Computing of heating energy consumption in a model villa house by using artificial neural networks in Gilan Province.

Gilan Province is one of the 31 provinces of Iran. Gilan has a humid subtropical climate with, by a large margin, the heaviest rainfall in Iran. Large parts of the province are mountainous, green and forested. Along with expanding natural issues and decreasing fossil assets, considers zeroing in on energy decrease just as utilization of sustainable power assets have quickened. Be that as it may, considering the innovative and efficient inconceivability's, the most intelligent arrangement is energy saving by giving energy proficiency in family units. In this study, an artificial neural network (ANN) model is developed in order to compute hourly heating energy consumption of a model house designed in Gilan which is located in north of Region of Iran. Hourly heating energy consumption of the model house is calculated by degree-hour method. ANN model is trained with heating energy consumption values of years 2015–2018 and tested with heating energy consumption values of year 2019. The training and test figures were depicted for February month of these years. Best estimate is found with 29 neurons and a good coherence is observed between calculated and considered values. According to the results obtained, root-mean-squared error (RMSE), absolute fraction , mean absolute percentage error (MAPE) values are 1.2668, 0.9905, and 0.2095 for training phase and 1.2129, 0.9890, and 0.2085 for testing phase respectively. There was a great consistency between the predicted and tested results, demonstrating the feasibility and practicability of the proposed ANN models for predicting the thermal property of a villa house

Keywords:

energy consumption , Heating , Artificial Neural Networks , building and villa , Gilan Province.