Forecasting Electricity Demand in Thailand with an Artificial Neural Network Approach

Demand planning for electricity consumption is a key success factor for the development of any countries. However, this can only be achieved if the demand is forecasted accurately. In this research, different forecasting methods—autoregressive integrated moving average (ARIMA), artificial neural network (ANN) and multiple linear regression (MLR)—were utilized to formulate prediction models of the electricity demand in Thailand. The objective was to compare the performance of these three approaches and the empirical data used in this study was the historical data regarding the electricity demand (population, gross domestic product: GDP, stock index, revenue from exporting industrial products and electricity consumption) in Thailand from 1986 to 2010. The results showed that the ANN model reduced the mean absolute percentage error (MAPE) to 0.996%, while those of ARIMA and MLR were 2.80981 and 3.2604527%, respectively. Based on these error measures, the results indicated that the ANN approach outperformed the ARIMA and MLR methods in this scenario. However, the paired test indicated that there was no significant difference among these methods at α = 0.05. According to the principle of parsimony, the ARIMA and MLR models might be preferable to the ANN one because of their simple structure and competitive performance

[1]  P. Young,et al.  Time series analysis, forecasting and control , 1972, IEEE Transactions on Automatic Control.

[2]  Douglas C. Montgomery,et al.  Integrating Statistical Process Control and Engineering Process Control , 1994 .

[3]  Chuin-Shan Chen,et al.  Customer short term load forecasting by using ARIMA transfer function model , 1995, Proceedings 1995 International Conference on Energy Management and Power Delivery EMPD '95.

[4]  S. J. Kiartzis,et al.  A neural network short term load forecasting model for the Greek power system , 1996 .

[5]  A. Al-Garni,et al.  Forecasting monthly electric energy consumption in eastern Saudi Arabia using univariate time-series analysis , 1997 .

[6]  Frederick W. Faltin,et al.  Statistical Control by Monitoring and Feedback Adjustment , 1999, Technometrics.

[7]  Chia-Yon Chen,et al.  Regional load forecasting in Taiwanapplications of artificial neural networks , 2003 .

[8]  P. Bodger,et al.  Forecasting electricity consumption in New Zealand using economic and demographic variables , 2005 .

[9]  B. W. Ang,et al.  A trigonometric grey prediction approach to forecasting electricity demand , 2006 .

[10]  S. F. Ghaderi,et al.  Integration of Artificial Neural Networks and Genetic Algorithm to Predict Electrical Energy consumption , 2006, IECON 2006 - 32nd Annual Conference on IEEE Industrial Electronics.

[11]  V. Ediger,et al.  ARIMA forecasting of primary energy demand by fuel in Turkey , 2007 .

[12]  V. Mendes,et al.  Short-term electricity prices forecasting in a competitive market: A neural network approach , 2007 .

[13]  Ali Azadeh,et al.  A simulated-based neural network algorithm for forecasting electrical energy consumption in Iran , 2008 .

[14]  Lambros Ekonomou,et al.  Electricity demand loads modeling using AutoRegressive Moving Average (ARMA) models , 2008 .

[15]  Wei-Chiang Hong,et al.  Electric load forecasting by support vector model , 2009 .

[16]  Lambros Ekonomou,et al.  Greek long-term energy consumption prediction using artificial neural networks , 2010 .