Short-Term Load Forecasting Approach Based on RS and PSO Support Vector Machine

Utilizing the advantages of RS (rough set) theory in processing large data and eliminating redundant information, the enormous historic data of power load were pre-conducted. Then the training data for the SVM (support vector machine) were reduced. Next, the PSO(particle swarm optimization) is used to optimize the parameter of the SVM, the result is that the SVM has even more global optimization ability. Using this model for the load forecasting, the result showed that it is a precision and speedy forecasting model.