HA379 : Modeling and forecasting the trend of electricity consumption in Iran
Thesis > Central Library of Shahrood University > Industrial Engineering & Management > MSc > 2022
Authors:
[Author], Mohammad Mirbagherijam[Supervisor]
Abstarct: An accurate and correct forecast of the development of electricity consumption is especially important for the correct planning and development of the country's electricity industry. Therefore, the main objective of this research is to model and predict the evolution of electricity consumption in the country. Factors and variables influencing the trend of electricity consumption in the country were identified baxsed on previous studies and relevant data collected over the period 1978-2019 to create forecast models. Several models and methods were used to predict the trend of electricity consumption in 2020-2026, including the method of using simple indicators, energy consumption intensity, consumption trend line, regression model and neural network. The estimation results of the regression model show that the development of electricity consumption in the country is influenced by the per capita income and the consumption of the previous period and that other model variables such as air temperature, precipitation and energy prices have no statistically significant influence. Electricity consumption has increased almost tenfold in the period 1978-1998 and its average annual growth is 7.47%, on the basis of which the electricity consumption in 2026 is projected to be 455504 million kilowatt hours. While the forecast of electricity consumption this year using the regression model is equal to 369556 million kilowatt hours. The difference in the forecast results of electricity consumption trend shows that the accuracy of forecasting different models and approaches is not the same, and therefore it is important to choose the appropriate forecasting approach and model.  
Keywords:
#Keywords: Prediction models #Electricity consumption trend #Regression model #Neural network #Simple indicators of electricity consumption prediction. Keeping place: Central Library of Shahrood University
Visitor: