摘要
在分析电力负荷频谱特性时发现负荷信号的变化过程具有连续频谱的特性。该文在此基础上提出一种基于小波变换的电力系统短期负荷预测新方法:通过小波变换,将各序列分量分别投影到不同的尺度上,对不同的子负荷序列进行数据处理,并分别采用相匹配的模型进行预测,最后通过小波重构,得到完整的负荷预测结果。算例计算表明新方法具有较高的预测精度和较强的适应能力。
Analysing the frequency characteristics of the power load , a new method for the short-term load forecasting is presented based on the wavelet transform (WT), particularly the multiresolution analysis technique. By the WT, the different load sequence components are projected to the different scales in which the matching forecast methods can be used. The forecasting results are then obtained by the reconstruction of the forecast results in different scales. Simulation results demonstrate that the proposed method can offer higher forecast precision.
出处
《中国电机工程学报》
EI
CSCD
北大核心
2003年第1期45-50,共6页
Proceedings of the CSEE
基金
中国博士后基金项目。
