基于熵关联数据挖掘的MPSO-Elman风电功率预测
|
摘要
为进一步提高风电功率预测计算效率及准确性,建立基于熵关联数据挖掘的MPSO-Elman风电功率预测模型:在分析信息熵与互信息的熵相关系数(ECC)后,对各个历史日数据样本和待测时段参考样本间的复杂非线性映射关系进行量化评估,经过高关联度样本筛选,Elman模型隐含层结构优化以及权值初值选取改进,最后采用改进粒子群算法(MPSO)对网络参数进一步优化,并以某风电场实测数据为依据进行实例分析。结果表明,该模型使得功率预测准确度达到91.24%,预测效果要优于RBF-BP模型,证明了该模型的先进性与有效性。
In order to improve the prediction accuracy and the computational efficiency further,this paper establishes the MPSO-Elman wind power prediction model based on entropy association data mining.It adopts an index of entropy correlation coefficients(ECC) based on information entropy and mutual information to quantitatively evaluate the complex non-linear relationship between historical data samples and the data to be measured.After intimate-samples selection,Elman model′s hidden layer structure improvement and network weights choice,the network parameters are further optimized with MPSO.By analyzing the data of a wind farm in Jiangsu,the presented method has the power prediction accuracy of 91.24%,more accurate than the RBF-BP model,indicating its advancements and effectiveness.
In order to improve the prediction accuracy and the computational efficiency further,this paper establishes the MPSO-Elman wind power prediction model based on entropy association data mining.It adopts an index of entropy correlation coefficients(ECC) based on information entropy and mutual information to quantitatively evaluate the complex non-linear relationship between historical data samples and the data to be measured.After intimate-samples selection,Elman model′s hidden layer structure improvement and network weights choice,the network parameters are further optimized with MPSO.By analyzing the data of a wind farm in Jiangsu,the presented method has the power prediction accuracy of 91.24%,more accurate than the RBF-BP model,indicating its advancements and effectiveness.
引文
[1] 洪翠,林维明,温步瀛.风电场风速及风电功率预测方法研究综述[J].电网与清洁能源,2011,27(1):60-66.HONG Cui,LIN Wei-ming,WEN Bu-ying.Wind farm wind speed and wind power forecasting method research[J].Grid and Clean Energy,2011,27(1):60-66.
[2] LYDIA M,SURESH K S.A comprehensive overview on wind power forecasting[C]//9th International Power and Energy Conference,Singapore,2010,268-273.
[3] MU Gang,YANG Mao,WANG Dong,et al.Spatial dispersion of wind speeds and its influence on the forecasting error of wind power in a wind farm[J].Journal of Modern Power Systems and Clean Energy,2016,4(2):265-274.
[4] 丁志勇,杨苹,杨曦,等.基于连续时间段聚类的支持向量机风电功率预测方法[J].电力系统自动化,2012,36(14):131-135.DING Zhi-yong,YANG Ping,YANG Xi,et al.Wind power prediction method based on continuous time clustering of support vector machines [J].Power System Automation,2012,36(14):131-135.
[5] 张靠社,罗钊.基于RBF-BP组合神经网络的短期风电功率预测研究[J].可再生能源,2014,32(9):1346-1351.ZHANG Kao-she,LUO Zhao.Short-term wind power forecast based on RBF-BP combined neural network [J].Renewable Energy,2014,32(9):1346-1351.
[6] 叶小岭,刘波,邓华.基于小波分析和PSO优化神经网络的短期风电功率预测[J].可再生能源,2014,32(10):1486-1491.YE Xiao-ling,LIU Bo,DENG Hua.Short-term wind power prediction based on wavelet analysis and PSO optimization neural network [J].Renewable Energy,2014,32(10):1486-1491.
[7] 侯家利.Elman神经网络的网络流量预测[J].计算机仿真,2011,28(7):154-157.HOU Jia-li.Elman neural network network traffic prediction [J].Computer Simulation,2011,28(7):154-157.
[8] 周品.MATLAB神经网络设计与应用[M].北京:清华大学出版社,2013.ZHOU Pin.MATLAB neural network design and application[M].Beijing:Tsinghua University Press,2013.
[9] 张建方,王秀祥.直方图理论与最优直方图制作[J].应用概率统计,2009,25(2):201-214.ZHANG Jian-fang,Wang Xiu-xiang.Histogram theory and optimal histogram production[J].Applied probability statistics,2009,25(2):201-214.
[10] 龚伟.基于信息熵和互信息的流域水文模型不确定性分析[D].北京:清华大学,2012.GONG Wei.Uncertainty analysis of watershed hydrological model based on information entropy and mutual information[D].Beijing:Tsinghua University,2012.
