預測太陽能發電（photovoltaic, PV）系統產生的電力對於一些應用至關重要，例如微電網、集成到智能建築中的光伏以及能源管理系統。在平衡供需所需的複雜決策過程中必須考慮不確定性，而用於解決此問題的方法是太陽能發電功率預測。 此外，通過將幾個不同或相同的預測模型結合起來的集成預測方法，提高了每個單獨模型的預測精度。本文針對短期光伏發電量預測提出了兩種集合預測方法。
首先，我們提出了一種基於堆疊集成模型的日前太陽能發電功率預測策略，其中遞歸神經網絡（RNN）作為學習器。這樣做是為了防止使用不準確的個別預測模型。為了訓練和測試模型，使用了太陽能發電功率輸出的歷史數據和天氣數據。人工神經網絡 (ANN)、深度神經網絡 (DNN)、支持向量回歸 (SVR)、長短期記憶 (LSTM) 和卷積神經網絡 (CNN) 是本研究中考慮的個體預測模型。每個模型的預測結果都使用 RNN 學習器進行組合。研究本研究中單個模型的哪些組合產生最佳結果也很重要。 此外，使用隨機森林集成進行性能比較。這允許對所提出的方法的性能進行更準確的評估。
然後，我們提出了一種基於回歸的集成方法來預測短期日前太陽能發電量。整體結構分為三個步驟：訓練模型、確定理想的權重分佈、驗證模型。在此過程的第一部分，使用具有各種參數的隨機森林 (RF) 構建單一預測方法。決定構建五個隨機森林模型（RF1、RF2、RF3、RF4 和 RF5）以及用於分類的支持向量機（SVM）。回歸模型，例如線性回歸 (LR) 或支持向量回歸 (SVR)，正則化，例如最小絕對收縮和選擇算子 (LASSO) 或 Ridge，以及正則化的懲罰係數 (λ) 是回歸的超參數。使用最小函數作為指導，進行貝葉斯優化以確定這三個超參數中的每一個的理想設置。第 2 步是獲得最佳權重集，每組權重將包括五個權重係數以及一個偏差。最後一個階段涉及使用來自目標日期的天氣預報數據作為五個 RF 模型的輸入，以及使用來自平均每日天氣預報的數據作為 SVM 分類模型的輸入。SVM 的輸出用於選擇天氣條件，然後將每個 RF 模型的輸出與步驟 2 中相應的一組權重係數相結合，以生成最終的預測結果。第一個提出的堆疊遞歸神經網絡 (RNN) 方法是作為第二個提出的集成方法的基準比較方法。
為了測試該方法，使用了來自台灣張濱工業區和友基工業有限公司的光伏站點的歷史光伏功率數據，這兩個光伏站點的容量分別為 2000 kWp 和 200 kWp。 為了驗證所提出的方法，所提出的方法在平均相對誤差 (MRE)、平均絕對誤差 (MAE)、歸一化均方根誤差 (nRMSE) 和決定係數 (R2) 方面進行了比較。顯示，所提出的集合預測技術優於個別和基準預測模型。此外，還對兩種提出的方法進行了比較，結果顯示第二種提出的方法比第一種方法提高了 2% 預測精確度。

Forecasting the power generated by photovoltaic (PV) systems is essential for some applications such as micro-grids, PV integrated into smart buildings, and energy management systems. The uncertainty must be considered in the complex decision-making processes required to balance supply and demand, and the method used to address this problem is PV power forecasting. Furthermore, the accuracy of each individual model's forecast is improved through the ensemble forecasting approach, which combines several different or the same forecasting models. This dissertation proposes two ensemble forecasting methods for short-term PV power generation forecasting.
At first, we proposed a strategy for a one-day ahead PV power forecasting based on the stacking ensemble model with a recurrent neural network (RNN) as a meta-learner. This is done to prevent an inaccurate individual forecasting model from being used. In order to train and test the model, historical data on PV power output and weather data are employed. Artificial neural network (ANN), deep neural network (DNN), support vector regressions (SVR), long short-term memory (LSTM), and convolutional neural network (CNN) are the individual forecasting model that is taken into consideration in this research. Each model's forecasting results are combined using an RNN meta-learner. It is also essential to investigate which combinations of the individual model in this study produce the best results. In addition, a random forest ensemble is utilized for performance comparison. This allows for a more accurate assessment of the proposed method's performance.
