簡易檢索 / 詳目顯示

研究生: 陳家豪
Chen, Chia-Hao
論文名稱: 基於深度學習之光流法應用於全天空影像之日射量估計與預測
Solar Irradiance Estimation and Prediction Based On Deep Learning Optical Flow Method Applied to All-Sky Images
指導教授: 呂藝光
Leu, Yih-Guang
口試委員: 鄭錦聰
Jeng, Jin-Tsong
吳政郎
Wu, Jenq-Lang
陶金旺
Tao, Chin-Wang
莊鎮嘉
Chuang, Chen-Chia
呂藝光
Leu, Yih-Guang
口試日期: 2023/07/14
學位類別: 碩士
Master
系所名稱: 電機工程學系
Department of Electrical Engineering
論文出版年: 2023
畢業學年度: 111
語文別: 中文
論文頁數: 85
中文關鍵詞: 深度學習卷積神經網路全天空影像光流法長短期記憶
英文關鍵詞: Deep learning, convolution neural network, all-sky images, optical flow, LSTM
DOI URL: http://doi.org/10.6345/NTNU202301271
論文種類: 學術論文
相關次數: 點閱:92下載:4
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報
  • 因應太陽能發電日益重要,又因太陽能發電量受制於日射量的影響,同時考量太陽能發電是間歇性的能源,故提出一種基於深度學習光流應用於全天空影像之日射量估計與預測的方法。由於日射量變化容易受到天氣狀況影響,本文藉由全天空影像,建立一個以影像特徵為基礎之日射量估計與預測系統,其影像特徵包括,利用紅藍比例法計算影像中雲層比例、雲層厚度,及藉太陽位置演算法得到影像中太陽位置,分析太陽附近雲層特徵,萃取全域與局部的雲層權重。同時用基於深度學習的光流法推算雲層移動的狀態,並製作未來數分鐘之天空預測圖像,將這些預測圖像作長短期記憶(LSTM)之輸入特徵,日射量作為訓練輸出,其深度學習光流法是透過卷積神經網路來實現。
    本文將資料集區分為月、季、半年與一年,分別進行10分鐘至60分鐘的日射量預測。同時,本文使用多個效能指標評估效果,包括平均絕對誤差(Mean Absolute Error)、均方根誤差(Root Mean Square Error)與判定係數(R^2)。最後,與文獻的方法進行比較,本文所提的方法具有較好的結果。

    Due to the increasing importance of solar power generation, the fact that solar power generation is affected by the amount of solar irradiance, and the fact that solar power is an intermittent energy source, the study of solar irradiance estimation and prediction based on deep learning optical flow method is presented. Since the change of solar irradiance is easily affected by the weather conditions, this study utilizes the all-sky images to establish a system for estimating and predicting solar irradiance by analyzing and processing image features. Meanwhile, the deep learning optical flow method implemented using convolutional neural network is used to predict cloud movement states and generate future sky images which are used as input features for LSTM.
    In this study, we categorize the datasets into monthly, quarterly, semiannual, and annual datasets and predict the irradiance for the next 10 minutes to 60 minutes, respectively. In order to illustrate the validity of the predictions and estimates, several performance metrics, including MAE, RMSE and R^2, are used. Finally, the proposed method is compared with several methods in the literature and the results show better performance.

