臺灣博碩士論文加值系統

本論文主要是以類神經網路為基本架構，研究三種不同演算法及參數型態應用於電力系統不良資料(Bad Data)之偵測，所提方法的目的是為了改進傳統統計法逐步偵測的方式，以增加偵測的效能。其三種架構分別為：以實數為參數型態的倒傳遞類神經網路(Real Back-Propagation Artificial Neural Network)的架構，其優點可用於並行偵測不良資料的存在；另一為以複數型態為參數的倒傳遞類神經網路(Complex Back-Propagation Neural Network)，所用的方法是將參數型態分離為實部與虛部，並以複數神經元作為網路架構，以為學習及偵測之基本單元，其優點是：可減少神經元的個數、加快收斂效果、提高雜訊免疫力；最後以複數推廣型卡爾曼濾波器為基礎之類神經網路(Complex Extended Kalman Filter Artificial Neural Network)，其方法是利用卡爾曼濾波器估測的方式作權重的調整，本法最主要的優點是：雜訊抵抗力強，應用於不良資料偵測可顯著提高不良資料的辨識率。
本論文利用六個匯流排電力系統與IEEE標準之30個匯流排的電力系統作基礎，驗證本論文所提各種方法之可行性。經由各種不良資料的偵測及數值模擬對此三種方法作比較證實：卡爾曼類神經網路所使用的神經元個數較實數型式減少一半，而在訊號雜訊比40dB情況，不良資料的偵測仍可獲得不錯的成效。

This thesis proposes three different algorithms based on Artificial Neural Network (ANN) for improving performances of bad data detection in power systems. First, it is ANN of real-type parameter and it has an advantage of parallel process. Secondly, it is complex ANN since it has combined the real and imagination parts to one neuron that can reduce the number of the neuron and enhance the speed of convergence. Thirdly, it is the ANN based on Kalman filter. This approach modifies the weighting factor by using the estimation manner. Moreover, this method has less impact on noises during bad data detection. In other words, it is better on identifying the bad data.
To verify the feasibility of the above three methods, two cases including 6-bus and IEEE standard of 30-bus power systems are used in this thesis. Based on various simulation cases, the number of neurons used in the Kalman filter ANN is half of the real-type ANN. Moreover, the obtained result of bad-data detection under the condition of SNR 40dB is still good.

摘 要 i
ABSTRACT ii
目 錄 iv
圖 目 錄 vi
表 目 錄 ix
符 號 說 明 x
第一章 緒論 1
1.1 研究背景及動機 1
1.2 論文架構 3
第二章 實數型倒傳遞類神經網路 5
2.1 前言 5
2.2 不良資料偵測流程 5
2.3 類神經網路簡介 9
2.3.1基本神經元架構 10
2.3.2激發函數(Activation Function) 11
2.3.3多層網路結構 13
2.3.4實數型倒傳遞類神經網路模型 16
2.4結語 21
第三章 複數型倒傳遞類神經網路 22
3.1 前言 22
3.2 不良資料偵測流程 23
3.3 複數類神經網路簡介 25
3.3.1複數神經元架構 26
3.3.2複數倒傳遞演算法 28
3.4 結語 32
第四章 複數推廣型卡爾曼濾波器類神經網路 33
4.1 前言 33
4.2 不良值偵測流程 33
4.3 複數卡爾曼濾波器簡介 36
4.4 結語 39
第五章 數值模擬 40
5.1前言 40
5.2 電力系統模型簡介 40
5.2.1六個匯流排之電力系統 40
5.2.2 IEEE標準30個匯流排之電力系統 45
5.3 類神經網路模擬測試 53
5.4 結語 94
第六章 結論與未來研究方向 95
6.1 結論 95
6.2未來研究方向 95
參考文獻 97
簡 歷 100

