臺灣博碩士論文加值系統

應用類神經網路於電力系統負載之溫度敏感度分析
陳智宏*陳朝順**
國立中山大學電機工程學系
摘　要
用戶負載特性的探討乃是電力系統運作最基本的一環，透過負載特性研究，可以有效掌握各類型用戶之用電特性，提高負載預測之準確性及更有效的支援系統規劃，以降低電力系統容量不足之壓力。
本論文以負載特性調查研究為基礎，以統計學分層隨機抽樣法，於全省12個抽樣區處選擇1315戶各類型具代表性之用戶，以統計分析推導各類型用戶標準化日負載模式，配合台電用戶資訊系統(CIS)之售電資料，推估區處各類型用戶日負載組成。整合全省12個抽樣區處各類型用戶之標準化日負載模式及台電系統各類型用戶售電資料，推估台電系統各類型用戶日負載組成。同時應用類神經網路訓練之方法，學習各類型用戶耗電量與溫度及溼度之關係，探討北市區處、鳳山區處及台電系統之溫度敏感度。藉由溫度敏感度分析可知冷氣空調佔比較高的類型用戶，其耗電量會隨著溫度變化而有明顯變動，因此商業化較高的北市區處之溫度敏感度，遠較工業化高的鳳山區處之溫度敏感度為高。對台電系統而言，透過用戶負載的溫度敏感度分析，能夠了解負載變動的範圍，並提供各區處供電及未來容量規劃之參考。
*作者**指導教授

The Temperature Sensitivity Analysis of Power System Load Demand with Neural Networks
Chih-Hung Chen*Chao-Shun Chen**
Institute of Electrical Engineering
National Sun Yat-Sen University
Kaohsiung, Taiwan, R.O.C.
ABSTRACT
The analysis of customer load characteristic plays the fundamental role of power system operation. Based on the load survey study, the load pattern of each customer class is derived to achieve more effective load forecast for system planning to reduce the risk of system capacity shortage.
For the load survey study, a stratified sampling method has been used to select the proper size of customers for meter installation to collect the customer power consumption. By the way, the customer load patterns derived can represent the load behavior of whole customer population. The standardized daily load pattern of each customer class has been solved with the mean per-unit method of customer load. According to the total power consumption by all customers within the same class and considering the corresponding daily load pattern, the daily load profile of the customer class is then determined. The standard daily load pattern of each customer class and total power consumption within the territory of service districts of Taipower system are integrated to construct Taipower system daily load profile. The temperature sensitivity analysis of customer power consumption is performed for each customer class by applying neural networks. The proposed method has been used to investigate the change of power consumption due to temperature rise for each district and Taipower system. For the districts with high ratio of the air conditioner loading, the increase of power consumption is in proportion to the temperature. It is concluded that the research of temperature sensitivity on power consumption can support power system operation and better capacity planning of power system in the future.
*Author**Advisor

目　錄
摘要i
Abstractiii
目錄v
圖目錄viii
表目錄x
第一章緒論1
1-1研究背景及目的1
1-2研究步驟5
1-3各章節概要8
第二章負載特性調查9
2-1前言9
2-2統計抽樣調查10
2-2-1主軸分析11
2-2-2群集分析15
2-3台電系統分層隨機抽樣20
2-4電表異常耗電資料處理24
第三章負載模式與組成推估29
3-1前言29
3-2日負載模式推估29
3-3區處日負載組成推估36
3-4台電系統日負載組成推估42
第四章類神經網路介紹48
4-1前言48
4-2類神經網路之發展48
4-3神經元之數學模式49
4-4網路架構55
4-5類神經網路學習法則57
4-5-1倒傳遞式演算法57
4-5-2 Levenberg-Marquardt 演算法60
4-6適時停止63
4-7合議機制66
第五章負載溫度敏感度分析68
5-1前言68
5-2應用類神經網路於溫度敏感度分析68
5-3各類型用戶溫度敏感度分析71
5-4區處溫度敏感度分析75
5-5台電系統溫度敏感度分析83
第六章結論與未來研究方向87
6-1前言87
6-2未來研究方向88

[1]Load Research Manual, Association of Edison Illuminating Companies, February 1990
[2]八十九年負載管理年報，台灣電力公司，2001年4月
[3]Chen, C. S.; Hwang, J. C. and Huang, C. W. “Determination of customer load characteristics by load survey system at Taipower,” IEEE Trans. on Power Delivery, Vol. 11, No. 3, July 1996, pp. 1430-1435.
[4]Chen, C. S.; Kang, M. S., Hwang, J. C.; Huang, C. W. “Synthesis of power system load profiles by class load study”, Electrical Power & Energy Systems, Vol. 22, No. 5, June 2000, pp. 325-330.
[5]Chen, C. S.; Kang, M. S., Hwang, J. C.; Huang, C. W. “Implementation of the load survey system in Taipower”, Proceedings of 1999 IEEE/PES T & D Conference, April 11-17, 1999.
[6]八十九年負載管理年報，台灣電力公司，2001年4月
[7]趙坤芳，「SAS基本資料處理與操作」，全華圖書，1998年7月
[8]SIEMENS, S4 Solid State Meter User’s Guide, Lafayette, USA.
[9]Hansen, M. H. ; Hurwifz, W. H. and Madow, W. G. Sample survey methods and theory, John Wiley & Sons, 1953.
[10]張健邦，應用多變量分析，文富出版社，1993年2月
[11]陳順宇，多變量分析，華泰書局，1998年7月
[12]儲全滋，抽樣方法，三民書局，1991年8月
[13]林惠玲、陳正倉等，統計學，雙葉書局，1999年1月
[14]Hagan, M.T., Demuth, H.B. and Beale, Neural Network Design, 1996
[15]Haykin, S., Neural Networks: A Comprehensive Foundation, 1998
[16]葉怡成，「類神經網路模式應用與實作」，儒林圖書，1993年
[17]Min Su; Basu, M. “Gating improves neural network performance”, International Joint Conference on Neural Networks, 2001, pp. 2159 —2164
[18]Jyh-Shing Roger Jang; Mizutani, E. “Levenberg-Marquardt method for ANFIS learning”, Fuzzy Information Processing Society, NAFIPS, Biennial Conference of the North American , 1996 , pp. 87 —91
[19]Winter, R.; Widrow, B. “MADALINE RULE II: a training algorithm for neural networks”, IEEE International Conference on Neural Networks, 1988, pp. 401 —408
[20]Hagan, M.T.; Menhaj, M.B. “Training feedforward networks with the Marquardt algorithm”, IEEE Transactions on Neural Networks, 1994, pp. 989 —993
[21]Hosseini, S.; Jutten, C. “Maximum likelihood neural approximation in presence of additive colored noise”, IEEE Transactions on Neural Networks, 2002, pp. 117 —131
[22]Hippert, H.S.; Pedreira, C.E.; Souza, R.C. “Neural networks for short-term load forecasting: a review and evaluation”, IEEE Transactions on Power Systems, 2001, pp. 44 —55
[23]Lawrence, S.; Giles, C.L. “Overfitting and neural networks: conjugate gradient and backpropagation”, Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks, 2000, pp. 114 —119
[24]康渼松，「台電負載特性之研究及其對電力系統運轉之影響」，國立中山大學電機工程研究所博士論文，2001年
[25]「台電系統負載特性調查分析研究」，第三期計劃期末報告，台灣電力公司，2002年
[26]Donald W. Marquardt. “An algorithm for least squares estimation of nonlinear parameters”, Journal of the Society of Industrial and Applied Mathematics, 1963, pp. 431 —441