隨著再生能源在電網中佔比提高，電力系統的可靠性將受到再生能源間歇供電。準確的太陽能預測能減少電力系統運行的不確定性，並提供電能管理系統進行最佳化排程控制。
本論文開發了一個結合天氣分類和動態雲影像追蹤的極短期太陽能發電預測模型，旨在提高太陽能發電預測的準確度。為了解決因雲層移動所造成太陽能發電的不穩定與不確定性，本論文提出了一個雲層覆蓋率預測模型。該模型利用稠密光流計算雲層運動的向量，從而實現對雲層覆蓋率的預測。此外，所提出的模型結合了雲層覆蓋率以及從Solcast天氣預報數據中提取的特徵作為輸入變數，應用於兩階段機器學習模型預測太陽能發電。
本論文所提出的模型在屏東的實際500 kWp太陽能發電廠進行了五個月的測試。研究結果顯示，該模型在不同預測時間範圍上優於其他模型，並且能夠預測太陽能發電的驟變。

The variability of PV power generation due to cloud movement would lead to sudden changes in power output, causing challenges in power system operation. Therefore, an accurate forecasting model for PV power generation is critical for the efficient operation and reliability of the power grid.
This thesis develops an ultra-short-term PV power forecasting model incorporating weather classification and dynamic cloud tracking. The research aims at improving the accuracy of fluctuant PV power generation forecasting to enable optimal scheduling and control of energy management systems. To address the issue of unpredictable fluctuations in PV power generation caused by changes in cloud cover, this thesis proposes a cloud-coverage ratio forecasting model. The model utilizes dense optical flow to compute the speed of cloud movement, enabling the prediction of cloud-coverage ratio. Additionally, the proposed model integrates the input features extracted from Solcast weather forecasting data for a two-stage machine learning model, which is used to predict PV power.
The effectiveness of the proposed model has been tested in an actual 500-kWp PV power plant located in Pingtung. The results of the study reveal that the proposed model outperforms other models with different forecasting time horizons and provides precise predictions for sudden changes in PV power.

[1] 經濟部能源局,“推動能源轉型「展綠、增氣、減煤、非核」,” [Online].Available:https://www.moea.gov.tw/MNS/populace/Policy/Policy.aspx?menu_id=32800&policy_id=9[Accessed Mar. 2023].
[2] 吳進忠與鄭宇軒, “大量再生能源併網的衝擊與電力調度因應策略,”中國工程師學會會刊, 93卷01期pp.79-90, 2020年3月.
[3] 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.
[4] 吳進忠,“再生能源預測對於電力調度的重要性,”財團法人中技社再生能源發電預測研討會, 2018年.
[5] R. Yan, T. K. Saha, P. Meredith, A. Ananth, and M. I. Hossain, “Megawatt‐Scale Solar Variability Study: An Experience From A 1.2 Mwp Photovoltaic System In Australia Over Three Years,”IET Renewable Power Generation, vol. 10, no. 8, pp. 1229-1236, 2016.
[6] J. Sharma, S. Soni and P. Paliwal et al.,“A Novel Long Term Solar Photovoltaic Power Forecasting Approach Using LSTM with Nadam Optimizer: A Case Study Of India,”Energy Science & Engineering, vol. 10, no. 8, pp. 2909-2929, 2022.
[7] F. Wang, Z. Zhang, and H. Chai et al.,“Deep Learning Based Irradiance Mapping Model for Solar PV Power Forecasting Using Sky Image,”2019 IEEE Industry Applications Society Annual Meeting, Baltimore, MD, USA, 2019.
[8] A. S. Rodrigo, M. Franco, D. Liber, and L. Agustin,“Satellite-Based Operational Solar Irradiance Forecast for Uruguay's Solar Power Plants,”2021 Ieee Urucon, 2021.
[9] Q. T. Phan, Y. K. Wu, and Q. D. Phan,“Short-Term Solar Power Forecasting Using XGBoost with Numerical Weather Prediction,” 2021 IEEE International Future Energy Electronics Conference, 2021.
[10] S. Pelland, J. Remund, J. Kleissl, T. Oozeki, and K. D. Brabandere, “Photovoltaic and Solar Forecasting: State of The Art,”IEA PVPS Task, 14, 1-36, 2013.
