The problem of power load market forecasting is studied and analyzed, and a new method of power load market forecasting is advanced in this paper. Counter to the characteristic of high nonlinear and high noise of stock time series, the noise is efficiently filtered and the reduction in the data performed by means of. LS-SVM model and BP neural network model are studied and analyzed, and the fuzz change weight combination prediction model based on the forecasting model of LS-SVM and BP neural network is introduced. The model is used to forecast power load time series and satisfactory effect is acquired.
展开▼