小波包变换在冲击负荷地区短期负荷预测中的应用

Application of Wavelet Packet Transform in Short Term Load Forecasting of Impact Load Area

针对大量冲击负荷接入系统给负荷预测造成困难,提出一种基于小波包变换的电力系统短期负荷预测新方法:通过小波包分解将原始负荷序列分解成不同频率的子序列,根据各个子序列的变化特点,分别采用相匹配的模型进行预测,最后叠加各子序列的预测值,得出实际预测结果。选择广东某电网实测负荷数据作为算例,仿真结果表明该方法能有效提高冲击负荷地区的短期负荷预测精度。

Facing the difficulties caused by a large number of random impact loads access systems for load forecasting,this paper proposes a new method based on wavelet packet transform for short term load prediction：decomposing the load sequence into load sub-sequences under different band by wavelet packet transform,adopting matched models to make prediction according to different features of load subsequences, superposing all sequences forecasting outputs to obtain the final forecasted results. At the end,a power system in Guangdong is chosen to be the case,the resuits show that this method can improve the short term load forecasting accuracy for impact load area.