近年來再生能源發展日益興旺，太陽能作為可持續性發展能源。其發電量與日射量成正關，如能建立一穩定且準確的日射量預測，可加強對緊急狀況之應變能力。在眾多類神經網路類型當中循環神經網路(RNN)已發展多年，其中長短期記憶網路(LSTM)更是被大量使用於具時間序列特性之日射量預測。近年來有學者提出新型態類神經網路模型Transformer，雖其最初目的為語言辨識但因與RNN相似之特性也被大量使用於時間序列之預測。過往之日射量研究多以LSTM為主，然而Transformer模型具有不會梯度爆炸且可同時從多個序列獲取資訊等優點，故本論文嘗試提出一基於Transformer網路為架構之日射量預測模型並以多種效能評估指標與LSTM進行比較。此外，從過往研究可知天氣狀況對日射量有顯著之影響，因此本論文輔以隨機森林(random forest)對數據先進行分類以加強訓練精確度。實驗結果顯示Transformer有不亞於LSTM的預測準確率，在某些指標甚至更勝LSTM。

In recent years, the development of renewable energy has become increasingly prosperous, and solar energy is used as a sustainable energy source. Its power generation is directly related to the amount of sun irradiance .The recurrent neural network (RNN) has been developed for many years, and the long-short-term memory network (LSTM) is widely used in the prediction of sunlight with time series characteristics. In recent years, some scholars have proposed a new type of neural network model Transformer. It is widely used in time series prediction due to its similar characteristics to RNN. In the past, LSTM was mainly used in the research of sunshine amount, but the Transformer model has the advantages of no gradient explosion and the ability to obtain information from multiple sequences at the same time. This study attempts to propose a sunshine forecast model based on the Transformer network and compares it with LSTM with various performance evaluation indicators. In addition, it is known from previous studies that weather conditions have a significant impact on the amount of sunshine, so this study supplemented with Random Forest to classify the data first to enhance the accuracy of training. Experiments show that Transformer has a prediction accuracy rate no less than LSTM, and even better in some indicators .

[1] Hsiao, K. Huang, and Y. Chang, "A model for forecasting of solar power annual electricity and its strategy application," Journal of Taiwan Energy, vol. 4, no. 4, pp. 01-430, 2017.
[2] M. Q. Raza, M. Nadarajah, and C. Ekanayake, "On recent advances in PV output power forecast," Solar Energy, vol. 136, pp. 125-144, 2016.
[3] J. X. Yeo, Y. H. Lee, and J. T. Ong, "Performance of site diversity investigated through RADAR derived results," IEEE Transactions on Antennas and Propagation, vol. 59, no. 10, pp. 3890-3898, 2011.
[4] S. Sun et al, "Short term cloud coverage prediction using ground based all sky imager," in 2014 IEEE international conference on smart grid communications (SmartGridComm), 2014: IEEE, pp. 121-126.
[5] M. Z. Hassan, M. E. K. Ali, A. S. Ali, and J. Kumar, "Forecasting day-ahead solar radiation using machine learning approach," in 2017 4th Asia-Pacific World Congress on Computer Science and Engineering (APWC on CSE), 2017: IEEE, pp. 252-258.
[6] P. Kumari ,D. Toshiwal, "Deep learning models for solar irradiance forecasting : A comprehensive review," Journal of Cleaner Production, vol.318 ,128566 ,2021.
[7] C .W. Chow, B. Urquart, "Intra-hour forecasting with a total sky imager at the UC San Diego solar energy tested, "Sol Energy vol.85, no. 11, pp. 2881-2893, 2011.
[8] D. Yang, Z.Ye, "Very short term irradiance forecasting using the lasso, "Sol Energy vol.114, pp. 314-316, 2015.
[9] N. Engerer , "Minute resolution estimates of the diffuse fraction of global irradiance for southeastern Australia, " Sol Energy vol.116, pp. 215-237, 2015.
[10] H. Jiang, Y. Dong, L. Xiao, "A multi_stage intelligent approach based on an ensemble of two-way interaction model for forecasting the global horizontal radiation of India, " Energy Convers Manage, vol. 137, pp. 142-154, 2017.
