Forecasting energy demand of PCM integrated residential buildings: A machine learning approach

Forecasting energy demand has become an essential element for energy stakeholders in planning and reducing the energy consumption of buildings. Machine learning techniques have become popular for forecasting building energy demand owing to their reliability and cost efficiency. This research aims to propose a model for predicting the energy consumption of PCM-integrated residential buildings in the Mediterranean climate region. For the model development, Multiple Regression (MR), Support Vector Machines (SVM), and Artificial Neural Networks (ANN) were used. For the first time, the PCM melting point, building, and environment parameters were considered simultaneously as input parameters to predict the energy consumption of PCM-integrated buildings. The energy simulation of nine different building types located in seven different cities of the Mediterranean climate region were performed to generate the database. After the model development, the most influential design parameters were established by performing sensitivity and parametric analysis. The results showed that the optimum PCM for annual energy savings varied from PCM-25 to PCM-27. The shape factor significantly influenced the specific heating and cooling demand of buildings. Moreover, the statistically evaluated prediction models showed that SVM and ANN methods are more reliable, with R² value of over 0.99. The externally validated prediction models demonstrated that the ANN model can estimate the energy consumption of PCM-integrated buildings with more accuracy. From sensitivity analysis, it was found that cooling degree days, heating degree days, volume, shape factor, and PCM melting point are the key influencing parameters affecting the energy demand of buildings.