近年來，能源短缺在全世界已經是個重要且必須面對的議題。因此，新生綠色能源也越來越受到重視。如今有許多新生能源不斷被開發並且落實到生活中，例如太陽能發電、水力發電、風力發電、以及氫能源。在眾多新生能源中，本研究將針對零汙染且低成本的風力發電進行電力供給量預測。在此研究中，我們使用類神經網路架構建立預測模型並以改良式的群體演算法進行求解。進行風力發電預測之前，本研究測試了五筆時間序列資料並與其他預測方法比較預測均方誤差，加以驗證本研究之方法對於時間序列的預測能力；在風力發電供給量預測問題中，風力發電預測資料來自台灣麥寮風力發電廠，資料年數從2002年9月至2007年8月，共計五年。在實例研究中，我們並使用主成份分析法進行輸入資料之預處理以增加求解效率。最後，藉由比較各方法之均方誤差，我們期望本研究提出之方法的結果能夠比其他預測方法求得更準確的預測模型。

Recently, energy shortage has become a significant issue that we must have to face. Hence, people now pay much more attention to renewable green energy than before. Nowadays, much renewable energy is being developed and applied to our lives, such as solar energy, water energy, wind energy, and hydrogen energy. Among the many kinds of renewable energy, in this study, we focused on wind power forecast, which has a low cost and is non-polluting. In this paper, our forecast model is based on an Artificial Neural Network (ANN) model; we seek the model solutions by Improved Simplified Swarm Optimization (ISSO). Before wind power forecast, we test our proposed model on five time series benchmark data set and compare the performance by mean square error (MSE) in order to verify the forecasting ability of our method. In the wind power forecast problem, the used data was collected at the Mai Liao wind farm in Taiwan over a period of five years from September 2002 to August 2007. In the experiment, we also carried out data pretreatment by performing a Principal Component Analysis (PCA) in order to increase the model efficiency. At last, we proved the forecasting results of our proposed method to be more precise than other methods by comparing the MSE.

[1] F. Lisi, R.A. Schiavo, “A comparison between neural networks and chaotic models for exchange rate prediction”, Computational Statistics & Data Analysis, 1999, Vol. 30, pp. 87–102.
[2] J. Wang et al, “Combined modeling for electric load forecasting with adaptive particle swarm optimization”, Energy, 2010, Vol. 35, pp. 1671–1678.
[3] S.-w. Fei et al., “Particle swarm optimization-based support vector machine for forecasting dissolved gases content in power transformer oil”, Energy Conversion and Management, 2009,Vol. 50, pp. 1604–1609.
[4] L. Aburto, R. Weber, “Improved supply chain management based on hybrid demand forecasts”, Applied Soft Computing, 2007, Vol. 7, pp. 136–144.
[5] J.T. Coshall, “Combining volatility and smoothing forecasts of UK demand for international tourism”, Tourism Management, 2009, Vol. 30, pp. 495–511.
[6] D. Kang et al., “Real-time bias-adjusted O3 and PM2.5 air quality index forecasts and their performance evaluations over the continental United States”, Atmospheric Environment, 2010, Vol. 44, pp. 2203–2212.
[7] L. Zhao, Y. Yang, “PSO-based single multiplicative neuron model for time series prediction”, Expert Systems with Applications, 2009, Vol. 36, pp. 2805–2812.
[8] http://www-psych.stanford.edu/~andreas/Time-Series/SantaFe.html
[9] K. Tar, S. Szegedi, “A statistical model for estimating electricity produced by wind energy”, Renewable Energy, 2011, Vol. 36, pp. 823–828.
[10] R. Blonbou, “Very short-term wind power forecasting with neural networks and adaptive Bayesian learning”, Renewable Energy, 2011, Vol. 36, pp. 1118–1124.
[11] DA. Fadare, “The application of artificial neural networks to mapping of wind speed profile for energy application in Nigeria”, Applied Energy, 2010, Vol. 87, pp. 934–942.
[12] G. Kariniotakis, GS. Stavrakakis, EF. Nogaret, “A fuzzy logic and neural network based wind power model”, In: Proceedings the 1996 European wind energy conference, Goteborg, Sweden, 1996, pp. 596–599.
[13] X. Wang, G. Sideratos, N. Hatziargyriou, LH. Tsoukalas, “Wind speed forecasting for power system operational planning”, In: 2004 International conference on probabilistic methods applied to power systems, 2004, pp. 470–474.
[14] M. Carolin Mabel, and E. Fernandez, “Analysis of wind power generation and prediction using ANN: A case study”, Renewable Energy, 2008, Vol. 33, pp. 986–992.
[15] S. Ke´louwani, K. Agbossou, “Non-linear model identification of wind turbine with a neural network”, IEEE Transactions on Energy Conversion, 2004, Vol.19, pp. 607–612.
[16] I.J. Ramirez-Rosado, et al., “Comparison of two new short-term wind-power forecasting systems”, Renewable Energy, 2009, Vol. 34, pp. 1848–1854.
[17] A. More, MC. Deo, “Forecasting wind with neural networks”, Marine Structures, 2003, Vol. 16, pp.35–49.
[18] S. Salcedo-Sanz, et al., “Short term wind speed prediction based on evolutionary support vector regression algorithms”, Expert Systems with Applications, In Press, Corrected Proof, Available online 29 September 2010.
[19] M.A. Mohandes, et al., “Support vector machines for wind speed prediction”, Renewable Energy, 2004, Vol. 29, pp. 939–947.
