IDEAS home Printed from https://ideas.repec.org/a/gam/jeners/v15y2022i11p4171-d832603.html
   My bibliography  Save this article

Short-Term PV Power Forecasting Using a Regression-Based Ensemble Method

Author

Listed:
  • Andi A. H. Lateko

    (Department of Electrical Engineering, National Cheng Kung University, Tainan 701, Taiwan
    Department of Electrical Engineering, Muhammadiyah University of Makassar, Makassar 90221, Indonesia)

  • Hong-Tzer Yang

    (Department of Electrical Engineering, National Cheng Kung University, Tainan 701, Taiwan)

  • Chao-Ming Huang

    (Department of Electrical Engineering, Kun Shan University, Tainan 710, Taiwan)

Abstract

One of the most critical aspects of integrating renewable energy sources into the smart grid is photovoltaic (PV) power generation forecasting. This ensemble forecasting technique combines several forecasting models to increase the forecasting accuracy of the individual models. This study proposes a regression-based ensemble method for day-ahead PV power forecasting. The general framework consists of three steps: model training, creating the optimal set of weights, and testing the model. In step 1, a Random forest (RF) with different parameters is used for a single forecasting method. Five RF models (RF 1 , RF 2 , RF 3 , RF 4 , and RF 5 ) and a support vector machine (SVM) for classification are established. The hyperparameters for the regression-based method involve learners (linear regression (LR) or support vector regression (SVR)), regularization (least absolute shrinkage and selection operator (LASSO) or Ridge), and a penalty coefficient for regularization ( λ ). Bayesian optimization is performed to find the optimal value of these three hyperparameters based on the minimum function. The optimal set of weights is obtained in step 2 and each set of weights contains five weight coefficients and a bias. In the final step, the weather forecasting data for the target day is used as input for the five RF models and the average daily weather forecasting data is also used as input for the SVM classification model. The SVM output selects the weather conditions, and the corresponding set of weight coefficients from step 2 is combined with the output from each RF model to obtain the final forecasting results. The stacking recurrent neural network (RNN) is used as a benchmark ensemble method for comparison. Historical PV power data for a PV site in Zhangbin Industrial Area, Taiwan, with a 2000 kWp capacity is used to test the methodology. The results for the single best RF model, the stacking RNN, and the proposed method are compared in terms of the mean relative error (MRE), the mean absolute error (MAE), and the coefficient of determination (R 2 ) to verify the proposed method. The results for the MRE show that the proposed method outperforms the best RF method by 20% and the benchmark method by 2%.

