support vector regression (svr)

Accurate monthly power demand network forecasting can help to plan the energy and it can handle the correct management of the power consumption. It has been found that the monthly electricity consumption demonstrates a complex nonlinear characteristic and has an obvious seasonal tendency. One of the models that is widely used to predict the nonlinear time series is the support vector regression model (SVR) in which the selection of key parameters and the effect of seasonal changes could be considered. The important issues in this research are to determine the parameters of the support vector regression model optimally, as well as the adjustment of the nonlinear and seasonal trends of the electricity data. The method that is proposed by this study is to hybrid the support vector regression model (SVR) with Fruit fly optimization Algorithm (FOA) and the seasonal index adjustment to forecast the monthly power demand. In addition, in order to evaluate the performance of the hybrid predictive model a small sample of the monthly power demand from Iran and a large sample of Iran monthly electricity production has been used to demonstrate the predictive model performance. This study also evaluates the superiority of the SFOASVR model to the other known predictive methods. In terms of the prediction accuracy, we used the evaluation criteria such as Root Mean Square Error (RMSE) and mean absolute percentage error (MAPE) as well as Wilcoxon's nonparametric statistical test. The results show that the SFOASVR model has less error than the other forecasting models and is superior to the most other models in terms of Wilcoxon test. Therefore, SFOASVR method is an appropriate option for prediction of the power demand.