Short-term photovoltaic power prediction using combined K-SVD-OMP and KELM method

LI Jun， ZHENG Danyang

（School of Automation and Electrical Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China）

Abstract： For photovoltaic power prediction, a kind of sparse representation modeling method using feature extraction techniques is proposed. Firstly, all these factors affecting the photovoltaic power output are regarded as the input data of the model. Next, the dictionary learning techniques using the K-mean singular value decomposition (K-SVD) algorithm and the orthogonal matching pursuit (OMP) algorithm are used to obtain the corresponding sparse encoding based on all the input data, i.e. the initial dictionary. Then, to build the global prediction model, the sparse coding vectors are used as the input of the model of the kernel extreme learning machine (KELM). Finally, to verify the effectiveness of the combined K-SVD-OMP and KELM method, the proposed method is applied to a instance of the photovoltaic power prediction. Compared with KELM, SVM and ELM under the same conditions, experimental results show that different combined sparse representation methods achieve better prediction results, among which the combined K-SVD-OMP and KELM method shows better prediction results and modeling accuracy.

Key words： photovoltaic power prediction；  sparse representation；  K-mean singular value decomposition algorithm (K-SVD)；  kernel extreme learning machine (KELM)

References

［1］MELLIT A, MASSI PAVAN A, LUGHI V. Deep learning neural networks for short-term photovoltaic power forecasting. Renewable Energy, 2021, 172(c)：  276-288.

［2］ZIANE A, NECAIBIA A, SAHOUANE N, et al. Photovoltaic output power performance assessment and forecasting：  Impact of meteorological variables. Solar Energy, 2021, 220： 745-757.

［3］AHMED R, SREERAM V, MISHRA Y, et al. A review and evaluation of the state-of-the-art in PV solar power forecasting：  Techniques and optimization. Renewable and Sustainable Energy Reviews, 2020, 124： 1-26. 

［4］LIU H Q, LI W J, LI Y C. Ultra-short-term wind power prediction based on copula function and bivariate EMD decomposition algorithm. Archives of Electrical Engineering, 2020, 69(2)：  271-286.

［5］AMMAR R B, OUALHA A. Photovoltaic power prediction using recurrent neural networks//DERBEL N, ZHU Q.Modeling. Identification and control methods in renewable energy systems. Singapore: Springer, 2019：  25-46.

［6］PEDRO H T C, COIMBRA C F M. Assessment of forecasting techniques for solar power production with no exogenous inputs. Solar Energy, 2012, 86(7)：  2017-2028.

［7］LI Y, SU Y, SHU L. An ARMAX model for forecasting the power output of a grid connected photovoltaic system. Renewable Energy, 2014, 66：  78-89. 

［8］VERZIJLBERGH R A, HEIJNEN P W, ROODE S R. Improved model output statistics of numerical weather prediction based irradiance forecasts for solar power applications, Solar Energy, 2015, 118：  634-645. 

［9］VOYANT C, NOTTON G, KALOGIROU S. Machine learning methodsfor solar radiation forecasting：  A review. Renewable Energy, 2017, 105：  569-582. 

［10］HOSSAIN M S, MAHMOOD H. Short-term photovoltaic power forecasting using an lstm neural network and synthetic weather forecast. IEEE Access, 2020, 8：  172524-172533. 

［11］TRAN T N. Grid search of convolutional neural network model in the case of load forecasting. Archives of Electrical Engineering, 2021, 70(1)： 25-36 

［12］LOUZAZNI M, OMRAN N, SINVALDO R. M. A local training strategy-based artificial neural network for predicting the power production of solar photovoltaic systems. IEEE Access, 2020, 8： 150262-150281.

［13］HUANG C, KUO P. Multiple-input deep convolutional neural network model for short-term photovoltaic power forecasting. IEEE Access, 2019, 7：  74822-74834.

［14］DA-SILVA T V, MONTEIRO R V A, GUIMARES G C F. Performance analysis of neuralnetwork training algorithms and support vector machine for power generation forecast of photovoltaic panel. IEEE Latin America Transactions, 2017, 15(6)：  1091-1100.

