Research on GA-SVM Model for Short Term Load Forecasting Based on LDM-PCA Technique

An integrated Genetic Algorithm (GA) based Support Vector Machine (SVM) model for short term load forecasting with input factors selection procession is presented in this paper. First, load distance method is used to for selecting main load influential factors which have more relevant to load parameter. Next, principal component analysis (PCA) technique is used to diminish the correlations among the selected factors without loss most information by looking for several linear combinations of selected ones, thus getting effective input variables set. Then GA based SVM forecasting model is established, whose parameters were optimized through genetic algorithms. Finally, the hybrid GA-SVM model was tested by using practical load data, which provided satisfactory forecasting results.