Then, we proposed a regression-based ensemble method for forecasting short-term one-day ahead PV power generation. The overall structure is divided into three steps: training the model, determining the ideal weight distribution, and validating the model. In the first part of this process, a single forecasting method is constructed using a random forest (RF) with a variety of parameters. It is decided to construct five random forest models (RF1, RF2, RF3, RF4, and RF5) as well as a support vector machine (SVM) for classification. Regression model, such as linear regression (LR) or support vector regression (SVR), regularization, such as least absolute shrinkage and selection operator (LASSO) or Ridge, and a penalty coefficient for regularization (λ) are the hyperparameters for the regression-based technique. Using the minimal function as a guide, Bayesian optimization is carried out in order to determine the ideal setting for each of these three hyperparameters. Step 2 is where you will obtain the optimal set of weights, and each set of weights will include five weight coefficients in addition to a bias. The last stage involves using the data from the weather forecast for the target day as an input for the five RF models, as well as using the data from the average daily weather forecast as an input for the SVM classification model. The output of the SVM is used to choose the weather conditions, and then the output from each RF model is coupled with the corresponding set of weight coefficients from step 2 to generate the final predicting results. The first proposed method of stacking recurrent neural network (RNN) is the method of comparison that serves as the benchmark for the second proposed ensemble method.
To test the methodology, historical PV power data from PV sites in Zhangbin Industrial Area and You Ji Industrial Co., Ltd in Taiwan, which have the capacity of 2000 kWp and 200 kWp, respectively, are utilized. In order to validate the proposed methods, the proposed methods are compared in terms of the mean relative error (MRE), the mean absolute error (MAE), the normalized root mean square error (nRMSE), and the coefficient of determination (R2). The results showed that the proposed ensemble forecasting techniques outperformed the individual and benchmark forecasting models. Furthermore, the comparison of the two proposed methods was also made, and the results showed that the second proposed method has a 2% improvement compared to the first.

[1] N. Javaid, G. Hafeez, S. Iqbal, N. Alrajeh, M. S. Alabed, and M. Guizani, “Energy efficient integration of renewable energy sources in the smart grid for demand side management,” IEEE Access, vol. 6, pp. 77077–77096, 2018.
[2] A. Shahid, “Smart Grid Integration of Renewable Energy Systems,” 2018 7th International Conference on Renewable Energy Research and Applications (ICRERA), Paris, France, 14-17 October 2018, pp. 944-948.
[3] Z. Ullah, R. Asghar, I. Khan, K. Ullah, A. Waseem, F. Wahab, A. Haider, S. M. Ali, and K. U. Jan, “Renewable Energy Resources Penetration within Smart Grid: An overview,” 2020 2nd International Conference on Electrical, Communication, and Computer Engineering (ICECCE), Istanbul, Turkey, 12–13 June 2020.
[4] C. Wan, J. Zhao, Y. Song, Z. Xu, J. Lin, and Z. Hu, “Photovoltaic and solar power forecasting for Smart Grid Energy Management,” CSEE Journal of Power and Energy Systems, vol. 1, no. 4, pp. 38–46, 2015.
[5] P. Li, K. Zhou, and S. Yang, “Photovoltaic Power Forecasting: Models and methods,” 2018 2nd IEEE Conference on Energy Internet and Energy System Integration (EI2), Beijing, China, 20–22 October 2018.
[6] R. Ahmed, V. Sreeram, Y. Mishra, and M. D. Arif, “A review and evaluation of the state-of-the-art in PV solar power forecasting: Techniques and Optimization,” Renewable and Sustainable Energy Reviews, vol. 124, pp. 109792, 2020.
[7] A. Rafati, M. Joorabian, E. Mashhour, and H. R. Shaker, “High dimensional very short-term solar power forecasting based on a data-driven heuristic method,” Energy, vol. 219, pp. 119647, 2021.
[8] N. Son and M. Jung, “Analysis of meteorological factor multivariate models for medium- and long-term photovoltaic solar power forecasting using long short-term memory,” Applied Sciences, vol. 11, no. 1, pp. 316, 2020.
[9] A. Mellit, A. Massi Pavan, E. Ogliari, S. Leva, and V. Lughi, “Advanced methods for photovoltaic output power forecasting: A Review,” Applied Sciences, vol. 10, no. 2, pp. 487, 2020.
[10] M. Massaoudi, I. Chihi, H. Abu-Rub, S. S. Refaat, and F. S. Oueslati, “Convergence of photovoltaic power forecasting and Deep Learning: State-of-art review,” IEEE Access, vol. 9, pp. 136593–136615, 2021.
