Combination Forecasting Model of Photovoltaic Power Based on Empirical Wavelet Transform

doi:10.16182/j.issn1004731x.joss.21-FZ0709

Abstract

Abstract: In order to improve the prediction accuracy of short-term photovoltaic power, a variable weight combined prediction model based on Empirical Wavelet Transform (EWT) and PSO-optimized random forest(RF) is proposed. Gray correlation analysis is used to select similar days, EWT is used to decompose the power time series into sub-modes of different frequencies, and three modes of high, medium, and low frequency are reconstructed according to the frequency, PSO-RF and PSO-BP and PSO-LSSVM prediction models are established to dynamically calculate their respective weights for reconstruction, and error correction is performed to output the prediction results. By predicting the output power of Australian photovoltaic power stations, the results verify the effectiveness of the EWT-PSO-RF combined model, which effectively improves the accuracy of ultra-short-term photovoltaic power prediction.

Key words: PV power prediction, empirical wavelet transform, random forest, grey correlation degree, model parameter optimization

CLC Number:

TP391.9

Chen Tao, Wang Yan, Ji Zhicheng. Combination Forecasting Model of Photovoltaic Power Based on Empirical Wavelet Transform[J]. Journal of System Simulation, 2021, 33(11): 2627-2635.

References

[1] 龚莺飞, 鲁宗相, 乔颖, 等. 光伏功率预测技术[J]. 电力系统自动化, 2016, 40(4): 140-151.
Gong Yingfei, Lu Zongxiang, Qiao Ying, et al.An Review of Photovoltaic Energy System Output Forecasting Technology[J]. Automation of Electric Power Systems, 2016, 40(4): 140-151.
[2] 丁明, 王伟胜, 王秀丽, 等. 大规模光伏发电对电力系统影响综述[J]. 中国电机工程学报, 2014, 34(1): 1-14.
Ding Ming, Wang Weisheng, Wang Xiuli, et al.A Review on the Effect of Large-scale PV Generation on Power Systems[J]. Proceedings of the CSEE, 2014, 34(1): 1-14
[3] 杨国清, 张凯, 王德意, 等. 基于包络线聚类的多模融合超短期光伏功率预测算法[J]. 电力自动化设备, 2021, 1(2): 1-8.
Yang Guoqing, Zhang Kai, Wang Deyi, et al.Multi-mode Fusion Ultra-short-term Photovoltaic Power Prediction Algorithm Based on Envelop Clustering[J]. Electric Power Automation Equipment, 2021, 1(2): 1-8.
[4] 许彪, 徐青山, 黄煜, 等. 基于藤copula分位数回归的光伏功率日前概率预测[J]. 电网技术2021, 1(1): 1-13.
Xu Biao, Xu Qingshan, Huang Yu, et al.Prediction of PV Power Day-ahead Probability Based on Vine Copula Quantile Regression[J]. Power Grid Technology, 2021, 1(1): 1-13
[5] Antonanzas J, Osorio N, Escobar R, et al.Review of Photovoltaic Power Forecasting[J]. Solar Energy (S0038-092X), 2018, 136(5): 78-111.
[6] 程泽, 李思宇, 韩丽洁, 等. 基于数据挖掘的光伏阵列发电预测方法研究[J]. 太阳能学报, 2017, 38(3): 726-733.
Cheng Ze, Li Siyu, Han Lijie, et al.Research on the Prediction Method of Photovoltaic Array Power Generation based on Data Mining[J]. Journal of Solar Energy, 2017, 38(3): 726-733.
[7] Dolara A, Grimaccia F, Leva S, et al.Aphysicalhy Brid Artificial Neural Network for Short Term Forecasting of PV Plant Power Output[J]. Energies (S1996-1073), 2015, 8(2): 1138-1153.
[8] Widodo A, Shim M, Caesarendra W, et al.Intelligent Prognostics for Battery Health Monitoring based on Sample Entropy[J]. Expert System With Applications (S0957-4174), 2011, 38(9): 11763-11769.
[9] 张彩庆, 郑强. SKBA-LSSVM短期光伏发电功率预测模型[J]. 电力系统及其自动化学报, 2019, 31(8): 86-93.
Zhang Caiqing, Zheng Qiang.Short-term PV Power Prediction Model of SKBA-LSSVM[J]. Journal of Power Systems and Automation, 2019, 31(8): 86-93
[10] 王粟, 江鑫, 曾亮, 等. 基于VMD-DESN-MSGP模型的超短期光伏功率预测[J]. 电网技术, 2020, 44(3): 917-926.
Wang Su, Jiang Xing, Zeng Liang, et al.Prediction of Ultra-short Term Photovoltaic Power based on VMD-DESN-MSGP Model[J]. Power Grid Technology, 2020, 44(3): 917-926.
[11] Chen C, Duan S, Cai T, et al.Online24-hsolar Power Forecasting based on Weather Type Classification Using Artificial Neural Network[J]. Solar Energy (S0038-092X), 2011, 85(11): 2856-2870.
[12] Mora-lopez L, Martinez-marchena I, Ppiliougine M, et al. Machine Learning Approach for Next Day Energy Production Forecasting Rid Connected Photovoltaic Plants[J]. Environmental Modelling and Software, 2005, 20(6):753-760.
[13] Shi J, Lee W J, Liu Y, et al. Forecasting Power Output of Photovoltaic System based on Weather Classification and Support Vector Machine[J]. IEEE Transactions on Industry Applications.2012.48(3):1064-1-69.
[14] 张金金, 张倩, 马愿, 等. 基于改进的随机森林和密度聚类的短期负荷频域预测方法[J]. 控制理论与应用, 2020, 37(10): 2257-2265.
Zhang Jinjin, Zhang Qian, Ma Yuan, et al.Short-term Load Frequency Domain Forecasting Method based on Improved Random Forest and Density Clustering[J]. Control Theory and Applications, 2020, 37(10): 2257-2265.
[15] Daubechies I, Lu J, Wu H T.Synchrosqueezed Wavelet Transforms: An Empirical Mode Decomposition-like Tool[J]. Applied and Computational Harmonic Analysis (S1063-5203), 2011, 30(2): 243-261.
[16] Daubechies I.Ten Lectures on Wavelets[J].USA: Society for Industrial and Applied Mathematics (S0916-7005), 1992, 21(5): 126-134.
[17] Breiman L.Random Forests[M]. Statistics Department. University of California: Machine Learning, 2001.
[18] Everitt B S.Classification and Regression Trees[M] Encyclopedia of Statistics in Behavioral Science. Cornell University, USA: John Wiley & Sons, Ltd, 2005.
[19] 梁彩霞, 高赵亮. 基于相似日和GA-DBN神经网络的光伏发电短期功率预测[J]. 电气应用, 2019, 38(3): 97-102.
Liang Caixia, Gao Zhaoliang.Short-term Power Prediction of Photovoltaic Power Generation based on Similar Days and GA-DBN Neural Network[J]. Electrical Application, 2019, 38(3): 97-102.