Research on Power Load Forecasting Base on Support Vector Machines

Research on power load forecasting base on support vector machines is an important problem.In order to improve the forecasting performance of support vector machines and to forecast the power load more accurately,a new method for exchange rate time series forecasting was proposed,in which particle swarm optimization is used to determine free parameters of support vector machines.PSO is an intelligent swarm optimization method,which derives from the research for behavior of bird flocking.The method not only has strong global search capability,but also is very easy to implement.Thus,particle swarm optimization is suitable to determine the parameters of support vector machine.The power load data from 2008.7 to 2009.7 of Guizhou are used to testify and analyze the performance of the proposed model.The result shows that SVM based on particle swarm has both fast training speed and small number of errors.The forecast precision has also been significantly improved,thus proving the validity of this model for power load forecasting.