چکیده مقاله :
هدف اصلی این مطالعه پیش بینی میزان مصرف انرژی الکتریکی در بخش‌کشاورزی است. برای این منظور از روش‌های سری زمانی خود توضیح جمعی میانگین متحرک(ARIMA) و شبکه ی عصبی مصنوعی استفاده شد. به منظور انجام بررسی، از داده‌های سالانه ی دوره ی 1346 تا 1383 برای برآورد و آموزش مدل‌ها و از داده‌های دوره ی 1384 تا 1387 به منظور بررسی قدرت پیش‌بینی مدل‌های مختلف استفاده شد. در این مطالعه معیارهای ارزیابی مختلفی شامل میانگین قدرمطلق خطا(MAE)، میانگین مجذور خطا(MSE) و درصد میانگین مطلق خطا(MAPE) مورد استفاده قرار گرفتند. نتایج مطالعه نشان داد که شبکه ی عصبی پرسپترون سه لایه با روش آموزش الگوریتم پس انتشار دارای MAPE معادل 02/1 درصد می‌باشد که کمتر از مقدار این آماره برای مدل سری زمانی است(13/1 درصد). سایر معیارهای خطا نیز نتایج یکسانی دارند و بر این اساس شبکه ی عصبی قادر است میزان مصرف برق در بخش کشاورزی را بهتر از مدل ARIMA پیش بینی نماید. لذا پیشنهاد می‌شود وزرات نیرو جهت پیش‌بینی‌های آتی خود از این روش استفاده نماید.
چکیده انگلیسی:
The main object of this study is to predict electricity consumption of agricultural sector in Iran. To get the objective, time series method of Auto-Regressive Moving Average (ARMA) and artificial neural networks (ANN) were used. Annual data for period of 1967 to 2008 was used. The Mean Absolute Percent Error (MAPE), Root of Mean of Squared Error (RMSE) and Mean Absolute Error (MAE) criteria were used for comparing the ability of different forecasting methods. As the result showed Feed Forward artificial neural network with back proportion algorithm can predict electricity consumption with MAPE equal to 1.02%, while the corresponding value for time series model obtained 1.13 percent. Other criteria also revealed the same result, so, ANN is expected to predict electricity consumption more precise than ARMA model. Therefore, energy ministry may use ANN in future predictions.
منابع و مأخذ:
1. Amini Fard, A. 2001, Estimate of electricity demand in
residential sector, M.S. thesis. Faculty of Economics and
Management, Shiraz University. (in Persian)
2. Amin Naseri, M. R., and Kochak Zadeh, A. 2006, Study of
ARIMA linear method and fuzzy-artificial neural network non
linear method in prediction of urban gas demand, Journal of
Economic research, , 71: 133-146. (in Persian)
3. Darbelly, G. S. and M. Slama 2000. Forecasting the short-term
demand for electricity, do neural networks stand a better chance?,
International Journal Of Forecasting, 16: 71-83.
4. Esfehaniyan, M. and Amin Naseri, M. R., 2008. Provide an
artificial neural network for short run prediction of petroleum
price, International Journal of Engineering Science, 19: 27-35. (in
Persian)
5. Esmaeili, A., and Tarazkar, M. H. 2005. Estimate of electricity
demand in agricultural sector, Case Study: Fars Province, 5th
Iranian Conference on Agricultural Economics, Iran, Zahedan. (in
Persian)
6. Greene W.H. 2000. Econometric analysis, 3th edition. PrenticeHall,
Englewood Cliffs, New Jersey.
7. Islam, S. M., Al-Alawi, S. M. and K. A. Ellithy 1995. Forecasting
monthly electric load and energy for a fast growing utility using
an artificial neural network, Electric Power Systems Research,
34( 1): 1-9.
8. Kavaklioglu K., Ceylan H., Ozturk H.K., Canyurt, O.E. 2009.
Modeling and prediction of Turkey’s electricity consumption
using Artificial Neural Networks, Energy Conversion and
Management, 50: 2719–2727.
9. Ministry of Energy, 2008. Energy Balance Sheet, Deputy for
Power and Energy Affairs, Power and Energy Planning
Department, Iran. (in Persian)
10. Murat YS, Ceylan H. 2006. Use of artificial neural networks for
transport energy demand modeling. Energy Policy, 34: 3165–72.
11. Pesaran, H.M. and B. pesaran 1997. Working With Microfit 4.0:
An Introduction to Econometrics, Oxford University Press,
Oxford.
12. Seddighi, H. R, Law ler, K. A. and A. V. Katos 2000.
Econometrics: A Practical Approach, Sunderland Business
School, UK.
13. Shakibai, A. R. and Koochekzadeh, S. 2009. Modeling and
predicting agricultural energy consumption in Iran, AmericanEurasian
J. Agric. & Environ. Sci., 5:308-312.
14. Sourosh, A., Baradaran Kazemzadeh, R. V. and Bahreyni Nejad,
A. 2009. Improvement of regression model by artificial neural
network clustering for prediction of monthly electricity
consumption, Journal of Sharif, 25: 73-83. (in Persian)
15. Sozen A, Arcaklioglu E, Ozkaymak M. 2005. Modelling of the
Turkey’s net energy consumption using artificial neural network.
Int. J. Comput. Appl. Technol., 22(2/3):130–6.
16. Tarazkar, M. H., Najafi, B. 2005. Application of artificial
intelligence in price forecasting Case study: price of rice in Fars
Province, Scientific & Research Quarterly Journal of Bank
Keshavarzi, 9: 181-209. (in Persian)
17. Zibaei, M. and Tarazkar, M. H., 2004. Study of short- and longrun
relationship between energy consumption and value added in
agricultural sector: separately energy component, Scientific &
Research Quarterly Journal of Bank Keshavarzi,6: 157-171. (in
Persian)
18. Zhang, G., Patuwo B. E. and M. Y. Hu 1998, Forecasting With
Artificial Neural Network: The State of Art, International Journal
of Forecasting, 14: 35-62.
