對社區發展而言，估測電力需求量為都市計劃中基礎設施設計的主要課題之一，而負載預測與電力需求之準確性緊密相關。負載預測方法雖然可使用自我回歸模型，藉由過去的歷史資料去推測出有時序性的電力負載趨勢，但非時序因素仍明顯地影響負載預測的準確性。因此本論文以提升預測之準確性為目標，提出一個可考慮非時間因素影響之負載預測架構。為了因應不同預測的對象而提升其預測能力，本文採用類神經網路搭配迴歸時間序列演算法建構混合型的負載預測模型。我們以國立成功大學（NCKU）為負載預測的對象，將其預測的結果使用最佳化演算法選出最適當的契約容量。其預測結果顯示本論文所提出的混合模型對於基礎設施之負載管理擬定將大有助益。

Estimating appropriate margins of electric power demands for the developing communities is one of the main issues in the infrastructure design of the urban planning. The accuracy of the demand estimation is highly dependent on the load forecast of the planning subject. Although the chronicle patterns inherent in the electric loads could be approached by the autoregressive model from the historical records, factors other than the chronicle patterns could still have significant impacts on the accuracy of the load forecast. Finding a way to incorporate non-chronicle factors into the load forecasting mechanism and thus enhance the forecasting accuracy is the objective of this thesis. To facilitate the forecasting ability for the various planning subjects, this thesis proposes a hybrid load forecasting model that combines the autoregressive time series algorithm with neural network to perform load forecasting. We took National Cheng Kung University (NCKU) as an example to test the accuracy of the proposed load forecast model, and then estimate the demand capacity using the optimization rules, which is gainfully useful in the infrastructure design of the demand planning.

[1] T. Haida and S. Muto, “Regression Based Peak Load Forecasting Using a Transformation Technique,” IEEE Transactions on Power Systems, Vol. 9, No. 4, pp. 1788-1794, November 1994.
[2] A. D. Papalexopoulos and T. C. Hesterberg, “A Regression-Based Approach to Short-Term System Load Forecasting,” IEEE Transactions on Power Systems, Vol. 5, No. 4, pp.1535-1550, November 1990.
[3] A. D. Papalexopoulos and T. C. Hesterberg, “A Regression-based Approach to Short-term System Load Forecasting,” IEEE Transactions on Power System., Vol. 5, No. 4, pp. 1535-1544, 1990.
[4] G. E. Box and G. M. Jenkins, Time Series Analysis Forecasting And Control, Holden-Day Publishing Company, New York, USA, 1982.
[5] M. T. Hagan and S. M. Behr, “The time series approach to short-term load forecast,” IEEE Trans. Power Syst., Vol. 2, No. 3, pp. 785-791, August 1987.
[6] N. Amjady, “Short-term hourly load forecasting using time-series modeling with peak load estimation capability,” IEEE Trans. Power Syst., Vol. 16, No. 4, pp. 798-805, 2001.
[7] A. A. El Desouky and M.M. EI Kateb, “Hybrid adaptive techniques for electric-load forecast using ANN and ARIMA,” IEE Proceedings- Generation Transmission and Distribution, Vol. 147, No. 4, pp. 213-217, 2000.
[8] F. J. Nogales and J. Contreras, “Forecasting Next-Day Electricity Prices by Time Series Models,” IEEE Transactions on Power Systems, Vol. 17, No. 2, pp. 342-348, May 2002.
[9] K. L. Ho, Y. Y. Hsu, C. F. Chen, T. E. Lee, C. C. Liang, T. S. Lai, and K. K. Chen, “Short Term Load Forecasting of Taiwan Power System Using a Knowledge-Based Expert System,” IEEE Transactions on Power Systems, Vol. 5, No. 4, pp. 1214-1221, November 1990.
[10] S. Rahman and R. Bhatnagar, “An Expert System Based Algorithm for Short-Term Load Forecasting,” IEEE Transactions on Power Systems,Vol. 3, No. 2, pp. 908-914, May 1988.
[11] H. Mori and H. Kobayashi, “Optimal Fuzzy Inference for Short-Term Load Forecasting,” IEEE Transactions on Power Systems, Vol. 11, No. 1, pp. 390-396, February 1996.
[12] M. Y. Chow, J. Zhu and H. Tram, “Application of Fuzzy Multi-Objective Decision Making in Spatial Load Forecasting,” IEEE Transactions on Power Systems, Vol. 13, No. 3, pp.1185-1190, August 1998.
[13] A-G. Bakirtzis, (M), J. B. Theocharls, (M), S. J. Klartzis, (S), K. J. Satsios, “Short Term Load Forecasting Using Fuzzy Neural Networks,” IEEE Transactions on Power Systems, Vol. 10, No. 3, pp.1518-1524, 1995.