[11] 丁晶,王文圣,赵永龙.以互信息为基础的广义相关系数[J].四川大学学报(工程科学版),2013,34(3):1-5.DING Jing,WANG Wen-sheng,ZHAO Yong-long.Generalized correlation coefficient based on mutual information [J].Journal of Sichuan University (Engineering Science Edition),2013,34(3):1-5.
[12] 张学文.组成论[M].北京:中国科学技术大学出版社,2003.ZHANG Xue-wen.Composition theory[M].Beijing:University of Science and Technology of China Press,2003.
[13] LIANG Fa-ming.Bayesian neural networks for nonlinear time series forecasting[J].Statistics and Computing,2005,15(1):13-29.
[14] 干旭波,姚栋伟,吴锋,等.基于PSO算法的SCR尿素热解动力学参数优化[J].内燃机工程,2016,37(3):83-93.GAN Xu-bo,YAO Dong-wei,WU Feng,et al.PSO algorithm based optimization of urea pyrolysis kinetic parameters [J].Internal Combustion Engine Engineering,2016,37(3):83-93.
[2] LYDIA M,SURESH K S.A comprehensive overview on wind power forecasting[C]//9th International Power and Energy Conference,Singapore,2010,268-273.
[3] MU Gang,YANG Mao,WANG Dong,et al.Spatial dispersion of wind speeds and its influence on the forecasting error of wind power in a wind farm[J].Journal of Modern Power Systems and Clean Energy,2016,4(2):265-274.
[4] 丁志勇,杨苹,杨曦,等.基于连续时间段聚类的支持向量机风电功率预测方法[J].电力系统自动化,2012,36(14):131-135.DING Zhi-yong,YANG Ping,YANG Xi,et al.Wind power prediction method based on continuous time clustering of support vector machines [J].Power System Automation,2012,36(14):131-135.
[5] 张靠社,罗钊.基于RBF-BP组合神经网络的短期风电功率预测研究[J].可再生能源,2014,32(9):1346-1351.ZHANG Kao-she,LUO Zhao.Short-term wind power forecast based on RBF-BP combined neural network [J].Renewable Energy,2014,32(9):1346-1351.
[6] 叶小岭,刘波,邓华.基于小波分析和PSO优化神经网络的短期风电功率预测[J].可再生能源,2014,32(10):1486-1491.YE Xiao-ling,LIU Bo,DENG Hua.Short-term wind power prediction based on wavelet analysis and PSO optimization neural network [J].Renewable Energy,2014,32(10):1486-1491.
[7] 侯家利.Elman神经网络的网络流量预测[J].计算机仿真,2011,28(7):154-157.HOU Jia-li.Elman neural network network traffic prediction [J].Computer Simulation,2011,28(7):154-157.
[8] 周品.MATLAB神经网络设计与应用[M].北京:清华大学出版社,2013.ZHOU Pin.MATLAB neural network design and application[M].Beijing:Tsinghua University Press,2013.
[9] 张建方,王秀祥.直方图理论与最优直方图制作[J].应用概率统计,2009,25(2):201-214.ZHANG Jian-fang,Wang Xiu-xiang.Histogram theory and optimal histogram production[J].Applied probability statistics,2009,25(2):201-214.
[10] 龚伟.基于信息熵和互信息的流域水文模型不确定性分析[D].北京:清华大学,2012.GONG Wei.Uncertainty analysis of watershed hydrological model based on information entropy and mutual information[D].Beijing:Tsinghua University,2012.
[11] 丁晶,王文圣,赵永龙.以互信息为基础的广义相关系数[J].四川大学学报(工程科学版),2013,34(3):1-5.DING Jing,WANG Wen-sheng,ZHAO Yong-long.Generalized correlation coefficient based on mutual information [J].Journal of Sichuan University (Engineering Science Edition),2013,34(3):1-5.
[12] 张学文.组成论[M].北京:中国科学技术大学出版社,2003.ZHANG Xue-wen.Composition theory[M].Beijing:University of Science and Technology of China Press,2003.
[13] LIANG Fa-ming.Bayesian neural networks for nonlinear time series forecasting[J].Statistics and Computing,2005,15(1):13-29.
[14] 干旭波,姚栋伟,吴锋,等.基于PSO算法的SCR尿素热解动力学参数优化[J].内燃机工程,2016,37(3):83-93.GAN Xu-bo,YAO Dong-wei,WU Feng,et al.PSO algorithm based optimization of urea pyrolysis kinetic parameters [J].Internal Combustion Engine Engineering,2016,37(3):83-93.