[11] L. Olatomiwa, "A support vector machine-firefly algorithm-based model for global solar radiation prediction" Sol Energy vol.115, pp. 632-644, 2015.
[12] X. Shao, S. Lu, and H. F. Hamann, "Solar radiation forecast with machine learning," in 2016 23rd International Workshop on Active-Matrix Flatpanel Displays and Devices (AM-FPD), 2016: IEEE, pp. 19-22.
[13] A. Alzahrani, P. Shamsi, M. Ferdowsi, and C. Dagli, "Solar irradiance forecasting using deep recurrent neural networks," in 2017 IEEE 6th international conference on renewable energy research and applications (ICRERA), 2017: Ieee, pp. 988-994.
[14] S. Mishra and P. Palanisamy, "Multi-time-horizon solar forecasting using recurrent neural network," in 2018 IEEE Energy Conversion Congress and Exposition (ECCE), 2018: IEEE, pp. 18-24.
[15] S. Srivastava and S. Lessmann, "A comparative study of LSTM neural networks in forecasting day-ahead global horizontal irradiance with satellite data," Solar Energy, vol. 162, pp. 232-247, 2018.
[16] X. Qing and Y. Niu, "Hourly day-ahead solar irradiance prediction using weather forecasts by LSTM," Energy, vol. 148, pp. 461-468, 2018.
[17] K. Chen, Z. He, K. Chen, J. Hu, and J. He, "Solar energy forecasting with numerical weather predictions on a grid and convolutional networks," in 2017 IEEE Conference on Energy Internet and Energy System Integration (EI2), 2017: IEEE, pp. 1-5.
[18] X. Yang, F. Jiang, and H. Liu, "Short-term solar radiation prediction based on SVM with similar data," in 2nd IET Renewable Power Generation Conference (RPG 2013), 2013: IET, pp. 1-4.
[19] H. S. Jang, K. Y. Bae, H.-S. Park, and D. K. Sung, "Solar power prediction based on satellite images and support vector machine," IEEE Transactions on Sustainable Energy, vol. 7, no. 3, pp. 1255-1263, 2016.
[20] A. Ulutaş, R. Çakmak, and İ. H. Altaş, "Hourly solar irradiation prediction by artificial neural network based on similarity analysis of time series," in 2018 Innovations in Intelligent Systems and Applications Conference (ASYU), 2018: IEEE, pp. 1-6.
[21] S. M. Ruffing and G. K. Venayagamoorthy, "Short to medium range time series prediction of solar irradiance using an echo state network," in 2009 15th International Conference on Intelligent System Applications to Power Systems, 2009: IEEE, pp. 1-6.
[22] H. Nazaripouya, B. Wang, Y. Wang, P. Chu, H. Pota, and R. Gadh, "Univariate time series prediction of solar power using a hybrid wavelet-ARMA-NARX prediction method," in 2016 IEEE/PES Transmission and Distribution Conference and Exposition (T&D), 2016: IEEE, pp. 1-5.
[23] R. Huang, T. Huang, R. Gadh, and N. Li, "Solar generation prediction using the ARMA model in a laboratory-level micro-grid," in 2012 IEEE third international conference on smart grid communications (SmartGridComm), 2012: IEEE, pp. 528-533.
[24] A. Katharopoulos, " Transformer are RNNs:Fast Autoregressive Transformer with Linear attention, ". arXiv, 2006.16236, 2020.
[25] N. Wu. "Deep Transformer Models for Time Series Forecasting :The influenza Prevalence Case ". arXiv, 2001.08317, 2020.
[26] Q. Wen , T.Zhou , " Transformers in Time Series: A Survey ," arXiv, 2202.07125, 2023.
[27] J. Pospichal, " Solar Irradiance Forecasting with Transformer Model ", Journal applied science, vol.12, iss.17, 2022.
[28] A. Vaswani, " Attention Is All You Need , " arXiv, 1706.03762, 2017.
