臺灣博碩士論文加值系統

The development plan of the PV power plant in Taiwan with high penetration makes the grid operator has to prepare the strategies to mitigate its intermittency behaviour. The power grid must be more flexible to receive the fluctuated power from PV. One of the economical ways is to conduct a solar power forecasting.
The solar power forecasting is made using artificial neural networks in this thesis. The networks are trained using backpropagation and extreme learning machine. The extreme learning machine was used due to its advantages in accuracy and computational time over backpropagation neural networks. The persistence model is used as the reference for the performance index. It can also be the input of the combined forecasting model to improve accuracy.
Later on, the month-based segmentation forecasting was investigated to accommodate the seasonal variation of generated PV power output. At the end of the research, it is found out that the segmented solar power forecasting has a better performance than the forecasting with only one model for the whole year.

Abstract I
Contents II
List of Figures V
1. Introduction 1
1.1 World Solar PV Development 1
1.2 Solar Power in Taiwan 4
1.3 Solar PV Integration 7
1.4 Objectives of the Research 8
1.5 Problem Scope 9
1.6 Thesis Overviews 10
2. Literature Review 11
2.1 Solar power forecasting methods 11
2.2 Machine learning method for solar power forecasting 13
3. Methodology and Data Collection for Solar Power Forecasting 15
3.1 Artificial Neural Networks 15
3.2 Extreme Learning Machine 22
3.3 Performance Metrics 25
3.4 Benchmarking the Forecasting Model 27
3.5 Data Collection 29
3.5.1 PV Power Output 29
3.5.2 Weather conditions 29
4. Forecasting Results 31
4.1 Modeling and validation procedure 31
4.2 Data preprocessing 33
4.2.1 Feature selection 33
4.2.2 Day only solar power forecasting 37
4.2.3 Feature scaling 38
4.2.4 Data splitting 38
4.3 Persistence model 39
4.4 Backpropagation neural networks model 41
4.4.1 The number of hidden nodes 41
4.4.2 The input variation 42
4.4.3 BPNN forecasting result 43
4.5 Extreme learning machine model 52
4.6 Combined forecasting model 60
4.7 Segmented forecasting model 62
5. Conclusions and Future Works 68
5.1 Concluding remarks 68
5.2 Future works 69
References 70

