A Forecasting Model for the Energy Requirements of an Office Building Based on Energy Modeling and Machine Learning Models - A Case Study of Morocco

In Morocco, where buildings consume more than 35% of the country's energy, the decision to integrate energy efficiency practices into the building from the design phase can avoid any energy waste. In this study, we examine the impact of integrating insulation on the energy efficiency of an office building using two approaches, with a focus on predicting the energy demand of an office building in Casablanca. The first method uses the Trnsys software for dynamic thermal modeling and the result is 37.45 kWh/m(2).year on total energy demand modeling over one year, which has allowed us to meet the requirements of the Moroccan Thermal Regulation for Buildings (RTCM). The second approach is based on the use of two machine learning models, and the results show that the SVM is more efficient than the RF model. It achieved a coefficient of determination of 97%.