Integration of Artificial Neural Networks and Genetic Algorithm to Predict Electrical Energy Consumption in Energy Intensive Sector

This study presents an integrated genetic algorithm (GA) and artificial neural network (ANN) to estimate and predict electricity demand using stochastic procedures. The considered sector is the energy intensive sector and the economic indicators used in this paper are price, value added, number of customers, price of the substitute fuel and electricity intensity. The chosen models are linear-logarithmic, exponential and quadratic ones. This model can be used to estimate energy demand in the future by optimizing parameter values. The GA applied in this study has been tuned for all its parameters and the best coefficients with minimum error are identified, while all parameter values are tested concurrently. The estimation errors of genetic algorithm models are less than that of estimated by regression method. Neural network is used to forecast each independent variable and then electricity consumption is forecasted up to year 2008 in this sector. It is pointed that neural networks dominate time series approach form the point of yielding less Mean Absolute Percentage Error (MAPE) error. In addition, another unique feature of this study is utilization of ANN instead of time series to obtain better predictions for energy consumption. Electricity consumption in Iranian energy intensive sector from 1981 to 2005 is considered as the case of this study