簡易檢索 / 詳目顯示

回結果列表
研究生： 洛達文
Roberts, Darvin Y.
論文名稱： 基於小波轉換與機器學習之短期風力發電預測系統
Short-Term Wind Power Forecasting Based on Wavelet Transform and Machine Learning Approach
指導教授： 楊宏澤
Yang, Hong-Tzer
學位類別： 碩士
Master
系所名稱： 電機資訊學院 - 電機工程學系
Department of Electrical Engineering
論文出版年： 2014
畢業學年度： 102
語文別： 英文
論文頁數： 64
中文關鍵詞： 機率分佈 、有限混合模型 、多解析度分布 、類神經網路 、模糊推論法 、鄰近時間點預測 、數值天氣預測 、短期風力發電預測
外文關鍵詞： probability distribution, finite mixtures model, multi-resolution analysis, neural networks, fuzzy inference, near real-time forecasting, numerical weather predictions, short-term forecasting
相關次數： 點閱：171  下載：13 
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

    • 由於風速具高度不確定及快速變化的特性，在高風力發電滲透率下的電力系統常遇到備轉容量規劃和電力調度等問題。為解決大規模風力發電系統併接於電力系統中產生之相關議題，風力發電預測是不可或缺的必要條件。

    本文提出一個整合數值天氣預測資料的短期風力發電預測法。每四小時產生未來一組十五分鐘為間格之預測結果，可應用於備轉容量規劃與電力調度問題上。本文所提方法利用機率分佈、有限混合模型、多解析度分析、類神經網路、模糊推論法以及整合鄰近時間點進行風力發電預測。由過去一年實際歷史風速資料數值模擬結果顯示，利用本文所提測試於一2MW之風力發電系統，可獲得每月平均相對誤差與均方根誤差分別是8.52%和287.28kW，明顯優於本文用以比較的類神經網路與多解析度分析類神經網路方法。

    Due to high uncertainty and fast fluctuations of wind speed, in the power system with high penetration of wind power generation, spinning reserve scheduling and power dispatching are two major problems encountered. To achieve the purposes, wind power forecasting is, therefore, a prerequisite for the integration of a large-scale wind generation farm in the electric power system.

    This thesis aims to present a short-term wind power forecasting method with numerical weather prediction (NWP) data integrated. The forecasts are up to 4-hr ahead with a 15-min interval, making the wind power forecasts suitable for addressing the spinning reserve scheduling and power dispatching problems. The proposed forecasting method integrates probability distribution analysis, finite-mixture model, multi-resolution analysis (MRA), radial basis neural networks (RBFNNs), fuzzy inference (FI), and near real-time forecasting approaches.

    Tested on the historical one-year wind-speed data, the numerical results obtained show that the forecasting accuracy of the wind power in terms of monthly average mean relative error (MRE) and relative error root mean square error (RMSE) for a 2MW wind-generation system is 8.52% and 287.28 kW, respectively. The performance obtained is obviously better than the compared conventional neural networks (NNs) and MRA-NNs methods in the thesis.

    List of Figures vii List of Tables x Nomenclature xi Chapter 1. INTRODUCTION 1 1.1 Backgrounds and Motivations 1 1.2 Review of Literature 3 1.3 Research Objective and Methods 6 1.4 Contributions of the Thesis 7 1.5 Organization of the Thesis 8 Chapter 2. ASPECTS OF WIND POWER GENERATION 9 2.1 Characteristics of Wind Speed 9 2.2 Characteristics of Wind Direction 9 2.3 Characteristics of Wind Power 10 2.4 Problem Formulation 11 Chapter 3. THE PROPOSED FORECASTING METHOD 12 3.1 Introduction 12 3.2 Description of Proposed Method 13 3.3 Wind Speed Profiling 15 3.4 Wind Direction Profiling 16 3.4.1 Finite Mixture Model 19 3.4.2 Basics of Finite Mixture Model 19 3.4.3 The Expectation-Maximization Algorithm 21 3.5 Auto-correlation 23 3.6 Wavelet Transform 25 3.6.1 Continuous Wavelet Transform 26 3.6.2 Discrete Wavelet Transform 28 3.7 Artificial Neural Networks 30 3.7.1 Radial Basis Function Neural Network 31 3.8 Fuzzy Inference 32 3.9 Near-Real Time Forecasting 37 Chapter 4. SIMULATION RESULTS 39 4.1 Introduction 39 4.2 Evaluation Indices 39 4.3 Parameter Determination in Proposed Method 41 4.3.1 Length of Time Series 41 4.3.2 Parameters of Fuzzy Membership Function 43 4.3.3 Direction-Dependent Power Curves 43 4.3.4 Reference Methods 46 4.4 Forecasting Results 46 Chapter 5. CONCLUSION AND FUTURE PROSPECTS 59 5.1 Conclusion 59 5.2 Future Prospects 60 REFERENCES 61

