臺灣博碩士論文加值系統

摘 要
近來解制及自由化在世界各地展開，不論在電信、運輸或電力產業均已見其成效，而電力產業邁向自由化後，市場買賣的行為變成一種透過競標方式的商業交易行為。在現今解制電業市場中，區域邊際價格（Locational Marginal Prices, LMPs）預測變得越顯重要，推估LMPs短期走勢，可幫助市場參與者於現貨價格市場中制訂競標策略。準確地預測電能價格是相當關鍵的，因為預測準確性的增加，相對之下可以降低發電業者或配電公司因為高估或低估自己的收益所造成的風險，因此也可提供較佳的風險管理。本論文利用類神經網路與模糊分類技術提出一個預測LMP的方法。
本論文利用模糊分類（Fuzzy-C-Means, FCM）的方法，對負載時段分別進行輕載、重載兩類，以及輕載、中載、重載三類的分割，並且配合遞迴式類神經網路與傳統倒傳遞類神經網路，分別對完整資料以及工作日與假日分開進行預測。
本論文將運用美國PJM（Pennsylvania, New Jersey, Maryland）Interconnection系統的歷史資料作為模擬測試之對象，利用所提出的人工智慧方法進行LMP之預測，並計算實際值與預測值兩者之誤差量及相關係數，以證實本論文所提出之LMP預測方法之可行性。

Abstract
Recently, deregulation has had a great impact on the telecommunications, transportation and electric power industry in various countries. Bidding competition is one of the main transaction approaches after deregulation. In today’s deregulated markets, Locational Marginal Prices (LMP) forecasting is becoming more and more important. In the short-term, LMPs reveal important information that is helpful for the market participants to develop their bidding strategies. Accuracy in forecasting these LMPs is crucial, since more accuracy in forecasting reduces the risk of under- or over-estimating the revenue from the gencos or transcos and provides better risk management. Artificial Neural Network (ANN) and Fuzzy-C-Means (FCM) algorithm based LMP forecasting is presented in this thesis..
The data are partitioned into two clusters (low load and heavy load) and three clusters (low load, middle load and heavy load) by FCM according to the load levels. The performance on LMPs forecasting toward the whole data and the data with separating weekday data from weekend data by Recurrent Neural Network (RNN) and Back-Propagation Network is given.
This thesis employs the PJM (Pennsylvania, New Jersey, Maryland) Interconnection historical data to serve as a test system for LMPs forecasting by the proposed Artificial Intelligence method. The errors and correlation coefficient between actual LMPs and forecasted LMPs are shown in order to show the applicability of the proposed method.
Keywords: Artificial Neural Network, Fuzzy-C-Means, LMP forecasting

目錄
中文摘要 Ⅰ
英文摘要 Ⅱ
誌謝 Ⅳ
目錄 Ⅴ
圖目錄 Ⅹ
表目錄
第一章 緒論 1
1-1 研究背景及動機 1
1-2 文獻回顧 2
1-3 研究目標 3
1-4 研究進行步驟 4
1-5 本論文之貢獻 4
1-6 論文架構 5
第二章 問題描述 6
2-1 前言 6
2-2 PJM系統介紹 6
2-3 區域邊際價格 9
2-4 節點電價的數學意義 10
2-5 LMPs預測的重要性 11
第三章 類神經網路與模糊分割理論 13
3-1類神經網路簡介 13
3-2 類神經網路基本架構 16
3-2-1 處理單元 16
3-2-2 層 17
3-2-3 網路 17
3-3倒傳遞類神經網路 18
3-3-1倒傳遞類神經網路基本結構 18
3-3-2倒傳遞演算法 19
3-4遞迴式類神經網路 21
3-4-1遞迴式類神經網路結構 22
3-4-2遞迴式類神經網路演算法 24
3-5模糊分類 26
3-5-1模糊理論及模糊分類簡介 26
3-5-2模糊C分割模型 26
3-5-3FCM演算法 27
第四章 LMP預測 29
4-1 PJM系統中LMP之特性 29
4-2類神經網路預測 32
第五章 模擬測試 34
5-1資料設計 34
5-2負載分兩類結果 34
5-2-1工作日（Weekday）分類結果 35
5-2-1-1當m=2時之負載分類結果 35
5-2-1-2當m=1.5時之負載分類結果 37
5-2-1-3當m=1.1時之負載分類結果 38
5-2-2星期六分類結果 40
5-2-3星期日分類結果 42
5-3負載分三類結果 43
5-3-1工作日（Weekday）分類結果 44
5-3-2星期六分類結果 45
5-3-3星期日分類結果 47
5-4利用遞迴式類神經網路進行LMP預測 49
