基于混合变分模态分解模型的短期风速预测
|
摘要
针对风速时间序列不稳定导致其难以准确预测的问题,提出一种基于最优变分模态分解(OVMD)和蝙蝠算法(BA)优化最小二乘支持向量机(LSSVM)的短期风速预测模型。采用OVMD技术,将原始风速时间序列先分解为若干个相对稳定的分量序列,然后对各个分量分别建立LSSVM模型进行预测,并采用蝙蝠算法优化LSSVM中的参数,最后对优化的分量预测模型的预测值求和,即得到原始风速序列的预测值。算例分析表明,该模型具有较高的预测精度,能有效跟踪风速的变化规律。研究成果为短期风速预测提供了新思路。
Aiming at the problem that wind speed time series are always instability so that it is difficult to predict accurately,this paper proposed a combined model based on optimal variational mode decomposition(OVMD)and the least squares support vector machine(LSSVM)optimized by bat algorithm(BA)for short-term wind speed prediction.Using OVMD technology,the original wind speed time series was decomposed into several relatively stable sequences.Then the LSSVM model was established to predict each component,and the bat algorithm was used to optimize the parameters of LSSVM.Finally,the prediction value of each component prediction model was accumulated to obtain the prediction value of the original wind speed series.The experimental results show that the model has higher prediction accuracy,and can effectively track the change law of wind speed.The research results provide new idea for short-term wind speed prediction.
Aiming at the problem that wind speed time series are always instability so that it is difficult to predict accurately,this paper proposed a combined model based on optimal variational mode decomposition(OVMD)and the least squares support vector machine(LSSVM)optimized by bat algorithm(BA)for short-term wind speed prediction.Using OVMD technology,the original wind speed time series was decomposed into several relatively stable sequences.Then the LSSVM model was established to predict each component,and the bat algorithm was used to optimize the parameters of LSSVM.Finally,the prediction value of each component prediction model was accumulated to obtain the prediction value of the original wind speed series.The experimental results show that the model has higher prediction accuracy,and can effectively track the change law of wind speed.The research results provide new idea for short-term wind speed prediction.
引文
[1]丁藤,冯冬涵,林晓凡,等.基于修正后ARIMA-GARCH模型的超短期风速预测[J].电网技术,2017,41(6):1 808-1 814.
[2]JUNG J,BROADWATER R P.Current Status and Future Advances for Wind Speed and Power Forecasting[J].Renewable&Sustainable Energy Reviews,2014,31(2):762-777.
[3]吴忠强,贾文静,吴昌韩,等.基于PSO-BSNN的短期风速预测[J].电力系统保护与控制,2015,43(15):36-41.
[4]范高锋,王伟胜,刘纯,等.基于人工神经网络的风电功率预测[J].中国电机工程学报,2008,28(34):118-123.
[5]朱霄珣,韩中合.基于PSO参数优化的LSSVM风速预测方法研究[J].中国电机工程学报,2016,36(23):6 337-6 342.
[6]D Liu,D Niu,H Wang,et al.Short-term Wind Speed Forecasting Using Wavelet Transform and Support Vector Machines Optimized by Genetic Algorithm[J].Renewable Energy,2014,62(2):592-597.
[7]柳玉,曾德良,刘吉臻,等.基于小波包变换的最小二乘支持向量机短期风速多步预测和信息粒化预测的研究[J].太阳能学报,2014,35(2):214-220.
[8]Dragomiretskiy K,Zosso D.Variational Mode Decomposition[J].IEEE Transactions on Signal Process,2014,62(3):531-544.
[9]Xin-She Yang,Amir Hossein Gandomi.Bat Algorithm:A Novel Approach for Global Engineering Optimization[J].Engineering Computations,2012,29(5):464-483.
[10]LIU H,CHEN C,TIAN H Q,et al.A Hybrid Model for Wind Speed Prediction Using Empirical Mode Decomposition and Artificial Neural Networks[J].Renewable Energy,2012,48(6):545-556.
[2]JUNG J,BROADWATER R P.Current Status and Future Advances for Wind Speed and Power Forecasting[J].Renewable&Sustainable Energy Reviews,2014,31(2):762-777.
[3]吴忠强,贾文静,吴昌韩,等.基于PSO-BSNN的短期风速预测[J].电力系统保护与控制,2015,43(15):36-41.
[4]范高锋,王伟胜,刘纯,等.基于人工神经网络的风电功率预测[J].中国电机工程学报,2008,28(34):118-123.
[5]朱霄珣,韩中合.基于PSO参数优化的LSSVM风速预测方法研究[J].中国电机工程学报,2016,36(23):6 337-6 342.
[6]D Liu,D Niu,H Wang,et al.Short-term Wind Speed Forecasting Using Wavelet Transform and Support Vector Machines Optimized by Genetic Algorithm[J].Renewable Energy,2014,62(2):592-597.
[7]柳玉,曾德良,刘吉臻,等.基于小波包变换的最小二乘支持向量机短期风速多步预测和信息粒化预测的研究[J].太阳能学报,2014,35(2):214-220.
[8]Dragomiretskiy K,Zosso D.Variational Mode Decomposition[J].IEEE Transactions on Signal Process,2014,62(3):531-544.
[9]Xin-She Yang,Amir Hossein Gandomi.Bat Algorithm:A Novel Approach for Global Engineering Optimization[J].Engineering Computations,2012,29(5):464-483.
[10]LIU H,CHEN C,TIAN H Q,et al.A Hybrid Model for Wind Speed Prediction Using Empirical Mode Decomposition and Artificial Neural Networks[J].Renewable Energy,2012,48(6):545-556.