[11] P. A. G. M. Amarasinghe, N. S. Abeygunawardana, T. N. Jayasekara, E. A. J. P. Edirisinghe, and S. K. Abeygunawardane,“Ensemble Models for Solar Power Forecasting—A Weather Classification Approach,”AIMS Energy, vol. 8, no. 2, pp. 252-271, 2020.
[12] M. J. Sanjari and H. B. Gooi,“Probabilistic Forecast of PV power Based on Higher Order Markov Chain,”IEEE Transactions on Power Systems, vol. 32, no. 4, pp. 2942-2952, 2017.
[13] C. W. Chow, S. Belongie, and J. Kleissl,“Cloud Motion and Stability Estimation for Intra-Hour Solar Forecasting,”Solar Energy, vol. 115, pp. 645-655, 2015.
[14] Z. Si, Y. Yu, M. Yang, and P. Li,“Hybrid Solar Forecasting Method Using Satellite Visible Images and Modified Convolutional Neural Networks,”IEEE Transactions on Industry Applications, vol. 57, no. 1, pp. 5-16, 2021.
[15] L. Cheng, H. Zang, Z. Wei, T. Ding, R. Xu, and G. Sun,“Short-Term Solar Power Prediction Learning Directly from Satellite Images with Regions of Interest,”IEEE Transactions on Sustainable Energy, vol. 13, no. 1, pp. 629-639, 2022.
[16] F. Wang, J. Li, and Z. Zhen et al.,“Cloud Feature Extraction and Fluctuation Pattern Recognition Based Ultrashort-Term Regional PV Power Forecasting,”IEEE Transactions on Industry Applications, vol. 58, no. 5, pp. 6752-6767, 2022.
[17] 中央氣象局,“中央氣象局產品說明文件紅外線黑白、彩色及色調強化雲圖,”2021年8月.
[18] 中央氣象局,“中央氣象局產品說明文件可見光黑白雲圖,” 2021年5月.
[19] Satellite Program Division, Japan Meteorological Agency, “Meteorological Satellites,”Mar. 2023. [Online] Available: https://www.jma.go.jp/jma/jma-eng/satellite/himawari89.html.
[20] M. S. Ghonima, B. Urquhart, C. W. Chow, J. E. Shields, A. Cazorla, and J. Kleissl,“A Method for Cloud Detection and Opacity Classification Based on Ground Based Sky Imagery,”Atmospheric Measurement Techniques, vol. 5, no. 11, pp. 2881-2892, 2012.
[21] C. Feng, M. Cui, B. M. Hodge, S. Lu, H. F. Hamann, and J. Zhang, “Unsupervised Clustering-Based Short-Term Solar Forecasting,” IEEE Transactions on Sustainable Energy, vol. 10, no. 4, pp. 2174-2185, 2019.
[22] H. Wen, D. Yang, and X. Chen et al.,“Deep Learning Based Multistep Solar Forecasting for PV Ramp-Rate Control Using Sky Images,”IEEE Transactions on Industrial Informatics, vol. 17, no. 2, pp. 1397-1406, 2021.
[23] Z. Zhen, J. Liu, and Z. Zhang et al.,“Deep Learning Based Surface Irradiance Mapping Model for Solar PV Power Forecasting Using Sky Image,”IEEE Transactions on Industry Applications, pp. 1-1, 2020.
[24] R. Zhang, H. Ma, T. K. Saha, and X. Zhou,“Photovoltaic Nowcasting with Bi-Level Spatio-Temporal Analysis Incorporating Sky Images,”IEEE Transactions on Sustainable Energy, vol. 12, no. 3, pp. 1766-1776, 2021.
[25] A. SYSTEM,“ALPHEA "All Sky" Camera: Installation and User Manual,”Mar. 2018. [Online]. Available: http://www.alcor‐system.com/us/AllSkyCamera/softwares.html.
[26] J. M. Bright,“Solcast: Validation of A Satellite-Derived Solar Irradiance Dataset,”Solar Energy, vol. 189, pp. 435-449, 2019.