5-4-1Kenney-500kV之LMP預測結果 50
5-4-2Benning-20kV之LMP預測結果 54
5-5利用倒傳遞類神經網路進行LMP預測 56
5-5-1Kenney-500kV之LMP預測結果 56
5-5-2Benning-20kV之LMP預測結果 59
5-6工作日週末分開利用隱藏層遞迴式類神經網路
進行LMP預測61
5-6-1Kenney之工作日週末分開之LMP預測 61
5-6-1-1工作日之LMP預測結果 61
5-6-1-2星期六之LMP預測結果 64
5-6-1-3星期日之LMP預測結果 66
5-6-2Benning之工作日週末分開之LMP預測 68
5-6-2-1工作日之LMP預測結果 68
5-6-2-2星期六之LMP預測結果 70
5-6-2-3星期日之LMP預測結果 72
5-7工作日週末分開利用輸出層遞迴式類神經網路
進行LMP預測74
5-7-1Kenney之工作日週末分開之LMP預測 74
5-7-1-1工作日之LMP預測結果 74
5-7-1-2星期六之LMP預測結果 77
5-7-1-3星期日之LMP預測結果 79
5-7-2Benning之工作日週末分開之LMP預測 81
5-7-2-1工作日之LMP預測結果 81
5-7-2-2星期六之LMP預測結果 83
5-7-2-3星期日之LMP預測結果 85
5-8工作日週末分開利用輸入層遞迴式類神經網路
進行LMP預測87
5-8-1Kenney之工作日週末分開之LMP預測 87
5-8-1-1工作日之LMP預測結果 87
5-8-1-2星期六之LMP預測結果 90
5-8-1-3星期日之LMP預測結果 92
5-8-2Benning之工作日週末分開之LMP預測 94
5-8-2-1工作日之LMP預測結果 94
5-8-2-2星期六之LMP預測結果 96
5-8-2-3星期日之LMP預測結果 98
5-9工作日週末分開利用倒傳遞類神經網路
進行LMP預測87
5-9-1Kenney之工作日週末分開之LMP預測 100
5-9-1-1工作日之LMP預測結果 100
5-9-1-2星期六之LMP預測結果 103
5-9-1-3星期日之LMP預測結果 105
5-9-2Benning之工作日週末分開之LMP預測 107
5-9-2-1工作日之LMP預測結果 107
5-9-2-2星期六之LMP預測結果 109
5-9-2-3星期日之LMP預測結果 111
5-10分兩類利用遞迴式類神經網路進行LMP預測 113
5-10-1輕載之LMP預測 113
5-10-2重載之LMP預測 116
5-11分三類利用遞迴式類神經網路進行LMP預測 118
5-11-1輕載之LMP預測 118
5-11-2中載之LMP預測 123
5-11-3重載之LMP預測 123
5-12預測結果之討論 125
5-12-1原始完整資料輸入之LMP預測 125
5-12-2工作日週末分開之LMP預測 126
5-12-3分兩類之LMP預測 129
5-12-4分三類之LMP預測 130
第六章 結論 131
參考文獻 132

參考文獻[1]Y.Y. Hong, and M.T. Weng, “Investigation of Nodal Prices in Deregulated Competitive Market -Case Studies,” international conference on PowerTech, Budapest, Aug. 29-Sep. 2, 1999, pp. 161.[2]A. Ott, “PJM: A Full Service ISO Market Evolution,” IEEE Power Engineering Society Summer Meeting, vol. 2, 1999, pp. 746-748.[3]Congestion Management Working Group of NERC Market Interface Committee, “Comparison of System Redispatch Methods for Congestion Management,” September 1999.[4]S. Hunt and G. Shuttleworth, Competition and Choice in Electricity, John Wiley & Sons, New York, 1996.[5]T.W. Hissey, "International Experience in Transmission Open Access," IEEE Power Engineering Review, Vol. 14, No. 12, Dec. 1994, pp.3-18. [6]O.B. Fosso, A. Gjelsvik, A. Haugstad, B. Mo, and I. Wangensteen, "Generation Scheduling in a Deregulated System. The Norwegian Case," IEEE 1998 PES Winter Meeting, Tampa, FL, 1998, PE-229-PWRS-0-11-1997.[7] J.W. Williams, "Open Transmission Access," IEEE Power Engineering Review, Vol. 16, No. 5, May 1996, pp.17-19. [8]"Promoting Wholesale Competition Through Open Access Non-discriminatory Transmission Services by Public Utilities," Federal Energy Regulatory Commission Order No. 888 & 889, 1996.[9]"Notices of Proposed Rulemaking," Federal Energy Regulatory Commission, Congressional Record, Docket No. RM95-8-000, March 29, 1995.[10]"Capacity Reservation Open Access Transmission Tariffs," Federal Energy Regulatory Commission, Docket No. RM 96-11-000, 1996.