為了提高太陽能光伏發電預測在能源管理系統中的準確度，本文通過使用能夠簡易取得的訊息，提出一個短期與超短期的太陽能光伏發電預測模型，藉以解決在太陽能案場實際使用中會遇到的問題。一天前的短期太陽能發電預測利用自組織對映與模糊控制理論來預測太陽能發電每15分鐘的發電功率。當即時的實際太陽能發電功率數據取得以後，超短期太陽能預測利用相關的數據對下一筆的一日前太陽能發電預測結果做即時修正。此外，在得出平面的日照預測值以後，本文也提出可以估計出實際太陽能模組板會接收到的日照量（包括直射光與漫射光），藉以提高太陽能發電的預測準確度。本文所提出的太陽能發電預測模型已被應用在樹林3kW太陽能電廠與台南499kW的太陽能電廠。一日前的短期太陽能發電預測平均誤差是4.98%，而超短期太陽能發電預測的平均誤差是2.67%。

To enhance the accuracy of the photovoltaic (PV) power output forecasting model for energy management system (EMS), this thesis proposes a one-day ahead short-term and real-time very short-term solar PV output forecasting model based on easier accessible information to solve some problems in practical application. The one-day ahead short-term PV output forecast of the proposed forecasting model predicts the PV power output every 15 minutes by using self-organizing map (SOM) and fuzzy inference method. The real-time very short-term PV output forecast of the proposed model constantly tunes the short-term predicted values achieved one-day ahead, once the actual power output one time-step of 15 minutes before is available. Further, from the forecast horizontal solar radiation, a method is proposed to estimate the actual radiation on the surface of the PV panels to have better forecasting accuracy of PV power generation. The proposed method has been tested in a practical 3 kW PV system in Shulin, Taiwan and a 499 kW commercial grid-connected PV system in Tainan, Taiwan. The average short-term forecast error is 4.98% with the average forecast error of 2.67% for real-time very short-term forecast model.

[1] A. Yona, T. Senjyu, T. Funabashi, and C. H. Kim, “Determination method of insolation prediction with fuzzy and applying neural network for long-term ahead PV power output correction,” IEEE Trans. Sustainable Energy, vol. 4, no. 2, pp. 527-533, Mar. 2013.
[2] A. Syahiman, H. Yokoyama, and N. Kakimoto, “High-precision forecasting model of solar irradiance based on grid point value data analysis for an efficient photovoltaic system,” IEEE Trans. Sustainable Energy, vol. 6, no. 2, pp. 474-481, Feb. 2015.
[3] J. Liu, W. Fang, X. Zhang, and C. Yang, “An improved photovoltaic power forecasting model with the assistance of aerosol index data,” IEEE Trans. Sustainable Energy, vol. 6, no. 2, pp. 434-442, Feb. 2015.
[4] H. T. Yang, C. M. Huang, Y. C. Huang, and Y. S. Pai, “A weather-based hybrid method for 1-day ahead hourly forecasting of PV power output,” IEEE Trans. Sustainable Energy, vol. 5, no. 3, pp. 917-926, Jul. 2014.
[5] R. J. Bessa, A. Trindade, and V. Miranda, “Spatial-temporal solar power forecasting for smart grids,” IEEE Trans. Industrial Informatics, vol. 11, no. 1, pp. 232-241, Feb. 2015.
[6] M. G. D. Giorgi, P. M. Congedo, and M. Malvoni, “Photovoltaic power forecasting using statistical method: impacts of weather data,” IET Science, Measurement and Technology, vol. 8, no. 3, pp. 90-97, Jan. 2014.
[7] T. Cai, S. Duan, and C. Chent, “Forecasting power output for grid-connected photovoltaic power system without using solar radiation measurement,” in Proc. 2010 2nd IEEE International Symposium on Power Electronics for Distributed Generation Systems Conference, Hefei, China, Jun. 2010.
[8] M. Fidan, F. O. Hocaoglu, and O. N. Gerek, “Harmonic analysis based hourly solar radiation forecasting model,” IET Renewable Power Generation, vol. 9, no. 3, pp. 218-227, Jul. 2014.
[9] P. Mathiesen, J. M. Brown, and J. Kleissl, “Geostrophic wind dependent probabilistic irradiance forecasts for coastal California,” IEEE Trans. Sustainable Energy, vol. 4, no. 2, pp. 510-518, Jul. 2012.
[10] 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 Trans. Industry Applications, vol. 48, no. 3, pp. 1064-1069, May 2012.
[11] Y. Zhang, M. Beaudin, R. Taheri, H. Zareipour, and D. Wood, “Day-Ahead Power Output Forecasting for Small-Scale Solar Photovoltaic Electricity Generators,” IEEE Trans. Smart Grid, vol. 6, no. 5, pp. 2253-2262, Sep. 2015.
[12] K. Stefferud, J. Kleissl, and J. Schoene, “Solar Forecasting and Variability Analyses using Sky Camera Cloud Detection & Motion Vectors,” in IEEE Power and Energy Society General Meeting, San Diego, CA, Jul. 2012.
[13] S. Sun, J. Ernst, A. Sapkota, E. Ritzhaupt-Kleissl, J. Wiles, J. Bamberger, and T. Chen, “Short Term Cloud Coverage Prediction using Ground Based All Sky Imager,” in IEEE International Conference on Smart Grid Communications (SmartGridComm), Venice, Nov. 2014.
[14] S. Cros, O. Liandrat, N. Sebastien, N. Schmutz, “Extracting cloud motion vectors from satellite images for solar power forecasting,” in IEEE International Conference on Geoscience and Remote Sensing Symposium (IGARSS), Quebec City, QC, Jul. 2014.
[15] A. Cazorla, F. J. Olmo, and L. Alados-Arboledas, “Development of a sky imager for cloud cover assessment,” Journal of the Optical Society of America, vol. 25, no. 1, pp. 29-39, Jan. 2008.
[16] Q. Y. Li, W. T. Lu, J. Yang, and Z. Wang, “Thin Cloud Detection of All-Sky Images Using Markov Random Fields,” IEEE Trans. Geoscience and Remote Sensing Letters, vol. 9, no. 3, pp. 417-421, May 2012.
[17] C. W. Chow, S. Belongie, and J. Kleissl, “Cloud motion and stability estimation for intra-hour solar forecasting,” Elsevier ScienceDirect Solar Energy, 115, vol. 115, no. 1, pp. 645-655, Apr. 2015.
[18] P. Wood-Bradley, J. Zapata, and J. Pye, “Cloud tracking with optical flow for short-term solar forecasting,” in [ONLINE] http://stg.anu.edu.au/publications/assets/inproc/woodbradley-ause, Solar Thermal Group, The Australian National University, 2012.
[19] T. Kohonen, “The self-organizing map,” IEEE Proc., vol. 78, no. 9, pp. 1464-1480, Sep. 1990.
[20] J. Kennedy and R. Eberhart, “Particle Swarm Optimization,” Proc. 1995 IEEE International Conference on Neural Networks, vol. 4, no. 1, pp. 1942-1948, Dec. 1995.
[21] J. A. Duffie and W. A. Beckman, “Chapter 2 Available Solar Radiation,” in Solar Engineering of Thermal Processes, New York City, John Wiley & Sons, Inc., 2006.
[22] S. Lu, Y. Hwang, I. Khabibrakhmanov, F. J. Marianno, X. Shao,J. Zhang, B. Hodge, H. F. Hamann, “Machine learning based multi-physical-model blending for enhancing renewable energy forecast - improvement via situation dependent error correction,” in 2015 European Control Conference (ECC), Linz, Austria, Jul. 2015.