Applying principal component analysis and weighted support vector machine in building cooling load forecasting

Abstract

In order to predict blended coal's property accurately, a new kind of hybrid prediction model based on principal component analysis (PCA) and weighted support vector machine (WSVM) was established. PCA was used to transform the high-dimensional and correlative influencing factors data to low-dimensional principal component subspace. These new features are then used as the inputs of WSVM to solve the load forecasting problem. The theoretical analysis and the simulation results show that PCA can efficiently extract the nonlinear feature of initial data. PCA-WSVM has powerful learning ability, good generalization ability and low dependency on sample data compared single SVR and PCA-SVM. It also indicates that the integration of PCA and WSVM forecast cooling load effectively and can be used in building cooling load prediction.