基于改进EMD与SVM的风电功率短期预测模型

发布时间：2018-03-05 23:05

本文选题：风电功率　切入点：预测　出处：《控制工程》2014年06期 　论文类型：期刊论文

【摘要】：风电功率短期预测对电力系统的调度运行有着重要意义。为提高风电功率短期预测的精度,构建基于改进的经验模态分解法(EMD)和支持向量机(SVM)相结合的预测模型,进行风电功率的短期预测。首先,采用镜像延拓算法对预处理后的功率序列进行处理,从而抑制经验模态分解法分解过程中的端点效应;同时,采用分段三次埃尔米特插值代替三次样条插值,由此得到的包络线可以有效改进EMD的欠冲或过冲问题;然后用改进后的EMD方法将风电功率序列分解成不同的分量,再针对各分量分别构建各自的SVM模型进行预测,最后将各预测分量进行叠加,由此得到总的风电功率预测值。实验结果表明,相比与其他的短期功率预测模型,改进的EMD-SVM预测模型具有更高的预测精度,具有一定的应用价值。
[Abstract]:Short-term prediction of wind power is of great significance to the dispatching operation of power system. In order to improve the accuracy of short-term prediction of wind power, a prediction model based on improved empirical mode decomposition (EMD) and support vector machine (SVM) is constructed. First of all, the image continuation algorithm is used to process the pretreated power series, so as to suppress the endpoint effect in the decomposition process of empirical mode decomposition (EMD), at the same time, By using piecewise cubic Hermitian interpolation instead of cubic spline interpolation, the envelope obtained from this method can effectively improve the underimpulse or overshoot problem of EMD, and then decompose the wind power sequence into different components by using the improved EMD method. Then the SVM models are constructed for each component, and the predicted components are superimposed to obtain the total wind power prediction value. The experimental results show that compared with other short-term power prediction models, The improved EMD-SVM prediction model has higher prediction accuracy and has certain application value.
【作者单位】：上海电机学院电气学院;华东理工大学信息科学与工程学院;
【基金】：上海市教委重点学科(J51901) 上海市教委科研创新项目(13YZ140) 上海市自然科学基金项目(11ZR1413900)
【分类号】：TM614

【参考文献】