[11]A. Zobian and M.D. Ilic, "Unbundling of Transmission and Ancillary Services, Part I: Technical Issues & Part II: Cost-Based Pricing Framework," IEEE Trans. on Power Systems, Vol. 12, No. 2, pp. 539-558.[12]A. Khotanzad, R. Afkhami-Rohnai and D. Maratukulam, “ANNSTLF-Artificial Neural Network Short-term Load Forecaster-generation Three,” IEEE Trans. Power Systems, vol. 13, no. 4, November 1998, pp. 1413-1422.[13]A. Keyhani, H.R. Kassaei, T. Woung, and M. Rahman, “A Hybrid Fuzzy, Neural Network Bus Load Modeling and Predication,” IEEE Trans. Power Systems, vol. 14 ,no. 2, May 1999, pp. 718-724.[14]S.Rahman and I. Drezga, “Input Variable Selection for ANN-based Short-term Load Forecasting,” IEEE Trans. Power systems, vol. 13, no. 4, November 1998, pp. 1238-1244. [15]K.Y. Lee, T.I. Choi, C.C. Ku ,and J.H. Park, “Short-term load forecasting using diagonal recurrent neural network,” Proceedings of the Second International Forum on Applications of Neural Networks to Power Systems, 1993, pp. 227-232.[16]A. Wang and B. Ramsay, “Prediction of system marginal price in the UK power pool,” international conference on Neural Networks, vol. 4, 1997, pp. 2116-2120.[17]B.R. Szkuta, L.A. Sanabria, and T.S. Dilon, “Electricity Price Short-term Forecasting Using Artificial Neural Networks,” IEEE Trans. Power Systems, vol. 14,no. 3, August 1999, pp. 2116-2120.[18]F. Gao, X. Guan, X.R. Cao, and A. Papalexopoulos, “Forecasting Power Narket Clearing Price and Quantity Using a Neural Network,” IEEE PES Summer Meeting, Seattle, 2000.[19]J.N. Hwang and E. Little, “ReaTime Recurrent Neural Networks for Time Series Prediction and Confidence Estimation,” IEEE International Conference on Neural Networks, vol. 4, 1996, pp. 1889-1994.[20]H. Mori and T. Ogasawara, “A Recurrent Neural Network for Short-term Load Forecasting,” Proceedings of the Second International Forum on Applications of Neural Networks to Power Systems, 1993, pp. 395-400.[21]X. Lu and C. Chen, “A New Hybrid Recurrent Neural Network,” Proceedings of the 1999 IEEE Internationa Symposium on Circuits and Systems, vol. 5, 1999, pp.616-618.[22]Y.Y. Hong and C.Y. Hsiao, “Locational Marginal Price Forecasting in Deregulated Electric Markets Using a Recurrent Neural Network,” IEEE PES Winter Meeting, Columbus, 2001.[23]J.J. Guo and Peter B. Luh, “Improving the prediction of Radial Basis Fuction Networks for Power Systems,” IEEE PES Winter Meeting, Columbus, 2001.[24]Ernam Ni and Peter B. Luh, “Forecasting Power Market Clearing Price and its Discrete PDF using a Bayesian- Based Classification Method,” IEEE PES Winter Meeting, Columbus, 2001.[25]Li Zhang and Peter B. Luh, “Confidence Regions for Cascaded Neural Network Prediction in Power Markets,” IEEE PES Winter Meeting, Columbus, 2001.[26]L. A. Zadeh, “Fuzzy Set,” Information and Control, Vol. 8, 1965, pp. 338-353.