Energy Demand Forecasting Model Using Artificial Neural Networks: A Case Study of a Faculty Building in Tehran

In this paper, the natural gas demand for an educational building in Tehran (Sharif University of Technology) is modeled using the artificial neural networks. An artificial neural network is a very powerful and intelligent tool that can be used to model and identify nonlinear and complex systems. According to the results obtained from this modeling, the accuracy of the natural gas demand forecasting for a typical day is more than 85 percent. The advantages of the model used in this paper are to consider the influence of climate parameters (ambient temperature, relative humidity, radiation intensity and wind speed) and the number of inhabitants.

Keywords:

Energy Demand Forecast , Energy Modeling , Artificial Neural Network