近年來，隨著全球環保意識的抬頭，再生能源在電網中的占比逐漸提高，太陽能發電作為其中的代表之一，目前已被廣泛使用，然而，太陽能發電受氣候影響使其供電存在不穩定性，勢必對電力系統的運行產生挑戰。準確的太陽能發電預測可降低再生能源供電的不確定性，預測結果除了有助於電網運行提高供電可靠度外，亦能有效協助電能管理系統進行最佳化排程。
本文提出結合衛星雲圖、數值天氣預報以及歷史發電量之日內滾動太陽能發電預測方法，旨在提高短期太陽能發電預測的準確性。所提方法將預測分為兩個時段，以因應衛星雲圖在日內的亮度變化，同時考慮不同時間天氣預報的不確定性，於每個滾動時間分別訓練合適的模型。此外所提方法採用混合式設計之預測模型，以多種卷積神經網路提取影像與數值資料之特徵，並使用粒子群最佳化演算法，最佳化影像與數值資料之輸入參數。
本文以屏東實際發電裝置容量為500kWp太陽能發電場資料進行測試。為評估所提方法的預測表現，隨機抽取各季中一個月的發電資料代表該季，比較所提方法與長短期記憶網路、門控循環單元等時間序列模型之預測結果。結果顯示，所提方法在各季代表月的預測表現皆優於其他方法，並且隨著時間的推移，可以逐漸修正太陽能發電量的預測值，有效提升預測準確度。

In recent years, with the rise of global environmental awareness, the proportion of renewable energy in the power grid is gradually increasing. PV power, as one of the representatives, has been widely used. However, PV power is affected by weather conditions, leading to instability in its power supply, which inevitably poses challenges to the operation of power systems. Accurate PV power forecasting can reduce the uncertainty of renewable energy power supply, and the forecasting results not only help improve the reliability of power grid operations but also effectively assist energy management systems (EMS) in optimizing scheduling.
This thesis proposes an intra-day rolling PV power forecasting method that combines satellite images, numerical weather prediction (NWP), and historical power generation. aiming to improve the accuracy of short-term PV power forecasting. The proposed method divides the prediction into two periods to accommodate the brightness changes of satellite images during the day and considers the uncertainties of weather forecasts at different times, training suitable models at each rolling time. Additionally, the proposed method adopts a hybrid design forecasting model that uses multiple convolutional neural networks (CNNs) to extract features from image and numerical data and employs a particle swarm optimization (PSO) algorithm to optimize the input parameters of image and numerical data.
In this thesis, the proposed method is tested on an actual PV power plant with capacity of 500kWp in Pingtung. To evaluate the forecasting performance of the proposed method, one month's generation data from each season is randomly selected to represent that season, and the forecasting results of the proposed method are compared with those of other time series models, including Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU). The results show that the proposed method outperforms the other methods in the representative month of each season, and can gradually modify the predicted value of PV power over time, which effectively improves the accuracy of the prediction.

[1] 經濟部，能源轉型白皮書，2020年11月。
[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第93卷01期，頁79-90，2020年3月。
[3] Energy Institute, “Statistical Review of World Energy,” Jun. 2023, [Online]. Available: https://www.energyinst.org/statistical-review [Accessed 2 Jun. 2024].
[4] J. Antonanzas, N. Osorio, R. Escobar, R. Urraca, F. J. Martinez-de-Pison, and F. Antonanzas-Torres, “Review of Photovoltaic Power Forecasting,” Solar Energy, vol. 136, pp. 78-111, Oct. 2016.
[5] 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。
[6] 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, Sept. 2016.
[7] W. Su, S. S. Yu, H. Li, H. H. -C. Iu, and T. Fernando, “An MPC-Based Dual-Solver Optimization Method for DC Microgrids with Simultaneous Consideration of Operation Cost and Power Loss,” IEEE Transactions on Power Systems, vol. 36, no. 2, pp. 936-947, Mar. 2021.
[8] M. J. Reno, C. W. Hansen, and J. S. Stein, “Global Horizontal Irradiance Clear-Sky Models : Implementation and Analysis,” Sandia National Laboratories, Albuquerque, NM, and Livermore, CA, Mar. 2012.
[9] 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, Apr. 2018.
[10] 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, Jun. 2019.
[11] 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, Sept. 2020.
[12] M. N. Akhter, S. Mekhilef, H. Mokhlis, and N. M. 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, May 2019.