[20] E. Cadenas, W. Rivera, “Wind speed forecasting in three different regions of Mexico, using a hybrid ARIMA-ANN model”, Renewable Energy, 2010, Vol. 35, pp. 2732–2738.
[21] M. Jafarian, A.M. Ranjbar, “Fuzzy modeling techniques and artificial neural networks to estimate annual energy output of a wind turbine”, Renewable Energy, 2010, Vol. 35, pp.2008–2014.
[22] A. Costa, A. Crespo, J. Navarro, G. Lizcano, H. Madsen, E. Feitosa, “A review on the young history of the wind power short-term prediction”, Renewable and Sustainable Energy Reviews, 2008, Vol. 12, pp. 1725–1744.
[23] M. Lei, L. Shiyan, J. Chuanwen, L. Hongling, Z. Yan, “A review on the forecasting of wind speed and generated power”, Renewable and Sustainable Energy Reviews, 2009, Vol. 13, pp. 915–920.
[24] J. Kennedy, R.C. Eberhart, “Particle swarm optimization”, In: Proceedings of the 1995 IEEE International Conference on Neural Networks, IEEE Service Center, Piscataway, 1995, pp. 1942–1948.
[25] D. E. Goldberg (1989). Genetic Algorithms in Search, Optimization and Machine Learning. Addison Wesley.
[26] W.C. Yeh, “A Two-Stage Discrete Particle Swarm Optimization for the Problem of Multiple Multi-Level Redundancy Allocation in Series Systems”, Expert Systems with Applications, 2009, Vol. 36, pp. 9192–9200.
[27] W.C. Yeh, W.W. Chang, and Y.Y. Chung, “A new hybrid approach for mining breast cancer pattern using Discrete Particle Swarm Optimization and Statistical method”, Expert Systems with Applications, 2009, Vol. 36, pp. 8204–8211.
[28] W.C. Yeh, “A Optimization the End-of-Life Disassembly Sequencing Problem Based on the Use of a Novel Method based on Self-adaptive Simplified Swarm Optimization and Precedence Preservative Operator”, IEEE Transactions on Systems, Man, and Cybernetics (Part A) (SMCA-10-02-0055), 2011/01/12.
[29] W.C. Yeh, “Study on Quickest Path Networks with Dependent Components and Apply to RAP”, 2008/08/01~2011/07/31, Report, NSC 97- 2221- E- 007- 099- MY3.
[30] Laurene Fausett (1994). Fundamentals of Neural Networks. United States: Upper Saddle River.
[31] L. Kua-Ping, R. Fildes, “The accuracy of a specifying feed forward neural networks forecasting” Computers & Operations Research, 2005, Vol. 32, pp. 2151–2169.
[32] Y.-L. Tu, et al., “Artificial neural networks in the estimation of monthly capacity factors of WECS in Taiwan”, Energy Conversion and Management, 2010, Vol. 51, pp. 2938–2946.
[33] A. Yadav, D. Mishra, R. N. Yadav, S. Ray, P. K. Kalra, “Time-series prediction with single integrate-and-fire neuron”, Applied Soft Computing, 2007, Vol. 7, pp. 739–745.
[34] A. Yadav, et al., “Time-series prediction with single integrate-and-fire neuron” Applied Soft Computing, 2007, Vol. 7, pp.739–745.
[35] R.N. Yadav, et al., “Time series prediction with single multiplicative neuron model”, Applied Soft Computing, 2007, Vol. 7, pp. 1157–1163.
[36] L. Zhao, Y. Yang, “PSO-based single multiplicative neuron model for time series prediction”, Expert Systems with Applications, 2009, Vol. 36, pp. 2805–2812.
[37] R. N. Yadav, P. K. Kalra, J. John, “Time series prediction with single multiplicative neuron model” Applied Soft Computing, 2007, Vol. 7, pp. 1157–1163.
[38] E.M. Iyoda, H. Nobuhara, K. Hirota, “A solution for the N-bit parity problem using a single multiplicative neuron”, Neural Process. Lett., 2003, Vol. 18, pp. 233–238.
[39] M. Mackey, L. Glass, “Oscillation and chaos in physiological control systems”, Science, 1977, Vol. 197, pp. 287–289.
[40] http://robjhyndman.com/TSDL/other/
[41] http://www.cs.colostate.edu
[42] U. Hübner, N.B. Abraham, C.O. Weiss, “Dimensions and entropies of chaotic intensity pulsations in a single-mode far-infrared NH3 laser”, Physical Review A, 1989, Vo1.40, pp. 6354–6365.
[43] N.A. Gershenfeld, A.S. Weigend (1993). The future of time series, in Time Series Prediction: Forecasting the Future and Understanding the Past, eds. A.S. Weigend and N.A. Gershenfeld, pp. 1–70, Addison-Wesley, Reading, MA.
[44] TG. Barbounis, JB. Theocharis, MC. Alexiadis, PS. Dokopoulos, “Long-term wind speed and power forecasting using local recurrent neural network models”, IEEE Transactions on Energy Conversion, 2006, Vol. 21, pp. 273–284.
[45] E. Cadenas, W. Rivera, “Short term wind speed forecasting in La Venta, Oaxaca, Me´xico, using artificial neural networks”, Renewable Energy, 2009, Vol. 34, pp. 274–278.
[46] G. Li, J. Shi, “On comparing three artificial neural networks for wind speed forecasting”, Applied Energy, 2010, Vol. 87, pp. 2313–2320.
[47] Subhash Sharma (1996). Applied Multivariate Techniques. United States: Wiley.