[11] M. J. Mayer and G. Gróf, “Extensive comparison of physical models for photovoltaic power forecasting,” Applied Energy, vol. 283, pp. 116239, 2021.
[12] B. Wolff, J. Kühnert, E. Lorenz, O. Kramer, and D. Heinemann, “Comparing support vector regression for PV power forecasting to a physical modeling approach using measurement, Numerical Weather Prediction, and Cloud Motion Data,” Solar Energy, vol. 135, pp. 197–208, 2016.
[13] B. Singh and D. Pozo, “A guide to solar power forecasting using Arma Models,” 2019 IEEE PES Innovative Smart Grid Technologies Europe (ISGT-Europe), Bucharest, Romania, 29 September–2 October 2019.
[14] S. Preda, S.-V. Oprea, A. Bâra, and A. Belciu (Velicanu), “PV forecasting using support vector machine learning in a big data analytics context,” Symmetry, vol. 10, no. 12, pp. 748, 2018.
[15] H. Zhu, X. Li, Q. Sun, L. Nie, J. Yao, and G. Zhao, “A power prediction method for photovoltaic power plant based on wavelet decomposition and artificial neural networks,” Energies, vol. 9, no. 1, pp. 11, 2015.
[16] J. Son, Y. Park, J. Lee, and H. Kim, “Sensorless PV power forecasting in grid-connected buildings through deep learning,” Sensors, vol. 18, no. 8, pp. 2529, 2018.
[17] M. Meng and C. Song, “Daily Photovoltaic Power Generation Forecasting model based on random forest algorithm for North China in Winter,” Sustainability, vol. 12, no. 6, pp. 2247, 2020.
[18] M. N. Akhter, S. Mekhilef, H. Mokhlis, and N. Mohamed Shah, “Review on forecasting of photovoltaic power generation based on machine learning and metaheuristic techniques,” IET Renewable Power Generation, vol. 13, no. 7, pp. 1009–1023, 2019.
[19] D. Liu and K. Sun, “Random Forest Solar Power Forecast based on classification optimization,” Energy, vol. 187, pp. 115940, 2019.
[20] A. Mellit, A. M. Pavan, and V. Lughi, “Deep Learning Neural Networks for short-term photovoltaic power forecasting,” Renewable Energy, vol. 172, pp. 276–288, 2021.
[21] A. Niccolai, A. Dolara, and E. Ogliari, “Hybrid PV power forecasting methods: A comparison of different approaches,” Energies, vol. 14, no. 2, pp. 451, 2021.
[22] M. Seyedmahmoudian, E. Jamei, G. Thirunavukkarasu, T. Soon, M. Mortimer, B. Horan, A. Stojcevski, and S. Mekhilef, “Short-term forecasting of the output power of a building-integrated photovoltaic system using a metaheuristic approach,” Energies, vol. 11, no. 5, pp. 1260, 2018.
[23] H. Aprillia, H.-T. Yang, and C.-M. Huang, “Short-term photovoltaic power forecasting using a convolutional neural network–salp swarm algorithm,” Energies, vol. 13, no. 8, pp. 1879, 2020.
[24] T. Yang, B. Li, and Q. Xun, “LSTM-attention-embedding model-based day-ahead prediction of photovoltaic power output using Bayesian optimization,” IEEE Access, vol. 7, pp. 171471–171484, 2019.
[25] F. Wang, Z. Zhen, B. Wang, and Z. Mi, “Comparative study on KNN and SVM based weather classification models for Day ahead short term solar pv power forecasting,” Applied Sciences, vol. 8, no. 1, pp. 28, 2017.
[26] M. S. Hossain and H. Mahmood, “Short-term photovoltaic power forecasting using an LSTM neural network and synthetic weather forecast,” IEEE Access, vol. 8, pp. 172524–172533, 2020.
[27] M. Massaoudi, H. Abu-Rub, S. S. Refaat, M. Trabelsi, I. Chihi, and F. S. Oueslati, “Enhanced deep belief network based on ensemble learning and tree-structured of parzen estimators: An Optimal Photovoltaic Power Forecasting Method,” IEEE Access, vol. 9, pp. 150330–150344, 2021.
[28] D. Yang and Z. Dong, “Operational Photovoltaics Power Forecasting using seasonal time series ensemble,” Solar Energy, vol. 166, pp. 529–541, 2018.
