隨著科技進步，能源使用的需求越來越大，其中電力能源更是不可或缺。然而隨著環保意識抬頭與永續能源發展，為了未來人類能有更好的生活品質，進而使再生能源的研究領域越來越受到重視，尤其以太陽能源最受矚目。
因為太陽能源受到重視，其太陽日射量不穩定之特性，會造成太陽能發電電廠的消耗成本增加，故本篇論文就是依太陽能發電的電力控管需求，提出短期的太陽日射量預測機制。傳統的衛星影像可以做大範圍以及長期的預測，但是衛星影像大多以數個小時到一天作為預測單位，無法達到以分鐘為單位之精確短期預測，同時也無法針對特定的小範圍精確預測預測。為了在預測上達到更好的時間和空間解析度，全天空相機被引入作為短期預測之取像裝置。
本篇論文提出一套短時間內日射量預測的系統架構與一套修正預測機制。本篇論文研究的日射量預測系統是以回歸模型(Regression Model)作為基礎，並搭配全天空影像與日射儀蒐集的資訊，當作訓練特徵，建立回歸模型。而預測模型又分為遮蔽模型與明朗模型。修正機制是藉由卡爾曼濾波預測(Kalman Filter predictor)和預測日射量修正公式(Ramp Down Correction Function)並依照融合機制，得到最後的短期預測日射量。最後，本篇論文將用具挑戰性的資料集來實驗，並驗證與分析。實驗顯示搭配全天空影像所抽取之特徵，可以達到更好的預測效果。並且本論文提出之雙模型預測較單模型預測可有效降低預測誤差。另外，本論文提出之修正預測機制，預測日射量修正，以及融合回歸模型和卡爾曼濾波預測模型之機制，可使預測更為準確。

For the qualities of life and sustainable development in the future, renewable power draws much attention in the modern society. Many countries have devoted themselves to the development of renewable power. And solar energy is one of the most important renewable energy. To take advantage of solar energy effectively, integrated and large scale photovoltaic systems need to overcome the unstable nature of solar resource.
This thesis proposes a short-term irradiance prediction framework that uses regression models. The prediction model is constructed by all-sky image features and historical data which is clearness index or irradiance. Two models are constructed based on the occlusion condition near the solar disk. Moreover, ramp-down events are detected and the predicted irradiance is corrected on ramp-down events. The amount of correction is determined by the features extracted from the all-sky images. We also compare the prediction results of regression models with a Kalman filter predictor.
Afterwards, we fuse the prediction results of the regressor and the Kalman filter predictor. Finally, we validate the proposed system using challenging experimental datasets.

[1] GK. Singh. Solar power generation by Photovoltaic technology: a review. Energy 2013; 53: 1-13.
[2] H. Lund. Renewable energy strategies for sustainable development. Energy 2007; 32: 912-919.
[3] B. Urquhart, CW. Chow, D. Nguyen, J. Kleissl, M. Sengupta, J. Blatchford, D. Jeon. Towards intra-hour solar forecasting using two sky imagers at a large solar power plant. American Solar Energy Society 2012; 1-6.
[4] F. Wang, Z. Mi, S. Su, H. Zhao. Short-term solar irradiance forecasting model based on artificial neural network using statistical feature parameters. Energies 2012; 5: 1355-1370.
[5] M. Marquez, C.F.M. Coimbra. Forecasting of global and direct solar irradiance using stochastic learning methods, ground experiments and the NWS database. Solar Energy 2011; 85: 746-756.
[6] E. Lorenz, J. Hurka, D. Heinemann, H.G. Beyer. Irradiance forecasting for the power prediction of grid-connected photovoltaic systems. IEEE Journal of Selected Topics in Applied Earth Observations Remote Sensing 2009; 2: 2-10.
[7] D. Heinemann, E. Lorenz, M. Girodo. Solar irradiance forecasting for the management of solar energy systems. Energy and Semiconductor Research Laboratory, Energy Meteorology Group, Oldenburg University 2006. 1-6.
[8] A. Heinle, A. Macke, A. Srivastav. Automatic cloud classification of whole sky images. Atmospheric Measurement Techniques Discussions 2010; 3: 269–299.
[9] M. Martínez-Chico, F.J. Batlles, J.L. Bosch. Cloud classification in a mediterranean location using radiation data and sky images. Energy 2011; 36: 4055-4062.
[10] H. Huang, S. Yoo, D. Yu, D. Huang, H. Qin. Correlation and local feature based cloud motion estimation. Proceeding of the Twelfth International Workshop on Multimedia Data Mining. ACM, 2012; 1-9.
[11] R. Marquez, C.F. Coimbra. Intra-hour DNI forecasting based on cloud tracking image analysis. Solar Energy 2013; 91: 327-336.
[12] M.S. Ghonima, B. Urquhart, C.W. Chow, J.E. Shields, A. Cazorla, J. Kleiss. A method for cloud detection and opacity classification based on ground based sky imagery. Atmospheric Measurement Techniques Discussions 2012; 5: 4535–4569.
