摘要
针对短期风电功率预测,提出一种基于经验小波变换(Empirical Wavelet Transform,EWT)预处理的核极限学习机(Extreme Learning Machine With Kernels,KELM)组合预测方法。首先采用EWT对风电场实测风速数据进行自适应分解并提取具有傅立叶紧支撑的模态信号分量,针对每个分量分别构建KELM预测模型,最后对各个预测模型的输出进行叠加得到风速预测值并根据风电场风功特性曲线可得对应风电功率预测值,为验证本文方法的有效性,将其应用于国内某风电场的短期风电功率预测中,在同等条件下,与KELM方法、极限学习机(Extreme Learning Machine,ELM)方法、支持向量机(Support Vector Mmachine,SVM)方法以及BP (Back Propagation Neural Network)方法对比,实验结果表明,本文所提方法具有较好的预测精度和应用潜力。
Aiming at short-term wind power forecasting,a kind of combining forecasting method for short-term wind power based on empirical wavelet transform(EWT)and extreme learning machine with kernels(KELM)is proposed in this paper.Firstly,the EWT method is used to decompose the wind speed data and extract the different modes which have a compact support Fourier spectrum.Secondly,different KELM forecasting models are constructed for the sub-sequences formed by the each mode component.Simultaneously,the ultimate wind speed forecasting results can be obtained by the superposition of the corresponding forecasting model,the forecast value of wind power is calculated by the wind power characteristic curve.In order to verify the effectiveness of the proposed methods,it is applied to some wind farms in China for short-term wind power forecasting.The experiments are also implemented in the ELM method,KELM method,SVM method and BP method in the same condition respectively.The comparing experimental results show that the proposed method has higher forecasting accuracy and superior application potential.
作者
卓泽赢
曹茜
李青
Zhuo Zeying;Cao Qian;Li Qing(Urumqi Power Supply Company of State Grid Xinjiang Electric Power Co.,Ltd.,Urumqi 830001,China;Economics and Technology Research Institute of State Grid Xinjiang Electric Power Co.,Ltd.,Urumqi 830001,China;Electric Power Research Institute of State Grid Xinjiang Electric Power Co.,Ltd.,Urumqi 830001,China)
出处
《电测与仪表》
北大核心
2019年第2期83-89,96,共8页
Electrical Measurement & Instrumentation
关键词
经验小波变换
核极限学习机
组合预测
风电功率
风速-功率特性曲线
empirical wavelet transform
extreme learning machine with kernels
combined forecasting
wind power
wind speed-power characteristic curve