Abstract
Accurate short-term forecasting of photovoltaic power generation is crucial for power dispatching, capacity analysis, and unit commitment. Existing data-driven prediction algorithms have a certain impact on calculation speed and prediction accuracy, but they fail to consider the internal mechanism of photovoltaic power generation and have the risk of generalization. First, the fuzzy C-means clustering (FCM) algorithm method was used for preprocessing of the PV sample set. The sample points with variability were categorized into different sample sets with less variability. Second, the photovoltaic mechanism model is added to the first layer learner of the Stacking framework to form a one-layer learner of the Long Short-Term Memory (LSTM) neural network, Light Gradient Boosting model (LGBM), and mechanism-driven model. The mechanistic model limits PV generation to a reasonable range as a prediction constraint for the data-driven model. The proposed model can seize the useful inherent information from the mechanism model and utilize the ability of data analysis to extract the inexplicit linear relationship. Finally, the PV power and weather observation data collected from photovoltaic power stations located in a certain place in Germany are used to verify the effectiveness of the proposed method.
Similar content being viewed by others
References
Cheng L, Zang H, Wei Z, Ding T, Xu R, Sun G (2021) Short-term solar power prediction learning directly from satellite images with regions of interest. IEEE Trans Sustain Energy 13(1):629–639
Shahbaz M, Raghutla C, Chittedi KR, Jiao Z, Vo XV (2020) The effect of renewable energy consumption on economic growth: Evidence from the renewable energy country attractive index. Energy 207:118162
Chang GW, Lu H-J (2018) Integrating gray data preprocessor and deep belief network for day-ahead pv power output forecast. IEEE Trans Sustain Energy 11(1):185–194
Wen H, Du Y, Chen X, Lim E, Wen H, Jiang L, Xiang W (2020) Deep learning based multistep solar forecasting for pv ramp-rate control using sky images. IEEE Trans Industr Inf 17(2):1397–1406
Marion B (2008) Comparison of predictive models for photovoltaic module performance. 2008 33rd IEEE Photovoltaic Specialists Conference. IEEE, pp 1–6
Li H, Ren Z, Xu Y, Li W, Hu B (2021) A multi-data driven hybrid learning method for weekly photovoltaic power scenario forecast. IEEE Trans Sustain Energy 13(1):91–100
Liu W, Xu Y (2020) Randomised learning-based hybrid ensemble model for probabilistic forecasting of pv power generation. IET Gener Transm Distrib 14(24):5909–5917
Qu Y, Xu J, Sun Y, Liu D (2021) A temporal distributed hybrid deep learning model for day-ahead distributed pv power forecasting. Appl Energy 304:117704
Yuan X, Qi S, Wang Y, Wang K, Yang C, Ye L (2021) “Quality variable prediction for nonlinear dynamic industrial processes based on temporal convolutional networks. IEEE Sens J 21(18):20493–20503
Jiajun H, Chuanjin Y, Yongle L, Huoyue X (2020) Ultra-short term wind prediction with wavelet transform, deep belief network and ensemble learning. Energy Convers Manage 205:112418
Ke G, Meng Q, Finley T, Wang T, Chen W, Ma W, Ye Q, Liu TY (2022) Lightgbm: A highly efficient gradient boosting decision tree. IEEE Trans Smart Grid 13:3173964
Lin G-Q, Li L-L, Tseng M-L, Liu H-M, Yuan D-D, Tan RR (2020) An improved moth-flame optimization algorithm for support vector machine prediction of photovoltaic power generation. J Clean Prod 253:119966
Liu W, Ren C, Xu Y (2020) Pv generation forecasting with missing input data: A super-resolution perception approach. IEEE Trans Sustain Energy 12(2):1493–1496
Yixiu G, Yong L, Xuebo Q, Zhenyu Z, Wangfeng Z, Yujie M, Jinjie L, Yicheng Z, Yosuke N (2022) BiLstm Multi-task Learning-Based Combined Load Forecasting Considering the Loads Coupling Relationship for Multienergy System. IEEE Trans Smart Grid 13:3173964
