, the machine learning model using the decision tree method is tested using 5-fold K-fold validation. The evaluation results of the model show a mean absolute error (MAE) of 0.2, mean squared error (MSE) of 0.4, root mean squared error (RMSE) of 0.63, and accuracy of 0.9. Based on these results, it can be concluded that the machine learning model using the decision tree method can be used to predict the energy efficiency rating of AC units with a satisfactory level of accuracy. However, to improve the accuracy of the predictions, it is necessary to increase the amount of data used in the modeling.