Study of power demand forecasting of a hospital by ensemble machine learning

Abstract

To save energy in existing buildings, power demand can be predicted so a more efficient operation of equipment can be realized, like utilizing heat storage to lower the peak. Many attempts to predict building power consumption by machine learning have used simulation values in virtual buildings with no measurement errors or defects in the data. These models tend to have higher accuracy scores but have the risk of overfitting and possibly malfunction for missing data or outliers. To avoid the problems, this study proposes an ensemble machine learning algorithm to forecast power demand for a hospital building in Japan. Using the power consumption data, predictions were made by using algorithms such as Deep Neural Network (DNN) and Random Forest (RF). Each algorithm was combined to create ensemble models that take the weighted average of the predicted values. Consequently, we overcame the issues of each individual method, and achieved higher prediction accuracies. We selected the appropriate method for forecasting the power demand of real buildings based on accuracy. In future studies, we will apply the same methodology to predict cooling load.