Pourkazeni, M., Aghaeifar, R. (2013). Forecast of Iran’s Electricity Consumption Using a Combined Approach of Neural Networks and Econometrics. Iranian Economic Review, 17(3), 139-159. doi: 10.22059/ier.2013.73502
Mohammad Hossein Pourkazeni; Roya Aghaeifar. "Forecast of Iran’s Electricity Consumption Using a Combined Approach of Neural Networks and Econometrics". Iranian Economic Review, 17, 3, 2013, 139-159. doi: 10.22059/ier.2013.73502
Pourkazeni, M., Aghaeifar, R. (2013). 'Forecast of Iran’s Electricity Consumption Using a Combined Approach of Neural Networks and Econometrics', Iranian Economic Review, 17(3), pp. 139-159. doi: 10.22059/ier.2013.73502
Pourkazeni, M., Aghaeifar, R. Forecast of Iran’s Electricity Consumption Using a Combined Approach of Neural Networks and Econometrics. Iranian Economic Review, 2013; 17(3): 139-159. doi: 10.22059/ier.2013.73502
Forecast of Iran’s Electricity Consumption Using a Combined Approach of Neural Networks and Econometrics
School of Economics and Political Sciences, University of Shahid Beheshti, Tehran, Iran.
Abstract
Electricity cannot be stored and needs huge amount of capital so producers and consumers pay special attention to predict electricity consumption. Besides, time-series data of the electricity market are chaotic and complicated. Nonlinear methods such as Neural Networks have shown better performance for predicting such kind of data. We also need to analyze other variables affecting electricity consumption so as to estimate their quantitative effects. This paper presents a new approach for forecasting: a combined method of Neural Networks (ANN) and econometrics methods which can also explain the effect of rising electricity prices on consumption after the Subsidies Reform Plan. Data is from 1988-2008, and the method is compared with Neural Network and ARIMA based on the RMSE performance function that shows the advantage of the combined approach. The provident prediction is done for 2009- 2014 and indicated that after decreasing subsidy, electricity consumption would increase slightly until 2014.
1- Aggarwal, Sanjeev Kumar, Lalit Mohan Saini, Ashwani Kumar, (2009). Electricity Price Forecasting in Deregulated Markets: A Review and Evaluation. Electrical Power and Energy Systems 31, pp 13-22. 2- Asgary, Ali, (2000), “Energy Demand”, Doctoral dissertation of Tehran University. 3- Azarbayejani, Karim and Sharifi Alimorad, and Sateei Mahsa, (2006). estimation of electrical energy in the country's industrial sector”, Journal of Economic Research, number 73, p 133-166. 4- Bill, Rasel and Jakson Tam, (2007), Introduction to Neural Networks, Alborzy, Mahmood, Tehran, Sharif University of Technology Institute of Scientific Publications.
5- Bishop, Christopher, (1995), “Neural Networks for Pattern Recognition”, Oxford. 6- Conejo, Antonio J, Javier Contreras, Rosa Espı´nola, Miguel A, (2005). Forecasting Electricity Prices for a Day-ahead Pool-based Electric Energy Market”, International Journal of Forecasting 21, pp 435-462. 7- Faost, Loran, (2009), “Fundamentals of Neural Networks”, Veisi, Hady and Mafakhery, Kobra and Baghery Shooraki, Saeed, Institute for Publishing and printing of ministry of culture and Islamic Guidance, first edition.
8- Goodarzvand Cheginy, Amir, (2009), Matlab toolbox, Naghoos press, Third Edition. 9- Pino Raul, Fuente David Dela, Priore Paolo, Parreno Jose, (2007), “Short Term Forecasting of the Electricity Market of Spain using Neural Networks”, Journal of Economic Literature.
10- Pino Raul, Jose´ Parreno, Alberto Gomez, Paolo Priore, (2008). Forecasting Next-day Price of Electricity in the Spanish Energy Market Using Artificial Neural Networks. Engineering Applications of Artificial Intelligence 21, pp 53-62.
11- Ramezani, Maryam and Reza Ramezani, “Electricity Demand Forecast in Iran using Neural Network and ARIMA Model”, Tarbiat Modares University of Tehran 12- Rajabzadeh, Ali, “Evaluation of combined methods for forecasting economic models”, Ph.D. dissertation, Tarbiat Modares University of Tehran 13- Ridley D, (2003), The Univariate Moving Window Spectral Method, Computers & Industrial Engineering, vol 45, pp 691–711 14- Sadeghi, Hossein & Mehdi Zolfaghari (2010). Short-term forecasts of electricity demand using Neural Networks and wavelet transform. Quarterly Journal of economic, Shahid Chamran University of Ahvaz, 2, 27-56. 15-Samadi, Saeed and Amene Shahidi and Farzane Mohammadi, (2008). Electricity Demand Analysis in Iran by Using Cointegration and ARIMA Modeling. Knowledge & development journal, 25. 16-Shalkof, Robert, G. (2003). Artificial Neural Networks, Joorabian, Mahmood, Ahvaz, Shahid Chamran University Press. 17-Sohrabkhani, Sara, (2006), Modeling the monthly electricity consumption using Neural Networks and simulation, MSc thesis, industry Engineering, Tehran University.
18-Tashkiny, Ahmad, (2005). applied econometrics with Microfit. Tehran, Dibagaran Arts, and Cultural Institute. 19-Vashaghani, Mohsen, (2009). Introduction around Neural Networks. Shahid Beheshti University.
20-Zhang G Peter, (2003). Time Series Forecasting Using a Hybrid ARIMA and Neural Network Model”, Neurocomputing 50, 50,159-175. 21- Ministry of Energy reports, http://amar.tavanir.org.ir. 22- Iran Grade Management Company, http://igmc.i.
Top