[13] J.E. Shields, M.E. Karr, T.P. Tooman, D.H. Sowle, S.T. Moore. The whole sky imager-a year of process. Atmospheric Radiation Measurement Science Team Meeting 1998; 23-27.
[14] M.P. Souza-Echer, E.B. Pereira, L.S. Bins, M.A.R. Andrade. A simple method for the assessment of the cloud cover state in high-latitude regions by a ground-based digital camera. Journal of Atmospheric and Oceanic Technology 2006; 23: 437-447.
[15] Q. Li, W. Lu, J. Yang. A hybrid thresholding algorithm for cloud detection on ground-based color images. Journal of Atmospheric and Oceanic Technology 2011; 28: 1286–1296.
[16] C.N. Long, D.W. Slater, T.P. Tooman. Total sky Imager model 880 status and testing results. Pacific Northwest National Laboratory, 2001. 1-36.
[17] C.N. Long, J.M. Sabburg, J. Calbó, D. Pagès, Retrieving cloud characteristics from ground-based daytime color all-sky images. Journal of Atmospheric and Oceanic Technology 2006; 23:633-652.
[18] CL. Fu, HY. Cheng. Predicting solar irradiance with all-sky image features via regression. Solar Energy 2013; 97: 537-550.
[19] HY. Cheng, CC. Yu, SJ. Lin. Bi-model short-term solar irradiance prediction using support vector regressors. Solar Energy 2014; 70: 121-127.
[20] L.S. Aiken, S.G. West, S.C. Pitts. Handbook of Psychology. Research methods in psychology. Willey N. Y. 2003; 2: 483-507.
[21] C.M. Douglas, C.R. George, 2007. Applied statistics and probability for engineers 4th edition. 435-447.
[22] D. Basak, S. Pal, D.C. Patranabis. Support vector regression. Neural Information Processing –Letters and Reviews 2007; 11: 203-224.
[23] V. Vapnik, S.E. Golowich, A. Smola. Support vector method for function approximation, regression estimation, and signal processing. Advances in Neural Information Processing Systems 1997; 281-287.
[24] JW. Bugler. The determination of hourly insolation on an inclined plane using a diffuse irradiance model based on hourly measured global horizontal insolation. Solar Energy 1997; 19: 477-491.
[25] R.E. Bird. A simple solar spectral model for direct-normal and diffuse horizontal irradiance. Solar Energy 1984; 32: 467-471.
[26] R.E. Bird, C. Riordan. Simple solar spectral model for direct and diffuse irradiance on horizontal and tilted planes at the earth's surface for cloudless atmospheres. Journal of Climate Applied Meteorology 1986; 25: 87–97.
[27] S. Liang, A. Strahler, C. Walthall. Retrieval of land surface albedo from satellite observations: a simulation study. IEEE Geoscience and Remote Sensing Symposium Proceedings 1998; 3: 1286 – 1288.
[28] I. Reda, A. Andreas. Solar position algorithm for solar radiation applications. Solar Energy 2004; 76: 577–589.
[29] K.G.T. Hollands, R.G. Huget. A probability density function for the clearness index with applications. Solar Energy 1983; 30: 195-209.
[30] R. Perez, P. Ineichen, R. Seals, A. Zelenka. Making full use of the clearness index for parameterizing hourly insolation conditions. Solar Energy 1990; 45: 111-114.
[31] D.M. Hawkins. The problem of over-fitting. Journal of Chemical Information and Computer Science 2004; 44: 1-12.
[32] R. Kohavi. A study of cross-validation and bootstrap for accuracy estimation and model selection. International Joint Conference on Artificial Intelligence 1995; 14: 1137-1145.
[33] CT. Chiang, YS. Lee, X.R. Li, CC. Liao. A RSCMAC based forecasting for solar irradiance from local weather information. Neural Network (IJCNN), The 2012 International Joint Conference on IEEE 2012; 1-7.
[34] ZN. Li, M.S. Drew. 2004. Fundamentals of Multimedia. School of Computing Science Simon Fraser University. Prentice Hall. 82-100.
[35] R.C. Gonzalez, R.E. Woods. 2002. Digital Image Processing 2nd Edition. Prentice Hall. 134-137.
[36] J. Shi, C. Tomasi. Good features to track. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 1994; 593-600.
[37] J. Matas, C. Galambos, J.V. Kittler. Robust detection of lines using the progressive probabilistic Hough transform. Computer Vision and Image Understanding 2000; 78: 119-137.
[38] G. Welch, G. Bishop. An Introduction to the Kalman Filter. Department of Computer Science University of North Carolina at Chapel Hill Chapel Hill. 1995. 1-16.
[39] D.B. Reid. An algorithm for tracking multiple targets. Automatic Control, IEEE Transactions 1979; 24: 843-854.
[40] D. Campbell. Widefield Imaging at Bayfordbury Observatory. University of Hertfordshire. 2010. 1-47.
[41] “MOXA UPort 1150/1150I,” [Online]
Available: http://www.moxa.com.tw/Product/UPort_1150_1150I.htm.