Grid Resources Prediction with Support Vector Regression and Particle Swarm Optimization

Accurate grid resources prediction is crucial for a grid scheduler. In this study, support vector regression (SVR), which is an effective regression algorithm, is applied to grid resource prediction. In order to obtain better prediction performance, SVR´s parameters must be selected carefully. Therefore, a particle swarm optimization-based SVR (PSO-SVR) model, in which PSO is used to determine free parameters of SVR, is presented in this study. The hybrid model (PSO-SVR) can automatically determine the parameters of SVR with higher predictive accuracy and generalization ability simultaneously. The performance of PSO-SVR, the back-propagation neural network (BPNN) and the traditional SVR model whose parameters are obtained by trail-and-error procedure (T-SVR) have been compared with benchmark data set. Experimental results indicate that the PSO-SVR model can achieve higher predictive accuracy than the other two models.