A PSO based NN-SVM for short-term load forecasting

Load forecasting has become one of the core research topics in the power system. As power load has time-variant characteristics and nonlinear characteristics, different computational intelligent techniques, neural networks (NN) in particular, are used in short-term load forecasting (STLF) to make it more effective. This study proposes a Particle Swarm Optimization (PSO) - based neural network with support vector machine (NN-SVM) model to predict the power load in short-term forecasting by using a radial-basis-function neural network (RBFNN), SVM and PSO. There are two stages in the proposed model. The first stage applies the RBFNN to predict monthly variations, and the second stage trains the SVM through hourly data to obtain the final forecast for short-term load forecasting (STLF). In the process of SVM training and NN learning, PSO is used to find the optimal parameters. The results of several experiments show that this new model performs more accurately and stably than some conventional models including RBFNN, RGA-SVM, Karman filter in STLF.