[13] Q. T. Phan, Y. K. Wu, Q. D. Phan, and H. Y Lo, “A Novel Forecasting Model for Solar Power Generation by a Deep Learning Framework with Data Preprocessing and Postprocessing,” IEEE Transactions on Industry Applications, vol. 59, no. 1, pp. 220-231, Jan.-Feb. 2023.
[14] 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, Jul. 2021.
[15] T. Yao et al., “Intra-Hour Photovoltaic Generation Forecasting Based on Multi-Source Data and Deep Learning Methods,” IEEE Transactions on Sustainable Energy, vol. 13, no. 1, pp. 607-618, Jan. 2022.
[16] 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, May 2020.
[17] Z. Wang, L. Wang, C. Huang, and X. Luo, “A Hybrid Ensemble Learning Model for Short-Term Solar Irradiance Forecasting Using Historical Observations and Sky Images,” IEEE Transactions on Industry Applications, vol. 59, no. 2, pp. 2041-2049, Mar.-Apr. 2023.
[18] H. Wen 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, Feb. 2021.
[19] Z. Zhen et al., “Deep Learning Based Surface Irradiance Mapping Model for Solar PV Power Forecasting Using Sky Image,” IEEE Transactions on Industry Applications, vol. 56, no. 4, pp. 3385-3396, Jul.-Aug. 2020.
[20] M. Caldas and R. Alonso-Suárez, “Very Short-Term Solar Irradiance Forecast Using All-Sky Imaging and Real-Time Irradiance Measurements,” Renewable Energy, vol. 143, pp. 1643-1658, Dec. 2019.
[21] H. Yang, B. Kurtz, D. Nguyen, B. Urquhart, C. W. Chow, M. Ghonima, and J. Kleissl, “Solar Irradiance Forecasting Using a Ground-Based Sky Imager Developed at UC San Diego,” Solar Energy, vol. 103, pp. 502-524, May 2014.
[22] S. Pelland, J. Remund, J. Kleissl, T. Oozeki, and K. D. Brabandere, “Photovoltaic and Solar Forecasting: State of the Art,” IEA PVPS Task 14, pp. 1-36, Oct. 2013.
[23] Z. Si, M. Yang, Y. Yu, and T. Ding, “Photovoltaic Power Forecast Based on Satellite Images Considering Effects of Solar Position,” Applied Energy, vol. 302, Nov. 2021.
[24] J. Qin, H. Jiang, N. Lu, L. Yao, and C. Zhou, “Enhancing Solar PV Output Forecast by Integrating Ground and Satellite Observations with Deep Learning,” Renewable and Sustainable Energy Review, vol. 167, Oct. 2022.
[25] F. Wang 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, Sept.-Oct. 2022.
[26] 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, Jan. 2022.
[27] Y. Lecun, L. Bottou, Y. Bengio, and P. Haffner, “Gradient-Based Learning Applied to Document Recognition,” Proceedings of the IEEE, vol. 86, no. 11, pp. 2278-2324, Nov. 1998.
[28] J. Kennedy and R. Eberhart, “Particle Swarm Optimization,” Proceedings of ICNN'95 - International Conference on Neural Networks, Perth, WA, Australia, vol.4, pp. 1942-1948, Nov.-Dec. 1995.
[29] C. Brester, V. Kallio-Myers, A. V. Lindfors, M. Kolehmainen, and H. Niska, “Evaluating Neural Network Models in Site-Specific Solar PV Forecasting Using Numerical Weather Prediction Data and Weather Observations,” Renewable Energy, vol. 207, pp. 266-274, May 2023.
[30] J. G. Moreno-Torres, T. Raeder, R. Alaiz-Rodríguez, N. V. Chawla, and F. Herrera, “A Unifying View on Dataset Shift in Classification,” Pattern Recognition, vol. 45, no. 1, pp. 521-530, Jan. 2012.
[31] J. Shi, W. -J. Lee, Y. Liu, Y. Yang, and P. Wang, “Forecasting Power Output of Photovoltaic Systems Based on Weather Classification and Support Vector Machines,” IEEE Transactions on Industry Applications, vol. 48, no. 3, pp. 1064-1069, May-Jun. 2012.
[32] H. Zhou, Y. Zhang, L. Yang, Q. Liu, K. Yan, and Y. Du, “Short-Term Photovoltaic Power Forecasting Based on Long Short Term Memory Neural Network and Attention Mechanism,” IEEE Access, vol. 7, pp. 78063-78074, Jun. 2019.
[33] P. Jia, H. Zhang, X. Liu, and X. Gong, “Short-Term Photovoltaic Power Forecasting Based on VMD and ISSA-GRU,” IEEE Access, vol. 9, pp. 105939-105950, Jul. 2021.