Artificial Neural Networks and regression approaches comparison for forecasting Iran's annual electricity load

Electrical load forecasting is one of the important concerns of power systems and has been studied from different views. Electrical load forecast might be performed over different time intervals of short, medium and long term. Various techniques have been proposed for short term, medium term or long term load forecasting. In this study we employ Artificial Neural Networks (ANN) and regression (Linear and Log-Linear) approaches for annual electricity load forecasting. This study presents a model that is affected by two economical parameters which are Real-GDP and Population. Using Real-GDP instead of nominal-GDP can provide more accuracy because the effects of inflation are considered in the structure of such model and this will cause the results to be more reliable. To improve forecasting accuracy of the model we apply data preprocessing techniques. Forecasting capability of each approach is evaluated by calculating three separate statistical evaluations of the Root Mean Square Error (RMSE), the Mean Absolute Error (MAE), and the Mean Absolute Percentage Error (MAPE). All evaluations indicate that the accuracy of ANN which is trained with preprocessed data is remarkably better than the other two conventional approaches.

[1]  H. Stoll.  Least-Cost Electric Utility Planning , 1989 .

[2]  Mehrzad Zamani,et al.  Energy consumption and economic activities in Iran , 2007 .

[3]  Ali Azadeh,et al.  Forecasting electrical consumption by integration of Neural Network, time series and ANOVA , 2007, Appl. Math. Comput..

[4]  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.

[5]  H Lee Willis,et al.  Power distribution planning reference book , 2000 .

[6]  A. Hainoun,et al.  Analysis of the Syrian long-term energy and electricity demand projection using the end-use methodology , 2006 .

[7]  Chi-Chung Chen,et al.  The relationship between GDP and electricity consumption in 10 Asian countries , 2007 .

[8]  Philippe De Wilde.  Neural Network Models: An Analysis , 1995 .

[9]  Paul A. Steenhof,et al.  Factors affecting electricity generation in China: Current situation and prospects , 2007 .

[10]  Matteo Manera,et al.  Modelling the Load Curve of Aggregate Electricity Consumption Using Principal Components , 2003, Environ. Model. Softw..

[11]  Kelvin K. W. Yau,et al.  Predicting electricity energy consumption: A comparison of regression analysis, decision tree and neural networks , 2007 .

[12]  Philippe De Wilde.  Neural Networks Models , 1996 .

[13]  T. Yalcinoz,et al.  Short term and medium term power distribution load forecasting by neural networks , 2005 .

[14]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[15]  H. Pao.  Comparing linear and nonlinear forecasts for Taiwan's electricity consumption , 2006 .

[16]  Timothy Masters,et al.  Practical neural network recipes in C , 1993 .

[17]  T. Senjyu,et al.  Neural networks approach to forecast several hour ahead electricity prices and loads in deregulated market , 2006 .

[18]  Azam Beg,et al.  Investigating data preprocessing methods for circuit complexity models , 2009, Expert Syst. Appl..