Photovoltaic Power Generation Forecasting Based on the ARIMA-BPNN-SVR Model
Abstract - 369
PDF

Keywords

Combination forecasting
Photovoltaic power generation
Support vector regression (SVR)
Back propagation neural network (BPNN)
Auto regression integrate moving average (ARIMA)

How to Cite

1.
Fan G-F, Wei H-Z, Chen M-Y, Hong W-C. Photovoltaic Power Generation Forecasting Based on the ARIMA-BPNN-SVR Model. Glob. J. Energy. Technol. Res. Updates. [Internet]. 2022 Aug. 5 [cited 2024 Oct. 14];9:18-3. Available from: https://avantipublishers.com/index.php/gjetru/article/view/1252

Abstract

With the continuous expansion of the capacity of photovoltaic power generation systems, accurate power generation load forecasting can make grid dispatching more reasonable and optimize load distribution. This paper proposes a combined forecasting model based on Auto Regression Integrate Moving Average (ARIMA), back propagation neural network (BPNN), and support vector regression (SVR), namely ARIMA-BPNN-SVR model, aiming at the problem of low accuracy of a single model and traditional forecasting model. Through the complementary advantages of ARIMA, BPNN, and SVR models, the model has good anti-noise ability, nonlinear mapping, and adaptive ability when processing photovoltaic power generation data. Data experiments are carried out on solar photovoltaic power generation in the United States, and the accuracy of model forecasting is evaluated according to MAE, MSE, RMSE, and MAPE. The experimental results show that the proposed ARIMA-BPNN-SVR outperforms the forecasting performance of the single models ARIMA, BPNN, and SVR. Its MAE, MSE, RMSE and MAPE are 0.53, 0.41, 0.64 and 0.84 respectively. In the Wilcoxon sign-rank test, the p-value of the proposed model reached 0.98, indicating the effectiveness of the ARIMA-BPNN-SVR model.

https://doi.org/10.15377/2409-5818.2022.09.2
PDF

References

Li YT, Su Y, Shu LJ. An ARMAX model for forecasting the power output of a grid connected photovoltaic system. Renewable Energy, 2014; 66: 78-89. https://doi.org/10.1016/j.renene.2013.11.067.

Zhang JL, Tan ZF, Wei YM. An adaptive hybrid model for day-ahead photovoltaic output power prediction. Journal of Cleaner Production, 2020; 244: 118858. https://doi.org/10.1016/j.jclepro.2019.118858.

Ding S, Li RJ, Tao Z. A novel adaptive discrete grey model with time-varying parameters for long-term photovoltaic power generation forecasting. Energy Conversion and Management, 2021; 227: 113644. https://doi.org/10.1016/j.enconman.2020.113644

Zhong ZF, Yang CX, Cao WY, Yan CY. Short-term photovoltaic power generation forecasting based on a multivariable grey theory model with parameter optimization. Mathematical Problems in Engineering, 2017; 2017: 5812394. https://doi.org/10.1155/2017/5812394

Yu L, Ma X, Wu WQ, Xiang XW, Wang Y, Zeng B. Application of a novel time-delayed power-driven grey model to forecast photovoltaic power generation in the Asia-Pacific region. Sustainable Energy Technologies and Assessments, 2021; 44:100968. https://doi.org/10.1016/j.seta.2020.100968.

Yadav AK, Chandel SS. Identification of relevant input variables for prediction of 1-minute time-step photovoltaic module power using artificial neural network and multiple linear regression models. Renewable and Sustainable Energy Reviews, 2017; 77: 955-969. https://doi.org/10.1016/j.rser.2016.12.029.

Zhong JQ, Liu LY, Sun Q, Wang XY. Prediction of photovoltaic power generation based on general regression and back propagation neural network. Energy Procedia, 2018; 152: 1224-1229. https://doi.org/10.1016/j.egypro.2018.09.173.

AlShafeey M, Csáki C. Evaluating neural network and linear regression photovoltaic power forecasting models based on different input methods. Energy Reports, 2021; 7: 7601-7614. https://doi.org/10.1016/j.egyr.2021.10.125.

Wu YX, Guo TT, Wang H. Photovoltaic power prediction method based on similar day and BP neutral network. IOP Conference Series: Earth and Environmental Science, 2018; 170: 042016. https://doi.org/10.1088/1755-1315/170/4/042016.

Zhang Y, Kong LQ. Photovoltaic power prediction based on hybrid modeling of neural network and stochastic differential equation. ISA Transactions, 2021. https://doi.org/10.1016/j.isatra.2021.11.008.

Natarajan Y, Kannan S, Selvaraj C, Mohanty SN. Forecasting energy generation in large photovoltaic plants using radial belief neural network. Sustainable Computing: Informatics and Systems, 2021; 31: 100578. https://doi.org/10.1016/j.suscom.2021.100578.

Eseye AT, Zhang JH, Zheng DH. Short-term photovoltaic solar power forecasting using a hybrid Wavelet-PSO-SVM model based on SCADA and Meteorological information. Renewable Energy, 2018; 118: 357-367. https://doi.org/10.1016/j.renene.2017.11.011.

Xun T, Lei SH, Ding XC, Chen K, Huang K, Nie YX. Photovoltaic power forecasting method based on adaptive classification strategy and HO-SVR algorithm. Energy Reports, 2020; 6: 921-928. https://doi.org/10.1016/j.egyr.2020.11.108.

Pan MZ, Li C, Gao R, Huang YT, You H, Gu TS, Qin F. Photovoltaic power forecasting based on a support vector machine with improved ant colony optimization. Journal of Cleaner Production, 2020; 277: 123948. https://doi.org/10.1016/j.jclepro.2020.123948.

