Electric energy consumption forecasting via expression-driven approach

This study deals with estimation of the electricity demand of Iran on the basis of economic criteria using a genetic-based approach called Gene Expression Programming (GEP) as an expression-driven approach. The GEP-based mathematical model is provided based on population, gross domestic product, exports, and imports. The proposed model is derived based on available real data of 21 years (1992-2006). To validate the model in prediction, the electricity demand from 2007 until 2012 was calculated by the GEP driven model. The result was compared with the real demand during this period. To show the accuracy of the model, the result obtained by GEP model is compared with the results obtained from Multi-Layer Perceptron (MLP) neural network and Multiple Linear Regression (MLR) as the two conventional methods. In addition, a five-fold cross-validation and future year prediction (the data related to the year 2013 as the blind or unseen dataset) were used to show the robustness of the model in predicting the electricity demand. Finally, a sensitivity analysis was conducted to identify the important independent variables affecting electricity demand.