基于小波支持向量回归的电力系统负荷预测

Power Load Foresting Based on Wavelet Support Vector Regression

根据混沌动力系统的相空间延迟坐标重构理论,基于支持向量回归强大的非线性映射能力和小波核函数的局部分析和特征提取能力,提出一种基于小波支持向量回归的电力系统负荷预测模型,并采用最小二乘方法来训练该预测模型,利用该模型对嵌入维数与模型预测性能的关系进行探讨。仿真结果表明,该预测模型能精确地预测电力系统负荷,而且在电力系统负荷的最佳嵌入维数未知时也能取得比较好的预测效果。

Based on the powerful nonlinear mapping ability of support vector regression and the ability of wavelet kernel in analyzing locally and extracting characteristic features from time series, the power load forecasting model of wavelet support vector regression in combination with Takensr delay coordinate phase reconstruction of chaotic time series is proposed, and from the statistical learning theory, the least squares method is used to train this model. Moreover, using this model, relationships between the embedding dimension and Mean - Square - Error of this model are discussed. Simulations show that the wavelet support vector regression can predict power load accurately, and even if the embedding dimension is unknown, the predicted results are satisfied.