电力系统短期负荷预测的级联网络模型研究

提出一种基于BP子网络和小波网络的短期负荷预测的级联网络模型。在对气象影响因素与负荷关系深入分析的基础上,采用BP子网络来映射气象等不确定因素的影响。采用小波网络(预测网络)来映射历史负荷值的影响,它结合了小波变换良好的时频局域化性质和神经网络的自学习能力,明显地改善了神经网络难以合理确定网络结构和存在局部最优等缺陷。最后两级网络相互级联组成预测网络。研究算例表明,这种模型是优秀的。

Research on cascaded network model for short-term load forecasting in power system

This paper proposes a cascaded network model based on BP sub-network and WNN(wavelet neural network) for short-term load forecasting. The influence of uncertaint factors such as climate is mapped through BP sub-network based on the analysis of the relationship between the climatic factor and load data. Since WNN combines the time-frequency localization characteristic of wavelet and its self-learning ability, the influence of historical data is mapped through WNN, which helps to overcome the defects of ANN such as the difficulty of rationally determining the network structure and the existence of partial optimal points. Finally, the two sub-networks are combined to form the cascaded forecasting network. The results of the experimental research show that this method is superior.