Intelligent building energy consumption prediction system

Predicting how well a building consumes energy is an important area of study because it could help make building energy management systems work better. The applied building energy consumption data is used. The proposed method suggests an effective model to predict the energy consumption by a building. The model is good because it fits both the number of hours of heat pain and the amount of energy used during training and tests with R2 values higher than 0.97. The gaps in performance between the building energy computer model and field data were, on average, -12.5% less than what was really happening. The intelligence computer model was only 8.65% off when it came to overestimating, which was less than the field data. This paper uses the theoretical framework of artificial neural network for the prediction purpose. The proposed system is limited to our dataset alone at present.