Suggested Citation

  • Andi A. H. Lateko & Hong-Tzer Yang & Chao-Ming Huang, 2022. "Short-Term PV Power Forecasting Using a Regression-Based Ensemble Method," Energies, MDPI, vol. 15(11), pages 1-21, June.
    • Handle: RePEc:gam:jeners:v:15:y:2022:i:11:p:4171-:d:832603
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/1996-1073/15/11/4171/pdf
    Download Restriction: no
    File URL: https://www.mdpi.com/1996-1073/15/11/4171/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Ming Meng & Chenge Song, 2020. "Daily Photovoltaic Power Generation Forecasting Model Based on Random Forest Algorithm for North China in Winter," Sustainability, MDPI, vol. 12(6), pages 1-17, March.
    2. Ahmed, R. & Sreeram, V. & Mishra, Y. & Arif, M.D., 2020. "A review and evaluation of the state-of-the-art in PV solar power forecasting: Techniques and optimization," Renewable and Sustainable Energy Reviews, Elsevier, vol. 124(C).
    3. Jingyue Wang & Zheng Qian & Jingyi Wang & Yan Pei, 2020. "Hour-Ahead Photovoltaic Power Forecasting Using an Analog Plus Neural Network Ensemble Method," Energies, MDPI, vol. 13(12), pages 1-17, June.
    4. Andi A. H. Lateko & Hong-Tzer Yang & Chao-Ming Huang & Happy Aprillia & Che-Yuan Hsu & Jie-Lun Zhong & Nguyễn H. Phương, 2021. "Stacking Ensemble Method with the RNN Meta-Learner for Short-Term PV Power Forecasting," Energies, MDPI, vol. 14(16), pages 1-23, August.
    5. Yusen Wang & Wenlong Liao & Yuqing Chang, 2018. "Gated Recurrent Unit Network-Based Short-Term Photovoltaic Forecasting," Energies, MDPI, vol. 11(8), pages 1-14, August.
    6. Jebli, Imane & Belouadha, Fatima-Zahra & Kabbaj, Mohammed Issam & Tilioua, Amine, 2021. "Prediction of solar energy guided by pearson correlation using machine learning," Energy, Elsevier, vol. 224(C).
    7. Happy Aprillia & Hong-Tzer Yang & Chao-Ming Huang, 2020. "Short-Term Photovoltaic Power Forecasting Using a Convolutional Neural Network–Salp Swarm Algorithm," Energies, MDPI, vol. 13(8), pages 1-20, April.
    8. Rafati, Amir & Joorabian, Mahmood & Mashhour, Elaheh & Shaker, Hamid Reza, 2021. "High dimensional very short-term solar power forecasting based on a data-driven heuristic method," Energy, Elsevier, vol. 219(C).
    9. Yeojin Kim & Jin Hur, 2020. "An Ensemble Forecasting Model of Wind Power Outputs Based on Improved Statistical Approaches," Energies, MDPI, vol. 13(5), pages 1-11, March.
    10. Ahmad, Muhammad Waseem & Mourshed, Monjur & Rezgui, Yacine, 2018. "Tree-based ensemble methods for predicting PV power generation and their comparison with support vector regression," Energy, Elsevier, vol. 164(C), pages 465-474.
    11. Yuan-Kang Wu & Yi-Hui Lai & Cheng-Liang Huang & Nguyen Thi Bich Phuong & Wen-Shan Tan, 2022. "Artificial Intelligence Applications in Estimating Invisible Solar Power Generation," Energies, MDPI, vol. 15(4), pages 1-18, February.
    12. Mehdi Seyedmahmoudian & Elmira Jamei & Gokul Sidarth Thirunavukkarasu & Tey Kok Soon & Michael Mortimer & Ben Horan & Alex Stojcevski & Saad Mekhilef, 2018. "Short-Term Forecasting of the Output Power of a Building-Integrated Photovoltaic System Using a Metaheuristic Approach," Energies, MDPI, vol. 11(5), pages 1-23, May.
    13. Mayer, Martin János & Gróf, Gyula, 2021. "Extensive comparison of physical models for photovoltaic power forecasting," Applied Energy, Elsevier, vol. 283(C).
    14. Xue-Bo Jin & Wei-Zhen Zheng & Jian-Lei Kong & Xiao-Yi Wang & Yu-Ting Bai & Ting-Li Su & Seng Lin, 2021. "Deep-Learning Forecasting Method for Electric Power Load via Attention-Based Encoder-Decoder with Bayesian Optimization," Energies, MDPI, vol. 14(6), pages 1-18, March.
    15. Mellit, A. & Pavan, A. Massi & Lughi, V., 2021. "Deep learning neural networks for short-term photovoltaic power forecasting," Renewable Energy, Elsevier, vol. 172(C), pages 276-288.
    16. Liu, Da & Sun, Kun, 2019. "Random forest solar power forecast based on classification optimization," Energy, Elsevier, vol. 187(C).
    17. Honglu Zhu & Xu Li & Qiao Sun & Ling Nie & Jianxi Yao & Gang Zhao, 2015. "A Power Prediction Method for Photovoltaic Power Plant Based on Wavelet Decomposition and Artificial Neural Networks," Energies, MDPI, vol. 9(1), pages 1-15, December.
    18. Alessandro Niccolai & Alberto Dolara & Emanuele Ogliari, 2021. "Hybrid PV Power Forecasting Methods: A Comparison of Different Approaches," Energies, MDPI, vol. 14(2), pages 1-18, January.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Chao-Ming Huang & Shin-Ju Chen & Sung-Pei Yang & Hsin-Jen Chen, 2023. "One-Day-Ahead Hourly Wind Power Forecasting Using Optimized Ensemble Prediction Methods," Energies, MDPI, vol. 16(6), pages 1-22, March.
    2. Jose Cruz & Christian Romero & Oscar Vera & Saul Huaquipaco & Norman Beltran & Wilson Mamani, 2023. "Multiparameter Regression of a Photovoltaic System by Applying Hybrid Methods with Variable Selection and Stacking Ensembles under Extreme Conditions of Altitudes Higher than 3800 Meters above Sea Lev," Energies, MDPI, vol. 16(12), pages 1-21, June.