[29] M. W. Ahmad, M. Mourshed, and Y. Rezgui, “Tree-based ensemble methods for predicting PV power generation and their comparison with support vector regression,” Energy, vol. 164, pp. 465–474, 2018.
[30] M. Hossain, S. Mekhilef, M. Danesh, L. Olatomiwa, and S. Shamshirband, “Application of extreme learning machine for short term output power forecasting of three grid-connected PV systems,” Journal of Cleaner Production, vol. 167, pp. 395–405, 2017.
[31] D. van der Meer, G. R. Chandra Mouli, G. Morales-Espana Mouli, L. R. Elizondo, and P. Bauer, “Energy Management System with PV power forecast to optimally charge evs at the workplace,” IEEE Transactions on Industrial Informatics, vol. 14, no. 1, pp. 311–320, 2018.
[32] X. Qiu, L. Zhang, Y. Ren, P. Suganthan, and G. Amaratunga, “Ensemble deep learning for regression and time series forecasting,” 2014 IEEE Symposium on Computational Intelligence in Ensemble Learning (CIEL), Orlando, FL, USA, 9–12 December 2014.
[33] H. Eom, Y. Son, and S. Choi, “Feature-Selective Ensemble Learning-based long-term regional PV generation forecasting,” IEEE Access, vol. 8, pp. 54620–54630, 2020.
[34] M. Q. Raza, N. Mithulananthan, J. Li, K. Y. Lee, and H. B. Gooi, “An ensemble framework for day-ahead forecast of PV output power in smart grids,” IEEE Transactions on Industrial Informatics, vol. 15, no. 8, pp. 4624–4634, 2019.
[35] A. Ahmed Mohammed and Z. Aung, “Ensemble learning approach for probabilistic forecasting of solar power generation,” Energies, vol. 9, no. 12, pp. 1017, 2016.
[36] S. Al-Dahidi, O. Ayadi, M. Alrbai, and J. Adeeb, “Ensemble approach of optimized artificial neural networks for solar photovoltaic power prediction,” IEEE Access, vol. 7, pp. 81741–81758, 2019.
[37] C. Pan and J. Tan, “Day-ahead hourly forecasting of solar generation based on cluster analysis and Ensemble Model,” IEEE Access, vol. 7, pp. 112921–112930, 2019.
[38] J. Wang, Z. Qian, J. Wang, and Y. Pei, “Hour-ahead photovoltaic power forecasting using an analog plus neural network ensemble method,” Energies, vol. 13, no. 12, pp. 3259, 2020.
[39] A. A. H. Lateko, H.-T. Yang, C.-M. Huang, H. Aprillia, C.-Y. Hsu, J.-L. Zhong, and N. H. Phương, “Stacking Ensemble method with the RNN meta-learner for short-term PV power forecasting,” Energies, vol. 14, no. 16, pp. 4733, 2021.
[40] R. Zhu, W. Guo, and X. Gong, “Short-term photovoltaic power output prediction based on k-fold cross-validation and an ensemble model,” Energies, vol. 12, no. 7, pp. 1220, 2019.
[41] L. Liu, M. Zhan, and Y. Bai, “A recursive ensemble model for forecasting the power output of photovoltaic systems,” Solar Energy, vol. 189, pp. 291–298, 2019.
[42] D. Niu, K. Wang, L. Sun, J. Wu, and X. Xu, “Short-term photovoltaic power generation forecasting based on random forest feature selection and CEEMD: A case study,” Applied Soft Computing, vol. 93, pp. 106389, 2020.
[43] Y. Chen and D. Zhang, “Theory-guided deep-learning for electrical load forecasting (TGDLF) via ensemble long short-term memory,” Advances in Applied Energy, vol. 1, pp. 100004, 2021.
[44] I. Jebli, F.-Z. Belouadha, M. I. Kabbaj, and A. Tilioua, “Prediction of solar energy guided by Pearson Correlation Using Machine Learning,” Energy, vol. 224, pp. 120109, 2021.
[45] G. G. Kim, J. H. Choi, S. Y. Park, B. G. Bhang, W. J. Nam, H. L. Cha, N. S. Park, and H.-K. Ahn, “Prediction model for PV performance with Correlation Analysis of environmental variables,” IEEE Journal of Photovoltaics, vol. 9, no. 3, pp. 832–841, 2019.
[46] C. H. Goulden, Methods of statistical analysis. New York: Wiley, 1962.
