Application of Least Squares Support Vector Machine(LS-SVM) Based on Time Series in Power System Monthly Load Forecasting

A new methodology base on Least Squares Support Vector Machine (LS-SVM) for the electric power system monthly load forecasting is presented. The presented algorithm embodies the the structural risk minimization(SRM) principle is more generalized performance and accurate as compared to artificial neural network. In the time series the trend component and periodical component are considered to make the load forecasting model more coincident with the features of power loads. Applying the LS-SVM method based on time series to actual load forecasting, the comparison among the forecasted results and the true shows that the presented method is feasible and effective.