摘要
基于小波变换和神经网络,提出了一种电力系统短期负荷预测方法。通过小波变换把负荷序列分解为不同频段的子序列,再对这些子序列分别采用相应的人工神经网络模型进行预测,最后重构得到负荷序列的最终预测结果。在所提出的方法中小波分解能够提取负荷的一些周期性和非线性特征,根据其子序列各自所具有的特征采用相应的预测方法。实例结果表明该方法具有很高的预测精度和较强的适应能力。
An approach to short-time load forecasting （STLF） using artificial neural network and wavelet decomposition （WVNN） was proposed. Firstly, the load sequence was decomposed into sub-sequences on different scales by using the wavelet transform. Then, these sub-sequences were forecasted by appropriate artificial neural networks, respectively. Finally, the load forecasting sequence was obtained by the reconstruction of the forecasted results from the sub-sequences. The wavelet decomposition can extract some periodical and nonlinear features of the load, and corresponding forecasting method can be adopted according to the features of the sub-sequences, respectively. The simulation results show that the proposed method possesses high forecasting accuracy and adaptability.
出处
《系统仿真学报》
EI
CAS
CSCD
北大核心
2008年第18期5018-5020,共3页
Journal of System Simulation
基金
江苏省自然科学基金项目(BK2007210)
关键词
短期负荷
小波变换
人工神经网络
预测
short-term load
wavelet transform
artificial neural network （ANN）
forecasting
作者简介
向峥崃（1969-），男，江苏南京人，博士，副教授，研究方向为非线性系统，智能控制，数据挖掘等；
王学平（1982-）,男，安徽马鞍山人，硕士生，研究方向为数据建模与预报。
