Wv-SVM with genetic algorithms for gas load forecasting

Accurate short-term load forecasting is important in regional or national gas pipeline network system strategy management. Gas load forecasting is complex to conduct due to its nonlinearity of influenced factors. Support vector machines (SVM) has been successfully employed to solve nonlinear regression and time series problems, however, the application for load forecasting is rare. The purpose of this paper is to present a wavelet v-SVM with genetic algorithm (GA) to forecast the gas loads. GA is applied to the parameter determine of Wv-SVM model. The empirical results reveal that the proposed model outperforms the artificial neural network (ANN), Wv- SVM models.