    [1] Global Wind Energy Council, "Market Forecast for 2014-2018," [Online]. Available: http://www.gwec.net/global-figures/market-forecast-2012-2016/.
    [2] J. A. Ging, M. E. Galvin, D. J. Crilly, E. P. Kennedy, P. A. O'Donnell and J. E. Sustman, "Spatio-temporal analysis of possible wind generation output reductions for Irish transmission system with a high penetration of renewables," IET Renewable Power Generation, vol. 8, no. 3, pp. 230-239, July 2013.
    [3] C. Lowery and M. O'Malley, "Impact of Wind Forecast Error Statistics Upon Unit Commitment," vol. 3, no. 4, pp. 760-768, Oct. 2012.
    [4] M. A. Matos and R. J. Bessa, "Setting the Operating Reserve Using Probabilistic Wind Power Forecasts," IEEE Trans. on Power Systems, vol. 26, no. 2, pp. 594-603, May 2011.
    [5] G. N. Bathurst, J. Weatherill and G. Strbac, "Trading Wind Generation in Short Term Energy Markets," IEEE Trans. on Power Systems, vol. 17, no. 3, pp. 782-789, Aug. 2002.
    [6] S. D. Tomic, "A Study of the Impact of Load Forecasting Errors on Trading and Balancing in a Microgrid," IEEE Conference on Green Technologies, pp. 443-450, Apr. 2013.
    [7] M. Lange and U. Focken, Physical Approach to Short-term Wind Power Prediction, Heidelberg: Springer-Verlag, 2005.
    [8] G. Kariniotakis, I. H.-P. Marti, G. Giebel, T. S. Nielsen, J. Tamke, J. Usaloa, F. Dierich, A. Bocquet and S. Virlot, "Next generation forecasting tools for the optimal management of wind generation," IEEE International Confonference on Probabilistic Methods Applied to Power Systems (PMAPS), pp. 1-6, June 2006.
    [9] J. R. Xia and Y. P. Dai, "Neuro-Fuzzy Networks for Short-Term Wind Power Forecasting," IEEE International Conference on Power System Technology (POWERCON), pp. 1-5, Oct. 2010.
    [10] P. SangitaB and S. R. Deshmukh, "Use of Support Vector Machine for Wind Speed Prediction," IEEE International Conference on Power and Energy Systems (ICPS), pp. 1-8, Dec. 2011.
    [11] J. Shi, Y. Q. Liu, Y. P. Yang and W. J. Lee, "Short-term Wind Power Prediction Based on Wavelet Transform-Support Vector Machine and Statistic Characteristics Analysis," IEEE International Conference on Industrial and Commercial Power Systems (I&CPS), pp. 1-7, May 2011.
    [12] M. Khalid and A. V. Savkin, "A Method for Short-Term Wind Power Prediction With Multiple Observation Points," IEEE Trans. on Power Systems, vol. 27, no. 2, pp. 579-586, 2012.
    [13] J. P. Catalão, H. M. I. Pousinho and V. M. F. Mendes, "Hybrid intelligent approach for short-term wind power forecasting in Portugal," IET Renewable Power Generation, vol. 5, no. 3, pp. 251-257, 2011.
    [14] G. Sideratos and N. D. Hatziargyriou, "An Advanced Statistical Method for Wind Power Forecasting," IEEE Trans. on Power Systems, vol. 22, no. 1, pp. 285-265, Feb. 2007.
    [15] K. Bhaskar and S. N. Singh, "AWNN-Assisted Wind Power Forecasting using Feed-Forward Neural Network," vol. 3, no. 2, pp. 306-315, Apr. 2012.
    [16] C. Monterio, V. Miranda, A. Botterud, J. Wang and G. Conzelmann, "Wind Power Forecasting: State-of-the-Art 2009," U.S. Department of Energy, Illinois, Nov. 2009.
    [17] S. S. Soman, H. Zareipour, O. Malik and P. Mandal, "A Review of Wind Power and Wind Speed Forecsting Methods With Different Time Horizons," IEEE Conference North American Power Symposium (NAPS), pp. 1-8, Sep. 2010.
    [18] S. Tewari, C. J. Geyer and N. Mohan, "A Statistical Model for Wind Power Forecast Error and its Application to the Estimation of Penalties in Liberalized Markets," IEEE Trans. on Power Systems, vol. 26, no. 4, pp. 2031-2039, 2011.
    [19] W. Alan, Instant Wind Forecasting, Sheridan House, 2002.
    [20] F. D. Bianchi, R. J. Martz and H. De Battista, Wind Turbine Control Systems, London: Springer, 2007.
    [21] B. A. Harper, J. D. Kepert and J. D. Ginger, "Guidelines for converting between various wind averaging periods in tropical cyclone conditions," World Meterological Organization, Oct. 2008.