[29] NREL Solar Radiation Research Laboratory (SRRL). ASI-16 Sky Imager gallery. 2017. Available online:
https://midcdmz.nrel.gov/apps/imagergallery.pl?SRRLASI.
[30] T. P. Chu, "Estimation of solar irradiance and solar power based on all-sky image" Solar Energy, vol. 249, pp. 495-506, 2023.
[31] S. Sun et al., "Short term cloud coverage prediction using ground based all sky imager," in 2014 IEEE international conference on smart grid communications (SmartGridComm), 2014: IEEE, pp. 121-126.
[32] A. Taravat, F. Del Frate, C. Cornaro, and S. Vergari, "Neural networks and support vector machine algorithms for automatic cloud classification of whole-sky ground-based images," IEEE Geoscience and remote sensing letters, vol. 12, no. 3, pp. 666-670, 2014.
[33] F. Xie, M. Shi, Z. Shi, J. Yin, and D. Zhao, "Multilevel cloud detection in remote sensing images based on deep learning," IEEE Journal of Selected Topics I Applied Earth Observations and Remote Sensing, vol. 10, no. 8, pp. 3631-3640, 2017.
[34] S. Sun, S. Wang, G. Zhang, J. Zheng, "A decomposition-clustering- Ensemble learning approach for solar radiation forecasting," Sol. Energy 163, 189–199,2018
[35] L. M. Aguiar, B. Pereira. P. Lauret, F. Diaz, M. David, "Combining solar irradiance measurements, satellite-derived data and a numerical weather prediction model to improve intra-day solar forecasting, " Renew. Energy 97, 599–610,2016.
[36] P. Kumari, R. Wadhvani, "Wind power prediction using KLMS algorithm, " In:2018 International Conference on Inventive Research in Computing Applications (ICIRCA). IEEE, pp. 154–161,2018.
[37] G. Corea, " Forecasting short-term solar irradiance based on artificial neural networks and data from neighboring meteorological stations, " Sol. Energy 134, 119–131,2016.
[38] M. Ozgoren, M. Bilgili, B. Sahin, " Estimation of global solar radiation using ANN over Turkey, " Expert Syst. Appl. 39 (5), 5043–5051,2012.
[39] S. Srivastava , S. Lessmann, "A comparative study of LSTM neural networks in forecasting day-ahead global horizontal irradiance with satellite data," Solar Energy, vol. 162, pp. 232-247, 2018.
[40] X. Qing ,Y. Niu, "Hourly day-ahead solar irradiance prediction using weather forecasts by LSTM," Energy, vol. 148, pp. 461-468, 2018.
[41] N. Singh , S.Jena ," A novel application of Decision Tree classifier in solar irradiance prediction," Materials Today:Proceedings , vol.58 , pp 316-323, 2022.
[42] I. Arora, " Solar Irradioance Forecasting using Decision Tree and Ensemble Models ," Proceeding of the second international conference on inventive research in computing applications , 2020.
[43] F. Wang, Z. Zhang, H. Chai, Y. Yu, X .Lu, T. Wang, Y .Lin, " Deep learning based irradiance mapping model for solar PV power forecasting using sky image, " In: 2019 IEEE Industry Applications Society Annual Meeting. IEEE, pp. 1–9,2019.
[44] T. Peng, C. Zhang, J. Zhou, M. S. Nazir, "An integrated framework of Bidirectional long-short term memory (BiLSTM) based on sine cosine algorithm for hourly solar radiation forecasting," Energy 119887,2021.
[45] T. McCandless, S. Haupt, G. Young, "A regime-dependent artificial neural network technique for short-range solar irradiance forecasting, " Renew Energy 89, 351–359,2016.
[46] J. H. Guo, " A system for predicting and estimating solar irradiance based on satellite cloud image with superpixel segmentation, " Master’s Thesis , 2022
[47] A. AL-iahham, " Sky Imager-Based Forecast of Solar Irradiance Using Machine Learning," Electronics ,vol. 9 , issus 1700, 2020.
[48] A. Nespoli, " Machine Learning techniques for solar irradiation nowcasting : Cloud type classification forecast through satellite data and imagery, " Applied Energy , vol.305 , 2022.