基于DTCWT与LSSVM的风电场短期风速预测
|
摘要
由于风速具有很强的非线性特性,传统的预测方法难以对其准确预测。为提高预测精度,提出了将双树复小波与最小二乘支持向量机相结合的风速时间序列预测建模方法。首先,利用双树复小波对风速时间序列进行多尺度分解,将其分解为高频子带和低频子带;其次,利用最小二乘支持向量机对不同频率的子带建立相应的预测模型;最后,将各子带预测值进行等权求和得到预测结果。实验表明,基于双树复小波与最小二乘支持向量机的混合预测模型具有较高的预测精度,其平均绝对误差为3. 79%。
Because of the strong non-linear characteristics of wind speed,it is difficult to construct the model for accurate forecast with traditional methods. In order to improve the forecast precision,a forecasting method based on double tree complex w avelet transform( DTCWT) and least square support vector machine( LSSVM) is proposed in this paper. Firstly,DTCWT is used to depose wind speed time series into several high-frequency and low-frequency subbands. Secondly,LSSVM is used to establish the corresponding prediction model for different frequency subbands. Finally,these forecasting results of each subband are combined to obtain forecasting results. Experiments show that the hybrid forecasting model based on DTCWT and LSSVM has higher prediction accuracy and it is suitable for short-term wind speed forecasting of wind farms. And the value of MAPE can reach to 3. 79%.
Because of the strong non-linear characteristics of wind speed,it is difficult to construct the model for accurate forecast with traditional methods. In order to improve the forecast precision,a forecasting method based on double tree complex w avelet transform( DTCWT) and least square support vector machine( LSSVM) is proposed in this paper. Firstly,DTCWT is used to depose wind speed time series into several high-frequency and low-frequency subbands. Secondly,LSSVM is used to establish the corresponding prediction model for different frequency subbands. Finally,these forecasting results of each subband are combined to obtain forecasting results. Experiments show that the hybrid forecasting model based on DTCWT and LSSVM has higher prediction accuracy and it is suitable for short-term wind speed forecasting of wind farms. And the value of MAPE can reach to 3. 79%.
引文
[1]凌劲,茆美琴,李福根,等.短期风速预测的相关方法及其应用研究[J].合肥工业大学学报(自然科学版),2017,40(11):1502-1506.
[2]孙运涛,李玉敦,张婉婕,等.基于条件相依特性的风速仿真模型及其应用[J].太阳能学报,2017,38(11):3131-3137.
[3]张妍,韩璞,王东风,等.基于变分模态分解和LSSVM的风电场短期风速预测[J].太阳能学报,2018,39(1):194-202.
[4]张妍,王东风,韩璞.一种风电场短期风速组合预测模型[J].太阳能学报,2017,38(6):1510-1516.
[5]史可琴,王方雨,梁琛,等.基于随机过程自相关性的风速预测模型分析[J].电网技术,2017,41(2):529-535.
[6]田中大,李树江,王艳红,等.基于ARIMA与ESN的短期风速混合预测模型[J].太阳能学报,2016,37(6):1603-1610.
[7]徐梅梅,任祖怡,陈建国,等.基于空间相关性和小波-神经网络的短期风电功率预测模型[J].南京理工大学学报(自然科学版),2016,40(3):360-365.
[8]刘彦华,董泽.风速及风电功率超短期动态选择线性组合预测[J].太阳能学报,2016,37(4):1009-1016.
[9]管晟超,程浩忠,杨堤,等.基于风速预测的风储电压质量调节系统[J].电网技术,2016,40(5):1341-1347.
[10]王娜,周有庆,邵霞.基于混合神经网络的风电场风资源评估[J].电工技术学报,2015,30(14):370-376.
[11]杜文辽,陶建峰,巩晓赟,等.基于双树复小波变换的非平稳时间序列去趋势波动分析方法[J].物理学报,2016,65(9):1-8.
[12]张慧,卢文冰,赵雄文,等.基于最小二乘支持向量机和小波神经网络的电力线通信信道噪声建模研究[J].电工技术学报,2018,33(16):3879-3888.
[13]杨薛明,边继飞,朱霄殉,等.基于最大熵混沌时间序列的支持向量机短期风速预测模型研究[J].太阳能学报,2016,37(9):2173-2179.
[14]阳霜,罗滇生,何洪英,等.基于EMD-LSSVM的光伏发电系统功率预测方法研究[J].太阳能学报,2016,37(6):1387-1395.
[15]杨爱东,单立群,刘彦昌,等.基于WT与LSSVM的储层流动单元划分方法[J].测井技术,2017,41(2):237-242.
[2]孙运涛,李玉敦,张婉婕,等.基于条件相依特性的风速仿真模型及其应用[J].太阳能学报,2017,38(11):3131-3137.
[3]张妍,韩璞,王东风,等.基于变分模态分解和LSSVM的风电场短期风速预测[J].太阳能学报,2018,39(1):194-202.
[4]张妍,王东风,韩璞.一种风电场短期风速组合预测模型[J].太阳能学报,2017,38(6):1510-1516.
[5]史可琴,王方雨,梁琛,等.基于随机过程自相关性的风速预测模型分析[J].电网技术,2017,41(2):529-535.
[6]田中大,李树江,王艳红,等.基于ARIMA与ESN的短期风速混合预测模型[J].太阳能学报,2016,37(6):1603-1610.
[7]徐梅梅,任祖怡,陈建国,等.基于空间相关性和小波-神经网络的短期风电功率预测模型[J].南京理工大学学报(自然科学版),2016,40(3):360-365.
[8]刘彦华,董泽.风速及风电功率超短期动态选择线性组合预测[J].太阳能学报,2016,37(4):1009-1016.
[9]管晟超,程浩忠,杨堤,等.基于风速预测的风储电压质量调节系统[J].电网技术,2016,40(5):1341-1347.
[10]王娜,周有庆,邵霞.基于混合神经网络的风电场风资源评估[J].电工技术学报,2015,30(14):370-376.
[11]杜文辽,陶建峰,巩晓赟,等.基于双树复小波变换的非平稳时间序列去趋势波动分析方法[J].物理学报,2016,65(9):1-8.
[12]张慧,卢文冰,赵雄文,等.基于最小二乘支持向量机和小波神经网络的电力线通信信道噪声建模研究[J].电工技术学报,2018,33(16):3879-3888.
[13]杨薛明,边继飞,朱霄殉,等.基于最大熵混沌时间序列的支持向量机短期风速预测模型研究[J].太阳能学报,2016,37(9):2173-2179.
[14]阳霜,罗滇生,何洪英,等.基于EMD-LSSVM的光伏发电系统功率预测方法研究[J].太阳能学报,2016,37(6):1387-1395.
[15]杨爱东,单立群,刘彦昌,等.基于WT与LSSVM的储层流动单元划分方法[J].测井技术,2017,41(2):237-242.