    第一章 緒論 1 1.1研究動機與背景 1 1.2研究目的 2 1.3研究方法 2 1.4論文架構 3 第二章 文獻探討與回顧 4 2.1 圖像處理 4 2.2 光流法的應用 4 2.3 日射量估計與預測及模型的應用 5 第三章 日射量估計系統設計 7 3.1日射量估計之系統架構 8 3.2全天空影像 9 3.3紅藍比例法 10 3.4太陽位置演算法 11 3.4.1太陽軌跡模型 11 3.4.1.1 太陽時間 11 3.4.1.2 太陽高度角(θe)與太陽方位角(θa) 12 3.4.2 太陽中心區域剪裁 13 3.4.2.1 太陽座標空間轉換 13 3.4.2.2 倒傳遞演算法(Back Propagation, BP) 14 3.5影像處理與特徵資料處理流程 16 3.5.1 太陽區域雲權重 17 3.5.1.1 太陽面積消除 17 3.5.1.2 反距離權重(Inverse Distance Weighting, IDW) 17 3.4.1.3 太陽區域權重計算 18 3.5.2 全域權重 19 3.6長短期記憶(LSTM)模型 20 3.7性能指標 22 第四章 日射量預測系統設 23 4.1日射量預測之系統架構圖 23 4.2光流法 24 4.2.1 Lucas-Kanade 光流法 25 4.2.2卷積神經網路 (Convolution Neural Network) 27 4.2.3 基於Convolution Neural Network實現光流估計 29 4.3製造預測影像 32 第五章 實驗設計與結果 35 5.1資料集 36 5.2日射量估計 37 5.3 預測影像之雲相似性 41 5.3.1 全域雲相似性 41 5.3.2 區域雲相似性 43 5.4 日射量預測 45 5.4.1 以月份區分資料集 47 5.4.1.1 兩種光流特徵於領前10分鐘的日射量評估指標 48 5.4.1.2 兩種光流特徵於領前20分鐘的日射量評估指標 50 5.4.1.3 兩種光流特徵於領前30分鐘的日射量評估指標 52 5.4.1.4 兩種光流特徵於領前40分鐘的日射量評估指標 54 5.4.1.5 兩種光流特徵於領前50分鐘的日射量評估指標 56 5.4.1.6 兩種光流特徵於領前60分鐘的日射量評估指標 58 5.4.2 以季/半年/一年區間資料集 60 5.4.2.1 兩種光流特徵於領前10分鐘的日射量評估指標 61 5.4.2.2 兩種光流特徵於領前20分鐘的日射量評估指標 63 5.4.2.3 兩種光流特徵於領前30分鐘的日射量評估指標 65 5.4.2.4 兩種光流特徵於領前40分鐘的日射量評估指標 67 5.4.2.5 兩種光流特徵於領前50分鐘的日射量評估指標 69 5.4.2.6 兩種光流特徵於領前60分鐘的日射量評估指標 71 5.4.3 日射量預測之性能比較 73 5.5 光流效能的比較 76 第六章 結論與未來展望 77 6.1結論 77 6.2未來展望 78 參 考 文 獻 79

    [1] International Energy Agency (2022). Energy Efficiency 2022. https://iea.org/reports/energy-efficiency-2022
    [2] J. Almorox, C. Voyant, N. Bailek, A. Kuriqi, and J. A. Arnaldo, "Total solar irradiance's effect on the performance of empirical models for estimating global solar radiation: An empirical-based review," Energy, vol. 236, 2021.
    [3] J. Ospina et al., "Sampling-Based Model Predictive Control of PV-Integrated Energy Storage System Considering Power Generation Forecast and Real-Time Price," IEEE Power and Energy Technology Systems Journal, vol. 6, no. 4, pp. 195-207, 2019.
    [4] M. Shafiullah, S. D. Ahmed, and F. A. Al-Sulaiman, "Grid Integration Challenges and Solution Strategies for Solar PV Systems: A Review," IEEE Access, vol. 10, pp. 52233-52257, 2022.
    [5] Y. Liu, W. Wu, M. P. Jensen, and T. Toto, "Relationship between cloud radiative forcing, cloud fraction and cloud albedo, and new surface-based approach for determining cloud albedo," Atmos. Chem. Phys., vol. 11, no. 14, pp. 7155-7170, 2011.
    [6] L. Nonnenmacher and C. F. M. Coimbra, "Streamline-based method for intra-day solar forecasting through remote sensing," Solar Energy, vol. 108, pp. 447-459, 2014.
    [7] M. E. K. A. M. Z. Hassan, A. B. M. S. Ali and J. Kumar, "Forecasting Day-Ahead Solar Radiation Using Machine Learning Approach," 2017 4th Asia-Pacific World Congress on Computer Science and Engineering (APWC on CSE), Mana Island, Fiji, 2017.
    [8] L. Huang, J. Kang, M. Wan, L. Fang, C. Zhang, and Z. Zeng, "Solar Radiation Prediction Using Different Machine Learning Algorithms and Implications for Extreme Climate Events," Frontiers in Earth Science, vol. 9, 2021.
    [9] W. Liu et al., "Use of physics to improve solar forecast: Part II, machine learning and model interpretability," Solar Energy, vol. 244, pp. 362-378, 2022
    [10] C. W. Chow et al., "Intra-hour forecasting with a total sky imager at the UC San Diego solar energy testbed," Solar Energy, vol. 85, no. 11, pp. 2881-2893, 2011.
