Prediction of Petroleum Demand Based on SVM Optimized by PSO

Accurate prediction of petroleum demand is very important to work out the plan of oil production and import,arrange production planning of relevant industry,and adjust the industrial structure.In order to predict petroleum demand accurately,the support vector machine optimized by particle swarm optimization algorithm(PSO-SVM) is proposed to predict petroleum demand in the paper.In the model,particle swarm optimization algorithm is used to determine training parameters of support vector machine,and gain the optimized SVM forecasting model.The petroleum demand data in China from 1990 to 2007 are used to testify and analyze the performance of the proposed model.The experimental results show that the PSO-SVM model has greater prediction accuracy than BP neural network does.