Niu DX, Wang KK, Sun LJ, Wu J, Xu XM. Short-term photovoltaic power generation forecasting based on random forest feature selection and CEEMD: A case study. Applied Soft Computing 2020; 93: 106389. https://doi.org/10.1016/j.asoc.2020.106389.

Meng M, Song CG. Daily Photovoltaic Power Generation Forecasting Model Based on Random Forest Algorithm for North China in Winter. Sustainability 2020, 12: 2247. https://doi.org/10.3390/su12062247.

Wang JZ, Zhou YL, Li ZW. Hour-ahead photovoltaic generation forecasting method based on machine learning and multi objective optimization algorithm. Applied Energy, 2022; 312: 118725. https://doi.org/10.1016/j.apenergy.2022.118725.

Zang HX, Cheng LL, Ding T, Cheung KW, Wei ZN, Sun GQ. Day-ahead photovoltaic power forecasting approach based on deep convolutional neural networks and meta learning. International Journal of Electrical Power & Energy Systems, 2020; 118: 105790. https://doi.org/10.1016/j.ijepes.2019.105790.

Wang F, Zhang ZY, Liu C, Yu YL, Pang SL, Duić N, Shafie-khah M, Catalão JPS. Generative adversarial networks and convolutional neural networks based weather classification model for day ahead short-term photovoltaic power forecasting. Energy Conversion and Management, 2019; 181: 443-462. https://doi.org/10.1016/j.enconman.2018.11.074.

Sharma N, Mangla M, Yadav S, Goyal N, Singh A, Verma S, Saber T. A sequential ensemble model for photovoltaic power forecasting. Computers & Electrical Engineering, 2021; 96: 107484. https://doi.org/10.1016/j.compeleceng.2021.107484.

Ahmed R, Sreeram V, Togneri R, Datta A, Arif MD. Computationally expedient Photovoltaic power Forecasting: A LSTM ensemble method augmented with adaptive weighting and data segmentation technique. Energy Conversion and Management, 2022; 258: 115563. https://doi.org/10.1016/j.enconman.2022.115563.

Huang XQ, Li Q, Tai YH, Chen ZQ, Liu J, Shi JS, Liu WM. Time series forecasting for hourly photovoltaic power using conditional generative adversarial network and Bi-LSTM. Energy, 2022; 246: 123403. https://doi.org/10.1016/j.energy.2022.123403.

Mellit A, Massi Pavan A, Lughi V. Deep learning neural networks for short-term photovoltaic power forecasting. Renewable Energy, 2021; 172: 276-288. https://doi.org/10.1016/j.renene.2021.02.166.

Wang ZP, Qu JF, Fang XY, Li H, Zhong T, Ren H. Prediction of early stabilization time of electrolytic capacitor based on ARIMA-Bi_LSTM hybrid model. Neurocomputing, 2020; 403: 63-79. https://doi.org/10.1016/j.neucom.2020.03.054.

Liu LY, Liu DR, Sun Q, Li HL, Wennersten R. Forecasting power output of photovoltaic system using a BP network method. Energy Procedia, 2017; 142: 780-786. https://doi.org/10.1016/j.egypro.2017.12.126.

Li YQ, Zhou L, Gao PQ, Yang B, Han YM, Lian C. Short-Term power generation forecasting of a photovoltaic plant based on PSO-BP and GA-BP neural networks, Frontiers in Energy Research, 2022. https://doi.org/10.3389/FENRG.2021.824691.

Hu KY, Wang LD, Li WJ, Cao SH, Shen YY. Forecasting of solar radiation in photovoltaic power station based on ground‐based cloud images and BP neural network. IET Generation, Transmission & Distribution, 2021; 16: 333-350. https://doi.org/10.1049/GTD2.12309.

Lin GQ, Li LL, Tseng ML, Liu HM, Yuan DD, Tan RR. An improved moth-flame optimization algorithm for support vector machine prediction of photovoltaic power generation. Journal of Cleaner Production, 2020; 253: 119966. https://doi.org/10.1016/j.jclepro.2020.119966.

Boegli M, Stauffer Y. SVR based PV models for MPC based energy flow management. Energy Procedia, 2017; 122: 133-138. https://doi.org/10.1016/j.egypro.2017.07.317.

Lin JM, Li HM. A Hybrid K-Means-GRA-SVR model based on feature selection for day-ahead prediction of photovoltaic power generation. Journal of Computer and Communications, 2021; 9: 91-111. https://doi.org/10.4236/JCC.2021.911007.

Das UK, Tey KS, Seyedmahmoudian M, Mekhilef S, Idris MYI, Van Deventer W, Horan B, Stojcevski A. Forecasting of photovoltaic power generation and model optimization: A review. Renewable and Sustainable Energy Reviews, 2018; 8: 912-928. https://doi.org/10.1016/j.rser.2017.08.017.

VanDeventer W, Jamei E, Thirunavukkarasu, GS, Seyedmahmoudian M, Soon TK, Horan B, Mekhilef S, Stojcevski A. Short-term PV power forecasting using hybrid GASVM technique. Renewable Energy, 2019; 140:367-379. https://doi.org/10.1016/j.renene.2019.02.087.

Seyedmahmoudian M, Jamei E, Thirunavukkarasu GS, Soon TK, Mortimer M, Horan B, Stojcevski A, Mekhilef S. Short-Term Forecasting of the output power of a building-integrated photovoltaic system using a metaheuristic approach. Energies, 2018, 11:1260. https://doi.org/10.3390/en11051260.

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

Copyright (c) 2022 Guo-Feng Fan, Hui-Zhen Wei, Meng-Yao Chen, Wei-Chiang Hong