Electric energy consumption predictions for residential buildings: Impact of data-driven model and temporal resolution on prediction accuracy

This study aims to investigate the measurement parameters for predicting the electric energy consumption of residential buildings using a data-driven model. Herein, the temporal resolution of data and algorithms that can improve prediction accuracy are comparatively investigated. For the investigation, the time units of the data collected from the monitoring system of an actual residential building are set as 10 min and 1 h. Further, algorithms such as multiple linear regression (MLR), multilayer perceptron (MLP), support vector machine (SVM), and random forest (RF) are employed to predict the electric energy consumption of the building. The parameters of the data collection include electric energy consumption based on the usage type, occupancy information, and indoor environmental information. The model is validated using a Kfold technique, and the prediction accuracy is compared using R2 and the t-value. Analyses using seven input variables reveal that the prediction accuracy for the 1 h interval data is better than that for the 10 min interval data, based on the temporal resolution of the data. In addition, the results of the algorithms reveal that the prediction accuracy is the highest when the MLR algorithm is used, followed by those when using the RF, MLP, and SVM algorithms. A relatively simple statistical method and low-resolution data rather than a complex machine learning algorithm or high-resolution data achieved the best prediction accuracy. These results are expected to facilitate high-accuracy predictions of the electric energy consumption of residential buildings.