[47] G. Perveen, M. Rizwan, and N. Goel, “Comparison of intelligent modelling techniques for forecasting solar energy and its application in solar PV based energy system,” IET Energy Systems Integration, vol. 1, no. 1, pp. 34–51, 2019.
[48] Y.-C. Huang, C.-M. Huang, S.-J. Chen, and S.-P. Yang, “Optimization of module parameters for PV power estimation using a hybrid algorithm,” IEEE Transactions on Sustainable Energy, vol. 11, no. 4, pp. 2210–2219, 2020.
[49] W. Lee, K. Kim, J. Park, J. Kim, and Y. Kim, “Forecasting solar power using long-short term memory and Convolutional Neural Networks,” IEEE Access, vol. 6, pp. 73068–73080, 2018.
[50] M. Massaoudi, I. Chihi, L. Sidhom, M. Trabelsi, S. S. Refaat, and F. S. Oueslati, “Enhanced random forest model for robust short-term photovoltaic power forecasting using weather measurements,” Energies, vol. 14, no. 13, pp. 3992, 2021.
[51] M. Pierro, D. Gentili, F. R. Liolli, C. Cornaro, D. Moser, A. Betti, M. Moschella, E. Collino, D. Ronzio, and D. van der Meer, “Progress in regional PV power forecasting: A sensitivity analysis on the Italian case study,” Renewable Energy, vol. 189, pp. 983–996, 2022.
[52] M. Massaoudi, I. Chihi, L. Sidhom, M. Trabelsi, S. S. Refaat, H. Abu-Rub, and F. S. Oueslati, “An effective hybrid NARX-LSTM model for point and interval PV Power Forecasting,” IEEE Access, vol. 9, pp. 36571–36588, 2021.
[53] Z. M. Li, S. Q. Bao, and Z. L. Gao, “Short term prediction of photovoltaic power based on FCM and CG-DBN combination,” Journal of Electrical Engineering & Technology, vol. 15, no. 1, pp. 333–341, 2019.
[54] U. F. Siddiqi and S. M. Sait, “A new heuristic for the data clustering problem,” IEEE Access, vol. 5, pp. 6801–6812, 2017.
[55] G. Cervone, L. Clemente-Harding, S. Alessandrini, and L. Delle Monache, “Short-term photovoltaic power forecasting using artificial neural networks and an analog ensemble,” Renewable Energy, vol. 108, pp. 274–286, 2017.
[56] B. Warsito, R. Santoso, Suparti, and H. Yasin, “Cascade Forward Neural Network for time series prediction,” Journal of Physics: Conference Series, vol. 1025, pp. 012097, 2018.
[57] A. Catalina, C. M. Alaiz, and J. R. Dorronsoro, “Combining numerical weather predictions and satellite data for PV Energy Nowcasting,” IEEE Transactions on Sustainable Energy, vol. 11, no. 3, pp. 1930–1937, 2020.
[58] B. Chen, P. Lin, Y. Lai, S. Cheng, Z. Chen, and L. Wu, “Very-short-term power prediction for PV power plants using a simple and effective RCC-LSTM model based on short term multivariate historical datasets,” Electronics, vol. 9, no. 2, pp. 289, 2020.
[59] G. Li, S. Xie, B. Wang, J. Xin, Y. Li, and S. Du, “Photovoltaic Power Forecasting with a hybrid deep learning approach,” IEEE Access, vol. 8, pp. 175871–175880, 2020.
[60] C.-J. Huang and P.-H. Kuo, “Multiple-input deep convolutional neural network model for short-term photovoltaic power forecasting,” IEEE Access, vol. 7, pp. 74822–74834, 2019.
[61] Z. Zhen, J. Liu, Z. Zhang, F. Wang, H. Chai, Y. Yu, X. Lu, T. Wang, and Y. Lin, “Deep learning based surface irradiance mapping model for solar PV power forecasting using Sky Image,” IEEE Transactions on Industry Applications, pp. 1–1, 2020.
[62] M. Khashei and M. Bijari, “An artificial neural network (p,D,Q) model for timeseries forecasting,” Expert Systems with Applications, vol. 37, no. 1, pp. 479–489, 2010.
[63] I. Khan, H. Zhu, D. Khan, and M. K. Panjwani, “Photovoltaic power prediction by Cascade Forward Artificial Neural Network,” 2017 International Conference on Information and Communication Technologies (ICICT), 2017.