    [22] C. Gavriluta, S. Spataru, I. Mosincat, C. Citro, I. Candela and P. Rodriguez, "Complete methodology on generating realistic wind speed profiles based on measurements," EA International Conference on Renewable Energies and Power Quality, 2012.
    [23] K. V. Mardia, Statistics of Directional Data, London: Academic Press Inc., 1972.
    [24] G. McLachlan and D. Peel, Finite Mixture Models, John Wiley and Sons Inc., 2004.
    [25] J. Bently, "Modelling Circular Data Using a Mixture of von Mises and Uniform Distributions," Simon Fraser University Department of Statistics and Actuarial Science, 2006.
    [26] S. Calderara, A. Prati and R. Cucchiara, "Mixtures of von Mises Distributions for People Trajectory Shape Analysis," IEEE Trans. on Circuits and Systems for Video Technology, vol. 21, no. 4, pp. 457-471, Apr. 2011.
    [27] K. Pearson, "Contributions to the theory of mathematical evolution," Philosophical Transactions of the Royal Society of London. A, vol. 185, pp. 71-110, 1894.
    [28] G. J. McLachlan and T. Krishnan, The EM Algorithm and Extensions, New York: John Wiley, 1997.
    [29] R. E. Kass and A. E. Raftery, "Bayes Factors," Journal of the American Statistical Assoication, vol. 90, no. 430, pp. 773-795, June 1995.
    [30] C. Chatfield, The Analysis of Time Series: An Introduction, 6 ed., Chapman & Hall / CRC, 2004, pp. 22-24.
    [31] P. S. Addison, The Illustrated Wavelet Transform Handbook, London: Institute of Physics (IOP), 2002, pp. 73-77.
    [32] S. G. Mallat, "Multifrequency Channel Decomposition of Images and Wavelet Models," IEEE Trans. on Acoustics, Speech, and Signal Processing, vol. 37, no. 12, pp. 2091-2110, 1989.
    [33] A. Gubner and W. B. Chang, "Wavelet transforms for discrete-time periodic signals," Sig. Proc, vol. 42, no. 2, pp. 167-180, 1995.
    [34] J. Eynard, S. Grieu and M. Polit, "Wavelet-based muli-resolution analysis and artificial neural networks for forecasting temperature and thermal power consumption".ELIAUS Lab. University of Perpigan Via Domitia.
    [35] D. Parcival and A. Walden, "Wavelet Methods for Time Series Analysis," Cambridge University Press, 2000.
    [36] M. J. Powell, "Radial basis functions," Nuerical Analysis, vol. 2, pp. 105-210.
    [37] D. S. Broomhead and D. Lowe, "Multivariable functional interpolation and adaptive networks," Complex Systems, vol. 21, pp. 321-355.
    [38] S. A. Billings and G. L. Zheng, "Radial Basis Function Network Configuration Using Genetic Algorithms," Elsevier Science Ltd. Neural Networks, vol. 8, no. 6, pp. 877-890.
    [39] T. J. Ross, Fuzzy logic with engineering applications, New York: McGraw-Hill, 1995.
    [40] S. Misha, A. Sharma and G. Panda, "Wind Power Forecasting Model using Complex Wavelet Theory," IEEE International Conference on Energy, Automation, and Signal (ICEAS), pp. 1-4, 2011.
    [41] X. Qin and J. Zhang, "A New Circular Distribution and Its Application to Wind Data," Journal of Mathematics Research, vol. 2, no. 3, pp. 12-17, Aug. 2010.
    [42] J. A. Carta and P. Ramírez, "Use of finite mixture distribution models in the analysis of wind energy in the Canarian Archipelago," Elsevier Energy Conversion and Management, vol. 48, pp. 281-291, 2007.
    [43] B. Stephen, S. Gallloway, D. McMillan, L. Anderson and G. Ault, "Statistical profiling of site wind resource speed and directional characteristics," IET Renewable Power Generation, vol. 7, no. 6, pp. 583-592, May 2013.
    [44] L. Caretto, Use of Probability Distributions Functions for Wind, California State Univeristy, Northridge, 2010.
    [45] R. Karki, S. Thapa and R. Billinton, "A Simplified Risk-Based Method for Short-Term Wind Power Commitment," IEEE Trans. on Sustainable Energy, vol. 3, no. 3, pp. 498-505, 2012.
    [46] P. Pinson, H. A. Nielsen, J. K. Møller, H. Madsen and G. N. Kariniotakis, "Non-parametric Probabilistic Forecasts of Wind Power: Requied Properties and Evaluation," Wind Energy, vol. 10, pp. 497-516, May 2007.

    下載圖示 校內：立即公開
    校外：立即公開
    QR CODE