[14] E. Doveh et al, “Experience with FNN models for medium term power demand predictions,” IEEE Transactions on Power Systems, Vol.14, No.2, pp.538-546, 1999.
[15] Z. L. Gaing and R. C. Leon, “Optimal Grey Topological Predicting Approach to Short-Term Load Forecasting,” Proceedings of the IEEE Conference on Power Engineering Society Summer Meeting, Vol. 3, pp. 1244-1250, July 2002.
[16] H. T. Yang, T. C. Liang, K. R. Shih, and C. L. Huang, “Power System Yearly Peak Load Forecasting: A Grey System Modeling Approach,” Proceedings of EMPD ’95 Conference on Energy Management and Power Delivery, Vol. 1, pp. 261-266, November 1995.
[17] T. W. S. Chow, C. T. Leung, “Neural network based short-term load forecasting using weather compensation,” IEEE Transactions on Power Systems, Vol.11, No.4, pp.1736-1742, 1996.
[18] W. Charytoniuk, M. S. Chen, “Very short-term load forecasting using artificial neural networks,” IEEE Transactions on Power Systems, Vol.15, No.1, pp.263-268, 2000.
[19] Nagasaka, K.and Al Mamun, M., “Long-term peak demand prediction of 9 Japanese power utilities using radial basis function networks,” Proceedings of IEEE Power Engineering Society General Meeting,vol.1,no.6-10,pp.315 - 322, June 2004.
[20] T. Yalcinoz and U. Eminoglu, “Short term and medium term power distribution load forecasting by neural networks,” Energy Convers Manage, Vol. 46, pp. 1393-1405, 2005.
[21] Moghram, I., and Rahman, S., “Analysis and evaluation of five short-term load forecasting techniques,” IEEE Trans. Power Syst., Vol. 4, No. 4, pp. 1484-1491, 1989.
[22] Chow, T. W. S., and Leung, C.T., “Neural network based short-term load forecasting using weather compensation,” IEEE Trans. Power Syst., Vol. 11, No. 4, pp. 1736-1742, 1996.
[23] Drezga, I., and Rahman, S., “Input variable selection for ANN-based short-term load forecasting,” IEEE Trans. Power Syst., Vol. 13, No. 4, pp. 1238-1244, 1998.
[24] Yuan, J. L., and Fine, T. L., “Neural-network design for small training sets of high dimension,” IEEE Trans Neural Networks, Vol. 9, No. 2, pp. 266-280, 1998.
[25] 葉怡成，類神經網路模式應用與實作，儒林圖書公司，2003。
[26] 徐葉良，元智大學機械所最佳化設計課程教材，最佳化設計實驗室，2005。
[27] Edwin K.P. Chong and Stanislaw H.Zak, An Introduction to Optimization, 3rd ed., Wiley Interscience, 2001.
[28] 蘇木村、張孝德，機器學習:類神經網路、模糊系統以及基因遺傳演算法則，全華科技圖書股份公司，2001。
[29] 李聰穎、林義傑、詹榮茂、陳俊隆，基因演算法應用於時間電價用戶契約容量選定，明新學報31期，2007。
[30] 林茂文，時間數列分析與預測，華泰書局，1992增訂版。
[31] 劉興明，結合自我迴歸與類神經網路應用於電力負載預測，國立東華大學資訊工程研究所碩士論文，2004。
[32] M. Espinoza, C. Joye, R. Belmans, “Short-Term Load Forecasting, Profile Identification, and Customer Segmentation: A Methodology Based on Periodic Time Series,” IEEE Trans. Power Syst , Vol. 20, No. 3, August 2005.
[33] Ljung, L., System Identification-Theory for the User, Prentice- Hall, Englewood Cliffs, N.J, 1987.
[34] Lewis, C. D, Industrial and Business Forecasting Methods, London, Butterworths, 1982.
[35] 羅華強，類神經網路-MATLAB的應用，清蔚科技公司，2001。
[36] 台灣電力公司，高壓用戶與時間電價，民國2002年10月。
[37] T. Y. Lee and N. Chen, “Optimal Capacity of the Battery Energy Storage System in a Power System,” IEEE Trans. on Energy Conversion, Vol. 8, No. 4, pp. 667-673, Dec. 1993.
[38] 台灣電力公司，台灣電力公司營業規則，2001年4月2日。
[39] Bahman Kermanshahi, “Recurrent neural network for forecasting next 10 years loads of nine Japanese utilities,” Neurocomputing 23, pp. 125-133, 1998.