[27] J. Benesty, J. Chen, Y. Huang, and I. Cohen,“Pearson Correlation Coefficient,”Noise Reduction in Speech Processing, Springer Topics in Signal Processing, ch. Chapter 5, pp. 1-4, 2009.
[28] N. Shrestha,“Detecting Multicollinearity in Regression Analysis,” American Journal of Applied Mathematics and Statistics, vol. 8, no. 2, pp. 39-42, 2020.
[29] J. Stein, C. Hansen, and M. Reno,“Global Horizontal Irradiance Clear-sky Models : Implementation and Analysis,”Sandia National Laboratories, Albuquerque, NM, and Livermore, CA, 2012.
[30] M. Awad and R. Khanna,“Support Vector Regression,”Efficient learning machines: Theories, concepts, and applications for engineers and system designers, 2015.
[31] A. Karpathy, J. Johnson, and F. F. Li,“Visualizing and Understanding Recurrent Networks,”arXiv preprint, 2015.
[32] S. Hochreiter and J. Schmidhuber,“Long Short-Term Memory,” Neural Computation, 1997
[33] X. Li, Z. Lu, Q. Zhou, and Z. Xu, “A Cloud Detection Algorithm with Reduction of Sunlight Interference in Ground-Based Sky Images,”Atmosphere, vol. 10, no. 11, 2019.
[34] 王金印,“太陽能預測模式與分析技術研究,”行政院原子能委員會委託研究計畫研究報告, 2014年11月.
[35] G. Farneback,“Two-Frame Motion Estimation Based on Polynomial Expansion,”Image Analysis: 13th Scandinavian Conference, SCIA 2003 Halmstad, Sweden, 2003.
[36] D. P. Igoe, A. V. Parisi, and N. J. Downs,“Cloud Segmentation Property Extraction from Total Sky Image Repositories Using Python,” Instrumentation Science & Technology, vol. 47, no. 5, pp. 522-534, 2019.
[37] R. M. Haralick, S. R. Sternberg, and X. Zhuang,“Image Analysis Using Mathematical Morphology,”IEEE Transactions on Pattern Analysis and Machine Intelligence, 1987.
[38] W. F. Holmgren, C. W. Hansen, and M. A. Mikofski,“Pvlib Python: A Python Package for Modeling Solar Energy Systems,”Journal of Open Source Software, vol. 3, no. 29, 2018.
[39] A. A. H. Lateko, H. T. Yang,and C.-M. Huang et al.,“Stacking Ensemble Method with The RNN Meta-Learner for Short-Term PV Power Forecasting,”Energies, vol. 14, no. 16, 2021.
[40] Y. J. Zhong and Y. K. Wu,“Short-Term Solar Power Forecasts Considering Various Weather Variables,”2020 International Symposium on Computer, Consumer and Control, 2020.
[41] A. F. Romero, F. L. Quilumba and H. N. Arcos, "Short-Term Active Power Forecasting of A Photovoltaic Power Plant Using An Artificial Neural Network," 2017 IEEE Second Ecuador Technical Chapters Meeting (ETCM), 2017.
[42] H. He, R. Hu, Y. Zhang, Y. Zhang and R. Jiao, "A Power Forecasting Approach for PV Plant Based on Irradiance Index and LSTM," 2018 37th Chinese Control Conference (CCC), 2018.
[43] A. Alfadda, R. Adhikari, M. Kuzlu and S. Rahman, "Hour-ahead Solar PV Power Forecasting Using SVR Based Approach," 2017 IEEE Power & Energy Society Innovative Smart Grid Technologies Conference (ISGT), 2017.
[44] G. Wang, M. Yang and Y. Yu, "A Short-Term Forecasting Method for Photovoltaic Power Based on Ensemble Adaptive Boosting Random Forests," 2020 IEEE/IAS 56th Industrial and Commercial Power Systems Technical Conference (I&CPS), 2020.
[45] S. Tiwari, R. Sabzehgar and M. Rasouli, "Short Term Solar Irradiance Forecast Using Numerical Weather Prediction (NWP) with Gradient Boost Regression," 2018 9th IEEE International Symposium on Power Electronics for Distributed Generation Systems (PEDG), 2018.