基于总体平均经验模态分解与改进Elman神经网络的风功率组合预测

发布时间：2018-03-15 00:14

本文选题：风功率预测　切入点：EEMD　出处：《电网与清洁能源》2015年10期 　论文类型：期刊论文

【摘要】：风功率的短期预测对于电力系统的安全稳定运行具有重要意义。提出了一种基于总体平均经验模态分解(EEMD)和改进Elman神经网络的短期风功率组合预测方法。首先利用EEMD分解将风功率序列按不同波动尺度逐级分解,得到不同频率的分量以缓解风功率序列的非平稳性,然后对各分量分别建立改进的Elman神经网络预测模型进行预测,最后叠加各分量的预测结果得到最终预测数据。仿真结果表明,该方法不仅可以有效缓解风功率非平稳性对于预测精度的影响,还可以避免传统方法的模态混叠问题,具有较高的预测精度和适应性。
[Abstract]:Short-term wind power prediction is of great significance for the safe and stable operation of power system. A short-term wind power combination forecasting method based on the total average empirical mode decomposition (EEMD) and improved Elman neural network is proposed. The wind power series is decomposed according to different wave scales by EEMD decomposition. The components of different frequencies are obtained to alleviate the non-stationarity of wind power series, and then the improved Elman neural network prediction model is established for each component to predict the nonstationarity of the wind power series. The simulation results show that the proposed method can not only effectively mitigate the influence of non-stationary wind power on the prediction accuracy, but also avoid the modal aliasing problem of traditional methods. It has high prediction accuracy and adaptability.
【作者单位】：湖北省微电网工程技术研究中心(三峡大学);甘肃省电力科学研究院;
【基金】：国家自然科学基金项目(51207113)~~
【分类号】：TM614;TP183

【共引文献】