基于ECBO-VMD-WKELM的风电功率超短期多步预测  

Multi-step Ahead Ultra-short Term Forecasting of Wind Power Based on ECBO-VMD-WKELM

作　　者：李青 张新燕[1] 马天娇 马涛 王衡 尹红升 LI Qing;ZHANG Xinyan;MA Tianjiao;MA Tao;WANG Heng;YIN Hongsheng(Department of Electrical Engineering,Xinjiang University,Urumqi 830000,Xinjiang Uygur Autonomous Regions,China;Xinjiang Railway Vocational and Technical College,Urumqi 830000,Xinjiang Uygur Autonomous Regions,China;State Grid Xinjiang Electric Power Research Institute,Urumqi 830000,Xinjiang Uygur Autonomous Regions,China;State Grid Xinjiang Electric Power Co.,Ltd.,Urumqi 830000,Xinjiang Uygur Autonomous Regions,China)

机构地区：[1]新疆大学电气工程学院,新疆维吾尔自治区乌鲁木齐市830000 [2]新疆铁道职业技术学院,新疆维吾尔自治区乌鲁木齐市830000 [3]国网新疆电力有限公司电力科学研究院,新疆维吾尔自治区乌鲁木齐市830000 [4]国网新疆电力有限公司,新疆维吾尔自治区乌鲁木齐市830000

出　　处：《电网技术》2021年第8期3070-3078,共9页Power System Technology

基　　金：国家自然科学基金项目(51667018)。

摘　　要：提出一种全新的集合强化物体碰撞优化算法(enhanced colliding bodies optimization,ECBO)、变分模态分解(variational mode decomposition,VMD)、小波核极限学习机(wavelet kernel extreme learning machine,WKELM)的超短期风电功率多步预测模型。针对VMD方法自适应性低的问题,提出将ECBO方法用于VMD核心参数自动寻优,且基于加权排列熵(wavelet kernel extreme learning machine,WPE)算法思想来设计ECBO-VMD方法适应度函数,在提高VMD分解方法自适应性的同时实现了对各分解分量规律性的定量判别。采用ECBO-VMD对原始风电功率时间序列进行自适应分解,然后针对各分解分量建立WKELM预测模型并进行重构以得到最终预测结果。实验结果表明,该方法较现有单一及组合预测方法,多步预测精度均取得了大幅度提高,且预测误差分布可控制在较窄的期望预测区间内。A novel multi-step forecasting model of ultra-short term wind power based on the combination of the enhanced colliding bodies optimization(ECBO),the variational mode decomposition(VMD)and the wavelet kernel extreme learning machine(WKELM)is proposed.The ECBO algorithm is used to optimize the key parameters of the VMD,herein,a new fitness function is designed based on the idea of the weighted-permutation entropy(WPE),which not only improves the self adaptability of the VMD method,but also realizes the quantitative discrimination for the regularity of each decomposition component.First,the original wind power time series is decomposed by the ECBO-VMD adaptively,then the forecasting model based on the WKELM is established for each decomposition component,and the final forecasting results are obtained by reconstructing the forecasting value of each component.The experimental results confirm that the proposed method can significantly improve the multi-step forecasting accuracy compared with the existing single or combined forecasting methods,and the error distribution of the forecasting values can be controlled in a narrower expected forecasting range.

关 键 词：风电功率预测 强化物体碰撞优化 变分模态分解 小波核极限学习机 

分 类 号：TM614[电气工程—电力系统及自动化]