Kang JWHZXLQXYWC (2019) Exploring key weather factors from analytical modeling toward improved solar power forecasting. IEEE Trans Smart Grid 10(2):1417–1427
Han Y, Wang N, Ma M, Zhou H, Dai S, Zhu H (2019) A pv power interval forecasting based on seasonal model and nonparametric estimation algorithm. Sol Energy 184:515–526
Veldhuis AJ, Nobre AM, Peters IM, Reindl T, Ruether R, Reinders AH (2015) An empirical model for rack-mounted pv module temperatures for southeast asian locations evaluated for minute time scales. IEEE J Photovoltaics 5(3):774–782
Khan W, Walker S, Zeiler W (2022) Improved solar photovoltaic energy generation forecast using deep learningbased ensemble stacking approach. Energy 240:122812
Zhang Q, Wu J, Ma Y, Li G, Ma J, Wang C (2022) Short-term load forecasting method with variational mode decomposition and stacking model fusion. Sust Energy Grids Netw 30:100622
Chai S, Xu Z, Jia Y, Wong WK (2020) A robust spatiotemporal forecasting framework for photovoltaic generation. IEEE Trans Smart Grid 11(6):5370–5382
Kim KA, Krein PT, Seo GS, Cho BH (2013) Photovoltaic ac parameter characterization for dynamic partial shading and hot spot detection. Twenty-eighth annual IEEE applied power electronics conference and exposition (APEC). IEEE, pp 109–115
Barbieri F, Rajakaruna S, Ghosh A (2017) Very short-term photovoltaic power forecasting with cloud modeling: A review. Renew Sustain Energy Rev 75:242–263
Zhang R, Ma H, Hua W, Saha TK, Zhou X (2019) Data-driven photovoltaic generation forecasting based on a bayesian network with spatial–temporal correlation analysis. IEEE Trans Industr Inf 16(3):1635–1644
Lu X, Zhou Y, Wang Z, Yi Y, Feng L, Wang F (2019) Knowledge embedded semi-supervised deep learning for detecting non-technical losses in the smart grid. Energies 12(18):3452
Xiao F, Ai Q (2018) Data-driven multi-hidden Markov model-based power quality disturbance prediction that incorporates weather conditions. IEEE Trans Power Syst 34(1):402–412
Tan Y, Chen Y, Li Y, Cao Y (2020) Linearizing power flow model: A hybrid physical model-driven and datadriven approach. IEEE Trans Power Syst 35(3):2475–2478
Bloch A, Casale-Brunet S, Mattavelli M (2021) Methodologies for synthesizing and analyzing dynamic dataflow programs in heterogeneous systems for edge computing. IEEE Open J Circ Syst 2:769–781
Engerer N, Mills F (2015) Validating nine clear sky radiation models in australia. Sol Energy 120:9–24
Gueymard CA (2008) Rest2: High-performance solar radiation model for cloudless-sky irradiance, illuminance, and photosynthetically active radiation–validation with a benchmark dataset. Sol Energy 82(3):272–285
Faiman D (2008) Assessing the outdoor operating temperature of photovoltaic modules. Prog Photovoltaics Res Appl 16(4):307–315
Zheng F, Xia Y, Su H, Wang W (2021) Research on key technologies of power system visualization platform. 2021 13th International Conference on Measuring Technology and Mechatronics Automation (ICMTMA). IEEE, pp 235–238
Kumar DS, Yagli GM, Kashyap M, Srinivasan D (2020) Solar irradiance resource and forecasting: a comprehensive review. IET Renew Power Gener 14(10):1641–1656
Taylor KE (2001) Summarizing multiple aspects of model performance in a single diagram. J Geophys Res: Atmos 106(D7):7183–7192
Acknowledgements
This work is supported by the State Grid Company Technology Project(52120522000R). This work is supported by 2022 Collaborative Innovation Projects between Universities and Hefei Comprehensive National Science Center(GXXT-2022-023).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Chen, F., Ding, J., Zhang, Q. et al. A PV Power Forecasting Based on Mechanism Model-Driven and Stacking Model Fusion. J. Electr. Eng. Technol. (2024). https://doi.org/10.1007/s42835-024-01906-8
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s42835-024-01906-8