基于多尺度分析的电力月负荷预测

介绍了小波分析原理及多尺度分析法。根据月度负荷的增长和波动趋势，利用多尺度分析法将月度负荷序列进行分解，采用灰色理论法和神经网络法对序列进行预测，建立了优化预测模型，该模型优于只考虑单一发展趋势的负荷预测模型。计算结果表明，该方法可以明显提高月度负荷预测的精度。

Forecasting for power system monthly load based on multi-resolution analysis

This paper introduces the wavelet theory and multi-resolution analysis method.Multi-resolution analysis is applied to decompose monthly load according to the character and duality of increment and fluctuation of monthly load.GM(1,1) theory and neural network are used for forecasting,an optimal integrated forecasting model built up,in which the modeling features of above-mentioned two models were considered simultaneously,and the built forecasting model is better than the load forecasting models based on single load variation trend.The case calculation results show that the proposed method can remarkably improve the accuracy of monthly load forecasting.