基于OVMD-SSA-DELM-GM模型的超短期风电功率预测方法  

Ultra-short-term Wind Power Prediction Based on OVMD-SSA-DELM-GM Model

作　　者：曾亮 雷舒敏[1,3] 王珊珊 常雨芳 ZENG Liang;LEI Shumin;WANG Shanshan;CHANG Yufang(School of Electrical and Electronic Engineering,Hubei University of Technology,Wuhan 430068,Hubei Province,China;Engineering Research Center for Metallurgical Automation and Measurement Technology(Wuhan University of Science and Technology),Ministry of Education,Wuhan 430081,Hubei Province,China;Hubei Key Laboratory for High-efficiency Utilization of Solar Energy and Operation Control of Energy Storage System(Hubei University of Technology),Wuhan 430068,Hubei Province,China)

机构地区：[1]湖北工业大学电气与电子工程学院,湖北省武汉市430068 [2]冶金自动化与检测技术教育部工程研究中心(武汉科技大学),湖北省武汉市430081 [3]太阳能高效利用及储能运行控制湖北省重点实验室(湖北工业大学),湖北省武汉市430068

出　　处：《电网技术》2021年第12期4701-4710,共10页Power System Technology

基　　金：国家自然科学基金项目(51977061,61903129);湖北省重点研发计划项目(2020BAB114);武汉科技大学冶金自动化与检测技术教育部工程研究中心开放基金项目(MADTOF2020B0)。

摘　　要：为了提高风电功率的预测精度,提出了一种基于最优变分模态分解(optimal variational model decomposition,OVMD)、麻雀算法(sparrow search algorithm,SSA)、深度极限学习机(deep extreme learning machine,DELM)和灰色模型(grey model,GM)的超短期风电功率预测方法。该方法通过OVMD对原始风电功率时间序列进行自适应分解;然后针对各分量建立DELM预测模型并利用SSA算法进行参数寻优,并对各个分量的预测结果进行求和重构;利用GM对误差序列进行预测;最后将误差的预测值与原始风电功率的预测值叠加得到最终预测结果。对北方某风电场的风电功率数据进行仿真实验,结果表明,该方法预测效果明显优于传统方法,有效提高了超短期风电功率预测的精确性。In order to improve the prediction accuracy of wind power,a forecasting method of ultra-short-term wind power based on the optimal variational modal decomposition(OVMD),the sparrow algorithm(SSA),the deep extreme learning machine(DELM)and the grey model(GM)is proposed.In this study,the original wind power time series is decomposed by the optimal variational modal decomposition.Then the forecasting model based on the DELM,which is optimized by the SSA algorithm,is established for the forecasting results of each of the decomposition components to be summed and reconstructed.Next the prediction error is compensated with the grey model.Finally,the predicted value of the error is superimposed on the predicted value of original power to obtain the final prediction result.A simulation experiment results on the wind power data of a wind farm in the north of China show that the proposed method is better than the traditional method,effectively improving the accuracy of ultra-short-term wind power prediction.

关 键 词：超短期风电功率预测 最优变分模态分解 深度极限学习机 麻雀算法 灰色模型 

分 类 号：TM614[电气工程—电力系统及自动化]