Electric load forecasting based on improved LS-SVM algorithm

摘要

An Improved least squares support vector machine (LS-SVM) algorithm is proposed for 24 points electric load forecasting. First of all, facing with the problem how to choose the optimal LS-SVM algorithm parameters, an improved LS-SVM algorithm based on chaos optimization is put forward to obtain the optimal LS-SVM algorithm parameters and corresponding model parameters. Then, a method of 24 points electric load forecasting based on the improved LS-SVM algorithm is presented, which makes 24 points forecasting models respectively. Compared with the RBF neural network method, the prediction accuracy of the proposed method is better than that of neural network method, so the validity and the superiority of the proposed method are proved.