［15］SUN Y, WANG F, MI Z, et al. Short-term prediction model of module temperature for photovoltaic power forecasting based on support vector machine//The 4th International Conference on Renewable Power Generation, Oct. 17-18, 2015, Beijing, China. London: IET, 2015：  106-110.

［16］KARABIBER A, ALCIN  F. Short term PV power estimation by means of extreme learning machine and support vector machine//The 7th International Istanbul Smart Grids and Cities Congress and Fair, Apr. 25-26, 2019,  Istanbul, Turkey. New York:  IEEE, 2019：  41-44.

［17］LIN G Q, LI L L, TSENG M L, et al. An improved moth-flame optimization algorithm for support vector machine prediction of photovoltaic power generation. Journal of Cleaner Production, 2020, 253：  119966.

［18］MAO M, GONG W, ZHANG L, et al. Short-term output prediction of photovoltaic power station based on EEMD-SVM method. Proceedings of the CSEE, 2013, 33(34)：  17-24. 

［19］ZHANG F, ZHANG Z, WAN L, et al. Short-term output prediction of photovoltaic power station based on EEMD-GRNN method. Acta Solar Energy, 2020, 41(12)：  103-109.

［20］AL-DAHIDI S, AYADI O, ADEEB J. Extreme learning machines for solar photovoltaic power predictions. Energies, 2018, 11(10)：  2725.

［21］LV J C, YI Z, LI Y. Non-divergence of stochastic discrete time algorithms for pca neural networks. IEEE Transactions on Neural Networks and Learning Systems, 2017, 26(2)：  394-399.

［22］FIGUEIREDO M A T. Adaptive sparseness for supervised learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25(9)：  1150-1159. 

［23］ZHANG Y, WANG J, PRECUP D, et al. GEFCom2014 probabilistic solar power forecasting based on k-nearest neighbor and kernel density estimator//IEEE Power & Energy Society General Meeting, Jul. 26-30, 2015, Denver, CO, USA. New York: IEEE, 2015：  1-5.

［24］HONG T, PINSON P, FAN S. Probabilistic energy forecasting：  Global energy forecasting competition 2014 and beyond. International Journal of Forecasting, 2016, 32(3)：  896-913. 

［25］AHMED M A, AUNG Z. Ensemble learning approach for probabilistic forecasting of solar power generation. Energies, 2016, 9(12)：  1017.

基于K-SVD-OMP和KELM组合方法的短期光伏功率预测

李军，郑丹阳

（兰州交通大学 自动化与电气工程学院， 甘肃 兰州 730070）

摘要:针对光伏功率预测， 提出一种基于稀疏表示的特征提取建模方法。 首先， 将所有影响光伏功率预测输出的因素作为模型的输入， 将模型输入构成的数据向量作为初始字典， 由K-均值奇异值分解（K-mean singular value decomposition， K-SVD）算法进行稀疏分解与变换， 得到学习后的字典。 其次， 由正交匹配追踪（Orthogonal matching pursuit， OMP）算法获取相应的稀疏编码向量， 再将其作为核极限学习机（Kernel extreme learning machine， KELM）的模型输入， 以构建全局回归模型。 为了验证K-SVD-OMP和KELM组合方法的有效性， 将所提出的方法应用于光伏功率预测实例中， 在相同条件下， 与KELM、 SVM、 ELM等方法进行了比较。 实验结果表明， 不同的稀疏表示建模组合方法均可以达到好的预测效果， 其中K-SVD-OMP和KELM的组合方法可以给出更好的预测结果与精度。

关键词:光伏功率预测；  稀疏表示；  K-均值奇异值分解算法；  核极限学习机

引用格式：LI Jun， ZHENG Danyang． Short-term photovoltaic power prediction using combined K-SVD-OMP and KELM method． Journal of Measurement Science and Instrumentation， 2022， 13（3）： 320-328. DOI： 10．3969／j．issn．1674-8042．2022．03．008

[full text view]