[1]IRENA, Renewable capacity statistics 2018. 2018.
[2]IRENA, Renewable Power Generation Costs in 2017. 2018.
[3]M. A. Green, Y. Hishikawa, E. D. Dunlop, D. H. Levi, J. Hohl-Ebinger, and A. W. Y. Ho-Baillie, “Solar cell efficiency tables (version 52),” Prog. Photovoltaics Res. Appl., vol. 26, no. 7, pp. 427–436, 2018.
[4]Fraunhofer ISE, “Photovoltaics Report,” 2018.
[5]Bureau of Energy MOEA Taiwan, “Energy Statistics 2017,” 2018.
[6]Taiwan Power Company, “Taiwan Power Company Sustainability Report,” 2018.
[7]J. Cochran et al., “Flexibility in 21 st Century Power Systems,” 2014.
[8]A. Tuohy et al., “Solar Forecasting: Methods, Challenges, and Performance,” IEEE Power Energy Mag., vol. 13, no. 6, pp. 50–59, 2015.
[9]T. Tian and I. Chernyakhovskiy, “Forecasting Wind and Solar Generation: Improving System Operations.” 2016.
[10]E. Isaksson and M. K. Conde, “Solar Power Forecasting with Machine Learning Techniques,” 2018.
[11]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. Sustain. Energy, vol. 5, no. 3, pp. 917–926, 2014.
[12]C. Wan, J. Zhao, Y. Song, Z. Xu, J. Lin, and Z. Hu, “Photovoltaic and solar power forecasting for smart grid energy management,” CSEE J. Power Energy Syst., vol. 1, no. 4, pp. 38–46, Dec. 2015.
[13]R. Perez, S. Kivalov, J. Schlemmer, K. Hemker, D. Renné, and T. E. Hoff, “Validation of short and medium term operational solar radiation forecasts in the US,” Sol. Energy, vol. 84, no. 12, pp. 2161–2172, 2010.
[14]R. Huang, T. Huang, R. Gadh, and N. Li, “Solar generation prediction using the ARMA model in a laboratory-level micro-grid,” 2012 IEEE 3rd Int. Conf. Smart Grid Commun. SmartGridComm 2012, pp. 528–533, 2012.
[15]G. Reikard, “Predicting solar radiation at high resolutions: A comparison of time series forecasts,” Sol. Energy, vol. 83, no. 3, pp. 342–349, 2009.
[16]A. Mellit, A. Massi Pavan, and V. Lughi, “Short-term forecasting of power production in a large-scale photovoltaic plant,” Sol. Energy, vol. 105, pp. 401–413, 2014.
[17]J. Zeng and W. Qiao, “Short-term solar power prediction using a support vector machine,” Renew. Energy, vol. 52, pp. 118–127, 2013.
[18]C. W. Chow et al., “Intra-hour forecasting with a total sky imager at the UC San Diego solar energy testbed,” Sol. Energy, vol. 85, no. 11, pp. 2881–2893, 2011.
[19]A. Hammer, D. Heinemann, and B. Luckehe, “Short-term forecasting of solar radiation : a statistical approach using satellite data,” Sol. Energy, vol. 67, no. 1992, pp. 139–150, 2000.
[20]E. Lorenz, J. Hurka, D. Heinemann, and H. G. Beyer, “Irradiance Forecasting for the Power Prediction of Grid-Connected Photovoltaic Systems,” IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., vol. 2, no. 1, pp. 2–10, 2009.
[21]H. T. C. Pedro and C. F. M. Coimbra, “Assessment of forecasting techniques for solar power production with no exogenous inputs,” Sol. Energy, vol. 86, no. 7, pp. 2017–2028, 2012.
[22]G. Seif, “Selecting the best Machine Learning algorithm for your regression problem,” 2018, pp. 1–6, 2018.
[23]G.-B. Huang, Q.-Y. Zhu, and C. Siew, “Extreme learning machine : Theory and applications,” Neurocomputing, vol. 70, no. 1–3, pp. 489–501, 2006.
[24]B. Jing, Z. Qian, Y. Pei, and J. Wang, “Ultra short-term PV power forecasting based on ELM segmentation model,” J. Eng., vol. 2017, no. 13, pp. 2564–2568, 2017.
[25]C. Stergiou and D. Siganos, “Neural Networks.” [Online]. Available: https://www.doc.ic.ac.uk/~nd/surprise_96/journal/vol4/cs11/report.html.
[26]M. A. Nielsen, Neural Networks and Deep Learning. Determination Press, 2015.
[27]International Energy Agency, “Photovoltaic and Solar Forecasting : State of the Art,” 2013.
[28]F. H. Jufri and J. Jung, “Photovoltaic Generation Forecasting Using Artificial Neural Networks Model with Input Variables and Model Parameters Selection Algorithm in Korea,” Int. J. Mach. Learn. Comput., vol. 7, no. 5, pp. 156–161, 2017.
[29]P. Bacher, H. Madsen, and H. A. Nielsen, “Online short-term solar power forecasting,” Sol. Energy, vol. 83, no. 10, pp. 1772–1783, 2009.
[30]F. Bizzarri, M. Bongiorno, A. Brambilla, and G. Gruosso, “Model of Photovoltaic Power Plants for Performance Analysis and Production Forecast,” vol. 4, no. 2, pp. 278–285, 2013.
[31]E. Lorenz, A. Hammer, D. Heinemann, and E. M. Group, “Local and regional PV power forecasting based on PV measurements, satellite data and numerical weather predictions,” 2016.
[32]J. Wang, R. Ran, and Y. Zhou, “A Short-Term Photovoltaic Power Prediction Model Based on an FOS-ELM Algorithm,” Appl. Sci., vol. 7, no. 4, p. 423, 2017.