[27]J.A. Momoh, X.W. Ma and K.Tomsovic, “Overview and Literature Survey of Fuzzy Set Theory in Power System,” 1995 IEEE PES Winter Meeting, Jan. 29~Feb. 2, New York, 95 WM 208-9 PWRS.[28]K.H. Abdul-Rahman and S.M. Shahidehpour, “Reactive Power Optimization Using Fuzzy Load Representation,” 1993 IEEE PES Summer Meeting, Vanconver, B.C., Canada, July 18-22, 1993, Paper No. 93 SM 502-5 PWRS[29]K.H. Abdul-Rahman and S.M. Shahidehpour, “A Fuzzy based Optimal Reactive Power Control,” 1992 IEEE PES Summer Meeting, Seattle WA, July 12-16, 1992, Paper No.92 SM 402-8 PWRS.[30]Kevin Tomsovic, “A Fuzzy Linear Programming Approach to the Reactive Power/Voltage Control Problem,” IEEE Trans. on Power Systems, Vol. 7, No. 1, Feb. 1992, pp. 287-293.[31]V. Miranda and J.T. Saraiva, “Fuzzy Modeling of Power System Optimal Load Flow,” IEEE Trans. on Power Systems, Vol. 7, No. 2, May 1992, pp. 843-849.[32]N. Hosseinzadeh and A. Kalam, “A Rule-Based Fuzzy Power System Stabilizer Tuned by a Neural Network,” IEEE Trans. on Energy Conversion, Vol. 14, No. 3, Sep. 1999, pp. 773-779.[33]S.J. Huang, “Application of Genetic Based Fuzzy Systems to Hydroelectric Generation Scheduling,” IEEE Trans. on Energy Conversion, Vol.14, No.3, Sep. 1999, pp. 724-730.[34]H.J.C. Peiris, U.D. Annakkage, and N.C. Pahalawaththa, “Generation of Fuzzy Rules to Develop Fuzzy Logic Modulation Controllers for Damping of Power System Oscillations,” IEEE Trans. on Power Systems, Vol. 14, No.4, Nov. 1999, pp. 1440-1445.[35]J. Nazarko and W. Zalewski, “The Fuzzy Regression Approach to Peak Load Estimation in Power Distribution Systems,” IEEE Trans. on Power Systems, Vol. 14, No. 3, Aug. 1999, pp. 809-814.[36]R. Bellman, R. kalaba, L. A. Zadeh, “Absraction and Pattern Classification,” J, Math. Anal. and Appl., Vol. 2, 1996, pp. 581-586.[37]E. H. Ruspini, “A New Approach to Clustering,” Infornation and Control, Vol. 15, 1969, pp. 21-33.[38]E. H. Ruspini, “Numberical Methods for Fuzzy Clustering,“ Inf. Sci., Vol. 2, 1970, pp. 319-350.[39]J. C. Dunn, “A Fuzzy Relative of the ISODATA Process and Its Use in Detectng Compact Well-Separated Clusters,” J. Cybermetics 3, 1974, pp. 32-57.[40]H.J. Zimmerman,, “Fuzzy Set Theory and Its Application,” Dordrecht, Holland, Kluwer, 1991.[41] M.S. Yang and C.H. Ko, “On a Class of Fuzzy C-Number Clustering Procedures for Fuzzy Data,” Fuzzy Set Syst., Vol. 84, pp. 49-60.[42] H. Tanaka, S. Uejima, K. Asai, “Linear Regression Analysis with Fuzzy Model,” IEEE Trans. on Systems, Man and Cybernetics, Vol. 12, No. 6, Dec. 1982, pp. 903-906.[43]H. Tanaka, and H. Ischibuch “Possibilistic Regression Analysis Based on Linear Programming,” Fuzzy Regression Analysis, (eds. J. Kacprzyk, M. Fedrizzi), Physica-Verlag, Heidelberg, 1992, pp. 47-60.[44]M.S. Bazaraa and J.J. Jarvis, Linear Programming and Network Flows, John Wiley & Sons, New York, 1977.[45]葉怡成，「類神經網路模式應用與實作」，儒林圖書有限公司，1998年1月五版。[46]王進德、蕭大全，「類神經網路與模糊控制理論入門」，全華科技圖書股份有限公司，民國83年9月。