    [11] Z. El Jaouhari, Y. Zaz and L. Masmoudi, "Cloud tracking from whole-sky ground-based images," 2015 3rd International Renewable and Sustainable Energy Conference (IRSEC), Marrakech, Morocco, 2015, pp. 1-5.
    [12] M. Chang, Y. Yao, G. Li, Y. Tong, et al., "Cloud tracking for solar irradiance prediction," 2017 IEEE International Conference on Image Processing (ICIP), Beijing, China, 2017, pp. 4387-4391.
    [13] Z. Zhen, F. Wang, Z. Mi, Y. Sun and H. Sun, "Cloud tracking and forecasting method based on optimization model for PV power forecasting," 2015 Australasian Universities Power Engineering Conference (AUPEC), Wollongong, NSW, Australia, 2015, pp. 1-4
    [14] 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, 2015.
    [15] B. G. Pierce, J. S. Stein, J. L. Braid, and D. Riley, "Cloud Segmentation and Motion Tracking in Sky Images," IEEE Journal of Photovoltaics, vol. 12, no. 6, pp. 1354-1360, 2022.
    [16] Y. Chen, R. Fan, M. Bilal, X. Yang, J. Wang, and W. Li, "Multilevel Cloud Detection for High-Resolution Remote Sensing Imagery Using Multiple Convolutional Neural Networks," ISPRS International Journal of Geo-Information, vol. 7, no. 5, 2018.
    [17] S. Sun, E. Ritzhaupt-Kleissl and T. Chen, "Short term cloud coverage prediction using ground based all sky imager," in 2014 IEEE International Conference on Smart Grid Communications (SmartGridComm), Venice, Italy, 2014, pp. 121-126.
    [18] S. Zhang, Z. Dong, X. Yang, S. Chai, Z. Xu and D. Qi, "Intrahour Cloud Tracking Based on Optical Flow," 2019 Chinese Control Conference (CCC), Guangzhou, China, 2019, pp. 3023-3028.
    [19] Y. Li, X. Chen and M. Yang, "Optical Flow Based Solar Irradiance Forecasting in Satellite Images," 2019 IEEE International Conference on Real-time Computing and Robotics (RCAR), Irkutsk, Russia, 2019, pp. 442-447.
    [20] M. Zhai, X. Xiang, N. Lv, and X. Kong, "Optical flow and scene flow estimation: A survey," Pattern Recognition, vol. 114, 2021,
    [21] E. Ilg, N. Mayer, T. Saikia, M. Keuper, A. Dosovitskiy and T. Brox, "FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks," 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, 2017, pp. 1647-1655.
    [22] B. Jiang, X. Yin, and H. Song, "Single-stream long-term optical flow convolution network for action recognition of lameness dairy cow," Computers and Electronics in Agriculture, vol. 175, 2020,
    [23] J. Polo, L. F. Zarzalejo, L. Ramirez, and B. Espinar, "Iterative filtering of ground data for qualifying statistical models for solar irradiance estimation from satellite data," Solar Energy, vol. 80, no. 3, pp. 240-247, 2006.
    [24] P. Liu, X. Tong, J. Zhang, P. Meng, J. Li, and J. Zhang, "Estimation of half-hourly diffuse solar radiation over a mixed plantation in north China," Renewable Energy, vol. 149, pp. 1360-1369, 2020.
    [25] T. Watanabe, D. Nohara, “Prediction of time series for several hours of surface solar irradiance using one-granule cloud property data from satellite observations,”. Solar Energy, vol. 186, pp. 113-125, 2019
    [26] A. Alzahrani, J. W. Kimball, and C. Dagli, "Predicting Solar Irradiance Using Time Series Neural Networks," Procedia Computer Science, vol. 36, pp. 623-628, 2014.
    [27] C. N. Obiora and A. Ali, "Effective Implementation of Convolutional Long Short-Term Memory (ConvLSTM) Network in Forecasting Solar Irradiance," IECON 2021 – 47th Annual Conference of the IEEE Industrial Electronics Society, 2021.
    [28] 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), Charlotte, NC, USA, 2018, pp. 1-8.
    [29] X. Qing and Y. Niu, "Hourly day-ahead solar irradiance prediction using weather forecasts by LSTM," Energy, vol. 148, pp. 461-468, 2018.
