基于稀疏核偏最小二乘法的短期负荷预测研究

Study on short-termload forecasting based on sparse kernel partialaleast squares

支持向量机方法已成功地应用在负荷预测领域,但它在训练数据时存在数据处理量太大、处理速度慢等缺点。为此提出了一种基于稀疏核偏最小二乘法的预测方法,通过在高维特征空间的稀疏化,可减少在训练过程中的数据量,从而提高预测的速度和精度,将该方法应用于短期负荷预测中,与SVM方法相比,得到了较高的预测精度。

The support vector machine （SVM） has been successfully applied to the load forecasting area, but it has some disadvantages of very large data amount and slow processing speed. A better method of sparse kernel partial least squares was protmsed, the data amount is decreased in the training process by sparse in high dimension feature space, and the processing speed was improved. The simulation result shows that the algorithm has a better forecasting accuracy compared with the method of SVM.