摘要
提出了基于总体平均经验模态分解(EEMD)、最小二乘支持向量机(LSSVM)和BP神经网络的实用综合短期负荷预测方法,进行电力系统短期负荷预测.首先运用EEMD方法将非平稳的负荷序列分解,然后根据分解后各分量的特点选用最佳的核函数,利用最小二乘支持向量机分别对各分量进行预测,最后对各分量预测结果采用BP神经网络重构得到最终的预测结果.对实测数据的分析表明基于该综合方法的电力系统短期负荷预测具有较高的精度.
This paper proposes a hybrid model based on Ensemble Empirical Mode Decomposition (EEMD),least square-support and BP nature network as a short-term load forecasting model.At first,based on EEMD the load series is decomposed into different lots of calm series; then according to the change regulation of each "of all resulted intrinsic mode functions, the right parameter and kernel functions are chosen to build different LS-SVM respectively to forecast each intrinsic mode functions.Finally,using the BP network,to reconstruct the forecasted signals of the components and obtain the ultimate forecasting result.Simulink results show that the proposed forecasting method possesses accuracy.
出处
《数学的实践与认识》
CSCD
北大核心
2012年第8期151-158,共8页
Mathematics in Practice and Theory
关键词
短期负荷预测
总体平均经验模态分解
最小二乘支持向量机
BP神经网
short-term load forecasting
ensemble empirical mode decomposition(EEMD)
least square-support vector machine(LS-SVM)
BP neural network