    [30] E. Miranda, J. F. G. Fierro, G. Narvaez, L. F. Giraldo, M. Bressan,” Prediction of site-specific solar diffuse horizontal irradiance from two input variables in Colombia,”. Heliyon, vol. 7, no. 12, e08602.
    [31] O. El Alani, M. Abraim, H. Ghennioui, A. Ghennioui, I. Ikenbi, and F.-E. Dahr, "Short term solar irradiance forecasting using sky images based on a hybrid CNN–MLP model," Energy Reports, vol. 7, pp. 888-900, 2021.
    [32] A. Balan, T. Ramanathan, S. S, and L. S, "Comparative Analysis of Machine Learning Algorithms to Predict Solar Irradiance," 2022 International Conference on Disruptive Technologies for Multi-Disciplinary Research and Applications (CENTCON), 2022.
    [33] M. Khodayar, G. Liu, J. Wang and M. E. Khodayar, "Deep learning in power systems research: A review," CSEE Journal of Power and Energy Systems, 2020
    [34] J. Alonso-Montesinos and F. J. Batlles, "The use of a sky camera for solar radiation estimation based on digital image processing," Energy, vol. 90, pp. 377-386, 2015.
    [35] Y. Lin, D. Duan, X. Hong, X. Cheng, L. Yang and S. Cui, "Very-Short-Term Solar Forecasting with Long Short-Term Memory (LSTM) Network," 2020 Asia Energy and Electrical Engineering Symposium (AEEES), Chengdu, China, 2020, pp. 963-967.
    [36] Y. Bengio, "Practical recommendations for gradient-based training of deep architectures," 2012, arXiv:1206.5533.
    [37] D. Masters, C. Luschi, "Revisiting Small Batch Training for Deep Neural Networks," 2018, arXiv:1804.07612.
    [38] S. Dev, F. M. Savoy, Y. H. Lee, and S. Winkler, "Estimating solar irradiance using sky imagers," Atmos. Meas. Tech., vol. 12, no. 10, pp. 5417-5429, 2019.
    [39] I. Reda and A. Andreas, "Solar position algorithm for solar radiation applications," Solar Energy, vol. 76, no. 5, pp. 577-589, 2004.
    [40] D. Haputhanthri et al., "Solar Irradiance Nowcasting for Virtual Power Plants Using Multimodal Long Short-Term Memory Networks," Frontiers in Energy Research, vol. 9, 2021.
    [41] R. A. Rajagukguk, W.-K. Choi, and H. Lee, "Sun-blocking index from sky image to estimate solar irradiance," Building and Environment, vol. 223, 2022.
    [42] R. J. Davy, J. R. Huang, and A. Troccoli, "Improving the accuracy of hourly satellite-derived solar irradiance by combining with dynamically downscaled estimates using generalised additive models," Solar Energy, vol. 135, pp. 854-863, 2016.
    [43] B. D. Lucas and T. Kanade, "An iterative image registration technique with an application to stereo vision," presented at the Proceedings of the 7th international joint conference on Artificial intelligence - Volume 2, Vancouver, BC, Canada, 1981.
    [44] D. Teney, M. Hebert, "Learning to Extract Motion from Videos in Convolutional Neural Networks," 2016, arXiv:1601.07532.
    [45] A. Dosovitskiy et al., "FlowNet: Learning Optical Flow with Convolutional Networks," 2015 IEEE International Conference on Computer Vision (ICCV), Santiago, Chile, 2015, pp. 2758-2766.
    [46] T. Stoffel and A. Andreas. NREL Solar Radiation Research Laboratory (SRRL): Baseline Measurement System (BMS); Golden, Colorado (Data). United States: N. p., 1981. Web. doi:10.7799/1052221.
    [47] T.-P. Chu, J.-H. Guo, Y.-G. Leu, and L.-F. Chou, "Estimation of solar irradiance and solar power based on all-sky images," Solar Energy, vol. 249, pp. 495-506, 2023.
    [48] A. Al-lahham, O. Theeb, K. Elalem, T. A. Alshawi, and S. A. Alshebeili, "Sky Imager-Based Forecast of Solar Irradiance Using Machine Learning," Electronics, vol. 9, no. 10, 2020.

    下載圖示
    QR CODE