[64] A. J. Smola and B. Schölkopf, “A tutorial on support vector regression,” Statistics and Computing, vol. 14, no. 3, pp. 199–222, 2004.
[65] S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural Computation, vol. 9, no. 8, pp. 1735–1780, 1997.
[66] C.-C. J. Kuo, “Understanding convolutional neural networks with a mathematical model,” Journal of Visual Communication and Image Representation, vol. 41, pp. 406–413, 2016.
[67] L. Sehovac and K. Grolinger, “Deep learning for load forecasting: Sequence to sequence recurrent neural networks with attention,” IEEE Access, vol. 8, pp. 36411–36426, 2020.
[68] Y. Wang, W. Liao, and Y. Chang, “Gated recurrent unit network-based short-term photovoltaic forecasting,” Energies, vol. 11, no. 8, pp. 2163, 2018.
[69] Y.-K. Wu, Y.-H. Lai, C.-L. Huang, N. T. Phuong, and W.-S. Tan, “Artificial Intelligence Applications in estimating invisible solar power generation,” Energies, vol. 15, no. 4, pp. 1312, 2022.
[70] A. Bajpai and M. Duchon, “A hybrid approach of solar power forecasting using machine learning,” 2019 3rd International Conference on Smart Grid and Smart Cities (ICSGSC), Berkeley, CA, USA, 25–28 June, 2019.
[71] L. Breiman, Random forests. Machine Learning, vol. 45, pp. 5–32, 2001.
[72] Y. Kim and J. Hur, “An ensemble forecasting model of wind power outputs based on improved statistical approaches,” Energies, vol. 13, no. 5, p. 1071, 2020.
[73] N. Tang, S. Mao, Y. Wang, and R. M. Nelms, “Solar power generation forecasting with a lasso-based approach,” IEEE Internet of Things Journal, vol. 5, no. 2, pp. 1090–1099, 2018.
[74] T. C. Carneiro, P. A. C. Rocha, P. C. M. Carvalho, and L. M. Fernández-Ramírez, “Ridge regression ensemble of machine learning models applied to solar and wind forecasting in Brazil and Spain,” Applied Energy, vol. 314, p. 118936, 2022.
[75] D. Tao, Q. Ma, S. Li, Z. Xie, D. Lin, and S. Li, “Support vector regression for the relationships between ground motion parameters and macroseismic intensity in the sichuan–yunnan region,” Applied Sciences, vol. 10, no. 9, pp. 3086, 2020.
[76] R. Marco, S. S. Ahmad, and S. Ahmad, “Bayesian hyperparameter optimization and Ensemble Learning for Machine Learning Models on software effort estimation,” International Journal of Advanced Computer Science and Applications, vol. 13, no. 3, pp. 419-429, 2022.
[77] Available online: https://toolkit.solcast.com.au/weather-sites/48bb-7a5e-a09e-227f/detail (accessed 25 March 2022).
[78] W. VanDeventer, E. Jamei, G. S. Thirunavukkarasu, M. Seyedmahmoudian, T. K. Soon, B. Horan, S. Mekhilef, and A. Stojcevski, “Short-term PV power forecasting using hybrid GASVM technique,” Renewable Energy, vol. 140, pp. 367–379, 2019.
[79] S. Leva, A. Nespoli, S. Pretto, M. Mussetta, and E. G. Ogliari, “PV plant power nowcasting: A real case comparative study with an open access dataset,” IEEE Access, vol. 8, pp. 194428–194440, 2020.
[80] X.-B. Jin, W.-Z. Zheng, J.-L. Kong, X.-Y. Wang, Y.-T. Bai, T.-L. Su, and S. Lin, “Deep-learning forecasting method for electric power load via attention-based encoder-decoder with bayesian optimization,” Energies, vol. 14, no. 6, pp. 1596, 2021.
[81] Y. Ren, P. N. Suganthan, and N. Srikanth, “Ensemble methods for wind and solar power forecasting—a state-of-the-art review,” Renewable and Sustainable Energy Reviews, vol. 50, pp. 82–91, 2015.
[82] L. Wang, S. Mao, B. M. Wilamowski and R. M. Nelms, "Ensemble Learning for Load Forecasting," IEEE Transactions on Green Communications and Networking, vol. 4, no. 2, pp. 616-628, 2020.
[83] Z. Chen and I. Koprinska, “Ensemble Methods for Solar Power Forecasting,” 2020 International Joint Conference on Neural Networks (IJCNN), Glasgow, UK, 19–24 July 2020.