[1]S. J. Huang and K. R. Shih, “Dynamic-state-estimation scheme including nonlinear measurement-Function considerations,” IEE Proceedings-Generation, Transmission and Distribution, Vol. 149, No. 6, pp. 673-678, November 2002.
[2]J. K. Mandal, A. K. Sinha and L. Roy, “Incorporating nonlinearities of measurement function in power system dynamic state estimation,” IEE Proceedings-Generation, Transmission and Distribution, Vol. 142, No. 3, pp. 289-296, May 1995.
[3]K. R. Shih and S. J. Huang, “Application of a robust algorithm for dynamic state estimation of a power system,” IEEE Transactions on Power Systems, Vol. 17, No. 1, pp. 141-147, February 2002.
[4]J. M. Lin. S. J. Huang and K. R. Shih, “Application of sliding surface-enhanced fuzzy control for dynamic state estimation of a power system,” IEEE Transactions on Power Systems, Vol. 18, No. 2, pp. 570-577, May 2003.
[5]W. L. Miller and J. B. Lewis, “Dynamic state estimation in power systems,” IEEE Transactions on Automatic Control, Vol. 16, No. 6, December 1971.
[6]F. C. Schweppe, J. Wildes and D. B. Rom, “Power system static state estimation,” Parts I, II, III, IEEE Trans. Power Appar. Syst., PAS-89 , pp.120-135, 1970.
[7]R. E. Larson, W.F. Tinney, L.P. Hadju and D.S. Piercy, “State estimation in power system, Parts I and II. Theory and feasibility,” IEEE Trans. Power Appar. Syst., PAS-89, pp.345-362, 1970.
[8]M. B. Do Coutto Filho, A. M. Leite da Silva, J. M. C. Calvo Cantera and R. A. da Silva, “Information debugging for real-time power systems monitoring,” IEE Proceedings, Vol. 136, No. 3, pp. 145-152, May 1989.
[9]G. Durgaprasad and S. S. Thakur, “Robust dynamic state estimation of power systems based on M-Estimation and realistic modeling of system dynamics,” IEEE Transactions on Power Systems, Vol. 13, No. 4, pp.1331-1336, November 1998.
[10]史光榮, “電力系統動態狀態估計與負載預測之探討與研究,” 成功大學博士論文, 中華民國九十一年十月。
[11]林矩民, “電力系統狀態估測與不良資料鑑別之研究,” 成功大學博士論文, 中華民國九十三年六月。
[12]A. J. Wood and B. F. Wollenberg, “Power generation, operation and control,” John Wiley & Sons, Inc. 1996.
[13]H. Salehfar, and R. Zhao, “A neural network preestimation filter for bad-data detection and identification in power system state estimation,” Electric Power System Research, vol. 34, Issue 2, pp.127-134, August 1995.
[14]B. Widrow and M. A. Lehr, “30 years of adaptive neural networks: perceptron, madaline, and backpropagation,” Proceeding of the IEEE, Vol. 78, No. 9, pp.1415-1412, September. 1990.
[15]H. Leung and S. Haykin, “The complex backpropagation algorithm,” IEEE Transactions on Signal Processing, Vol. 39, No 9, pp. 2101-2104, September 1991.
[16]N. Benvenuto and F. Piazaa, “On the complex backpropagation algorithm,” IEEE Transactions on Signal Processing, Vol. 40, No. 4, pp. 967-969, April 1992.
[17]C. You and D. Hong, “Adaptive equalization using the complex backpropagation algorithm,” IEEE International Conference on Neural Networks, Vol. 4, pp. 2136-2141, June 1996.
[18]T. Kim and T. Adali, “Fully complex backpropagation for constant envelope signal processing,” Proceedings of the 2000 IEEE Signal Processing Society Workshop, Vol.1, pp. 231-240, 2000.
[19]T. Kim and T. Adali, “Complex backpropagation neural network using elementary transcendental activation functions,” 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing, Vol. 2, pp. 1281-1284, May 2001.
[20]T. Nitta, “An analysis on decision boundaries in the complex back-propagation network,” IEEE International Conference on Neural Networks, Vol. 2, pp. 934-939, June 27~July 2, 1994.
[21]T Nitta, “Ability of the complex backpropagation algorithm to learn similar transformation,” IEEE International Conference on Neural Networks, Vol. 3, pp. 1513-1516, November 27~December 1, 1995.
[22]A. Kanstila, T. Haverinen, M. Lehtokangas and J. Saarinen, “On equalization with complex MLP network in the GSM environment,” IFSA World Congress and 20th NAFIPS International Conference, Vol. 5, pp. 2687-2692, July 2001.
[23]T. L. Clarke, “Generalization of neural networks to the complex plane,” International Joint Conference on Neural Networks, pp. 435-440, June 1990.
[24]K. D. Rao, M. N. S. Swamy, and E. I. Plotkin, “Complex EKF neural network for adaptive equalization,” IEEE International Symposium on Circuits and Systems, Vol. 2, pp. 349-352, May 2000.
[25]K. D. Rao, “Narrowband direction finding using complex EKF trained multilayered neural Networks,” 3rd International Conference on Signal Processing, Vol. 2, pp. 1377-1380, October 1996.
[26]P. K. Dash, R. K. Jena, G. Panda and A. Routray, “An extended complex Kalman filter for frequency measurement of distorted signals,” IEEE Transactions on Instrumentation and Measurement, Vol. 49, No. 4, pp. 746-753, August 2000.
[27]P. K. Dash, G. Panda, A. K. Pradhan, A. Routray and B. Duttagupta, “An extended complex Kalman filter for frequency measurement of distorted signals,” IEEE Power Engineering Society Winter Meeting, Vol. 3, pp. 1569-1574, January 2000.
[28]K. Nishiyama, “A nonlinear filter for estimating a sinusoidal signal and its parameters in white noise: on the case of a single sinusoid,” IEEE Transactions on Signal Processing, Vol. 45, No.4, April 1997.
[29]D. E. Rumelhart and J. L. McClelland, “Learning internal representations by error propagation,” in Parallel Distributed Processing, Vol. I, Cambridge, MA: M.I.T. Press, 1986.
[30]F. M. Ham and I. Kostanic, “Principles of neurocomputing for science & engineering,” McGraw-Hill Higher Education, Inc. 2001.
[31]黃汗汶, “應用類神經網路於電力系統卸載策略之研究,” 中正大學碩士論文, 中華民國九十二年六月.