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Sarmas, Elissaios & Spiliotis, Evangelos & Stamatopoulos, Efstathios & Marinakis, Vangelis & Doukas, Haris, 2023. "Short-term photovoltaic power forecasting using meta-learning and numerical weather prediction independent Long Short-Term Memory models," Renewable Energy, Elsevier, vol. 216(C).
    2. Yuan-Kang Wu & Cheng-Liang Huang & Quoc-Thang Phan & Yuan-Yao Li, 2022. "Completed Review of Various Solar Power Forecasting Techniques Considering Different Viewpoints," Energies, MDPI, vol. 15(9), pages 1-22, May.
    3. Korkmaz, Deniz, 2021. "SolarNet: A hybrid reliable model based on convolutional neural network and variational mode decomposition for hourly photovoltaic power forecasting," Applied Energy, Elsevier, vol. 300(C).
    4. Zheng, Lingwei & Su, Ran & Sun, Xinyu & Guo, Siqi, 2023. "Historical PV-output characteristic extraction based weather-type classification strategy and its forecasting method for the day-ahead prediction of PV output," Energy, Elsevier, vol. 271(C).
    5. Leidy Gutiérrez & Julian Patiño & Eduardo Duque-Grisales, 2021. "A Comparison of the Performance of Supervised Learning Algorithms for Solar Power Prediction," Energies, MDPI, vol. 14(15), pages 1-16, July.
    6. Bo Gu & Xi Li & Fengliang Xu & Xiaopeng Yang & Fayi Wang & Pengzhan Wang, 2023. "Forecasting and Uncertainty Analysis of Day-Ahead Photovoltaic Power Based on WT-CNN-BiLSTM-AM-GMM," Sustainability, MDPI, vol. 15(8), pages 1-27, April.
    7. Nguyen, Thi Ngoc & Müsgens, Felix, 2022. "What drives the accuracy of PV output forecasts?," Applied Energy, Elsevier, vol. 323(C).
    8. Putri Nor Liyana Mohamad Radzi & Muhammad Naveed Akhter & Saad Mekhilef & Noraisyah Mohamed Shah, 2023. "Review on the Application of Photovoltaic Forecasting Using Machine Learning for Very Short- to Long-Term Forecasting," Sustainability, MDPI, vol. 15(4), pages 1-21, February.
    9. Yin, Linfei & Cao, Xinghui & Liu, Dongduan, 2023. "Weighted fully-connected regression networks for one-day-ahead hourly photovoltaic power forecasting," Applied Energy, Elsevier, vol. 332(C).
    10. Tang, Yugui & Yang, Kuo & Zhang, Shujing & Zhang, Zhen, 2022. "Photovoltaic power forecasting: A hybrid deep learning model incorporating transfer learning strategy," Renewable and Sustainable Energy Reviews, Elsevier, vol. 162(C).
    11. Andi A. H. Lateko & Hong-Tzer Yang & Chao-Ming Huang & Happy Aprillia & Che-Yuan Hsu & Jie-Lun Zhong & Nguyễn H. Phương, 2021. "Stacking Ensemble Method with the RNN Meta-Learner for Short-Term PV Power Forecasting," Energies, MDPI, vol. 14(16), pages 1-23, August.
    12. Thi Ngoc Nguyen & Felix Musgens, 2021. "What drives the accuracy of PV output forecasts?," Papers 2111.02092, arXiv.org.
    13. Veena Raj & Sam-Quarcoo Dotse & Mathew Sathyajith & M. I. Petra & Hayati Yassin, 2023. "Ensemble Machine Learning for Predicting the Power Output from Different Solar Photovoltaic Systems," Energies, MDPI, vol. 16(2), pages 1-15, January.
    14. Abdallah Abdellatif & Hamza Mubarak & Shameem Ahmad & Tofael Ahmed & G. M. Shafiullah & Ahmad Hammoudeh & Hamdan Abdellatef & M. M. Rahman & Hassan Muwafaq Gheni, 2022. "Forecasting Photovoltaic Power Generation with a Stacking Ensemble Model," Sustainability, MDPI, vol. 14(17), pages 1-21, September.
    15. Mohamed Massaoudi & Ines Chihi & Lilia Sidhom & Mohamed Trabelsi & Shady S. Refaat & Fakhreddine S. Oueslati, 2021. "Enhanced Random Forest Model for Robust Short-Term Photovoltaic Power Forecasting Using Weather Measurements," Energies, MDPI, vol. 14(13), pages 1-20, July.
    16. Wang, Xiaoyang & Sun, Yunlin & Luo, Duo & Peng, Jinqing, 2022. "Comparative study of machine learning approaches for predicting short-term photovoltaic power output based on weather type classification," Energy, Elsevier, vol. 240(C).
    17. Wang, Lining & Mao, Mingxuan & Xie, Jili & Liao, Zheng & Zhang, Hao & Li, Huanxin, 2023. "Accurate solar PV power prediction interval method based on frequency-domain decomposition and LSTM model," Energy, Elsevier, vol. 262(PB).
    18. Alipour, Mohammadali & Aghaei, Jamshid & Norouzi, Mohammadali & Niknam, Taher & Hashemi, Sattar & Lehtonen, Matti, 2020. "A novel electrical net-load forecasting model based on deep neural networks and wavelet transform integration," Energy, Elsevier, vol. 205(C).
    19. Chao-Rong Chen & Faouzi Brice Ouedraogo & Yu-Ming Chang & Devita Ayu Larasati & Shih-Wei Tan, 2021. "Hour-Ahead Photovoltaic Output Forecasting Using Wavelet-ANFIS," Mathematics, MDPI, vol. 9(19), pages 1-14, October.
    20. Abhnil Amtesh Prasad & Merlinde Kay, 2021. "Prediction of Solar Power Using Near-Real Time Satellite Data," Energies, MDPI, vol. 14(18), pages 1-20, September.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:gam:jeners:v:15:y:2022:i:11:p:4171-:d:832603. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.