Hossein Haghbin

The aim of this thesis is to use deep learning methods in predicting the electricity consumption in Bushehr city based on past electricity consumption information as well as available climate information. For this purpose, the hourly electricity consumption data of Bushehr city along with climatic features such as temperature, humidity and wind speed related to the years 2018 and 2019 have been collected. In order to model this prediction, deep learning methods such as convolutional neural network, recurrent neural network, long short-term memory model, residual neural network and hybrid models have been used. Finally, a proposed hybrid model has been presented, which can improve the prediction of electricity consumption compared to other models.