基于改进Cao算法的SSA与误差修正的超短期风电功率预测  

Ultra-short-term wind power forecasting through improved Cao algorithm for SSA and error correction

作　　者：张开伟 文中[1] 杨生鹏 胡梓涵 丁剑 Zhang Kaiwei;Wen Zhong;Yang Shengpeng;Hu Zihan;Ding Jian(School of Electrical and New Energy,Three Gorges University,Yichang 443002,China;Shanghai Survey and Design Institute Co.,Ltd.,Shanghai 200434,China)

机构地区：[1]三峡大学电气与新能源学院,宜昌443002 [2]上海勘测设计研究院有限公司,上海200434

出　　处：《国外电子测量技术》2024年第8期37-46,共10页Foreign Electronic Measurement Technology

基　　金：国家自然科学基金(52107108)项目资助。

摘　　要：针对风电历史信息运用不充分和未充分挖掘机器学习模型潜力的问题,提出一种特征奇异谱分析和模型误差修正的超短期功率预测。首先,利用随机森林分析不同特征对输出功率的影响程度,并利用累积贡献率进行特征提取。其次,通过改进的Cao算法确定奇异谱分析最佳嵌入维数,对提取的特征实现降噪处理,从而构建风电功率预测模型。最后,利用预测值与真实值的误差构建误差预测模型,通过预测的误差来修正功率预测的结果。以国内某小型风电场算例结果表明,所提方法较卷积神经网络-长短期记忆(CNN-LSTM)预测模型均方根误差(RSME)和均方误差(MSE)分别降低45%和53%,验证了所提模型的有效性。In order to address the issues of underutilization of historical wind power information and insufficient expLoRation of the potential of machine learning models,a method for ultra-short-term wind power forecasting has been proposed.This method is based on feature singularity spectrum analysis and model error compensation.Firstly,random forest is used to analyze the influence of different features on the output power,and the cumulative contribution rate is used to extract the features.Secondly,by improving the Cao algorithm,the optimal embedding dimension for singular spectrum analysis is determined.The extracted features are denoised and a wind power prediction model is constructed based on the denoised data.Finally,the error prediction model is constructed by using the error between the predicted value and the real value,and the result of power prediction is corrected by the predicted error.The results from a small wind farm in China confirm that the proposed method reduced RSME and MSE by 45%and 53%compared to CNN-LSTM,thus verifying its effectiveness.

关 键 词：奇异谱分析 超短期功率预测 随机森林 累积贡献率 Cao算法 误差修正 

分 类 号：TN2[电子电信—物理电子学]