基于小波分析的短期电力负荷组合预测方法

为了提高电力系统短期负荷预测的精度,提出了基于小波分析的人工神经网络(ANN)和累积式自回归滑动平均(ARIMA)模型的组合预测方法。针对电力系统负荷具有拟周期性、非平稳性和非线性的特点,首先利用小波变换对负荷序列进行小波分解与单支重构,得到各频段上的近似序列和细节序列。根据各序列的自身特点,将经奇异性检测后的数据分别采用相匹配的BP模型和ARIMA模型进行预测,最后将各负荷序列的预测结果加以组合得到最终的预测结果。经实际算例验证,该方法能够有效地提高预测精度。

A method of combination forecast for short-term power load based on wavelet analysis

In order to improve the forecast precision of short-term load for power system, a combinatorial forecast method based on wavelet analysis using Artificial Neural Network (ANN) and Auto Regressive Integrated Moving Average (ARIMA) models is presented in this paper. Aiming at the characteristic of quasi-periodicity,non-stationary and non-linear owned by load in power system, firstly, the load sequence is decomposed by wavelet transform and reconstructed respectively, the approximate sequence and the detail sequence in different frequency are obtained. After the fantastic property of data is detected, according to the trait the sub-sequences are forecasted by the suited BP and ARIMA models respectively. Finally, the forecasted results of the sub-sequences are reconstructed and considered as the final forecasted result. A practical example is used to test the proposed method, the results show that the proposed method can improve the accuracy of forecasting efficiently.