臺灣博碩士論文加值系統

智慧電網及智慧型電表建置在全球快速發展，在台灣已有特定地區裝設智慧型電網，透過智慧型電表蒐集用戶電表量測資料。消費者的用電習慣各有不同，而影響消費者的用電習慣有許多因素，本研究將會針對溫度、樓層等因素作用電量分析，使消費者不但可以瞭解自身的用電習慣，並加以調整，以減少電費支出，還可節省電能消耗。除了電量分析外，預測用電量也可幫助電力業者適時調整發電量，改善浪費電力能源之現象。本研究使用三種用電預測方法，分別為回看法(ε-LookBack-N)、差分整合自回歸移動平均模型(Autoregressive Integrated Moving Average Model)和支持向量回歸(Support Vector Regression)，我們將評估其適用性與準確度，並透過用電戶的用電特徵分群，進一步結合環境變因，研究用電戶用電度數的預測模型，並利用既有量測資料進行驗證。其預測模型可以幫助電力業者作用電預測，適時調整發電量，有效率的配送電能，以達到節能省碳之目的。

誌謝. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . i
摘要. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ii
第一章緒論. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1
第二章電表資料描述. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3
第三章多樣性分析. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5
第一節用電量基本分析. . . . . . . . . . . . . . . . . . . . . . . . . 6
第二節依樓層分析用電量. . . . . . . . . . . . . . . . . . . . . . . 8
第三節依溫度分析用電量. . . . . . . . . . . . . . . . . . . . . . . 11
第四節依溫度與樓層分析用電量. . . . . . . . . . . . . . . . . . 13
第五節依假日分析用電量. . . . . . . . . . . . . . . . . . . . . . . 15
第四章用電戶分群. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16
第一節分群演算法. . . . . . . . . . . . . . . . . . . . . . . . . . . . 16
第二節分群效度指標. . . . . . . . . . . . . . . . . . . . . . . . . . 20
第三節文化基因演算法. . . . . . . . . . . . . . . . . . . . . . . . . 23
第五章用電戶用電預測方法. . . . . . . . . . . . . . . . . . . . . . . . . . 26
第一節ε-LookBack-N . . . . . . . . . . . . . . . . . . . . . . . . . . 26
第二節ARIMA. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 28
第三節SVR . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 31
第六章預測結果. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 33
第七章相關文獻. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 39
第八章結論與未來展望. . . . . . . . . . . . . . . . . . . . . . . . . . . . . 42
參考文獻 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 44
附錄A 多樣性分析. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 48
附錄B SVR . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 60

[1] R. http://www.r-project.org/.
[2] Taiwan Power Company. http://www.taipower.com.tw/.
[3] E. Castillo, B. Guijarro, and A. Alonso. Electricity load forecast using functional
networks. In Electricity Load Forcast Using Intelligent Technologies,
page 75–84. EUNITE: The European Network on Intelligent Technologies for
Smart Adaptive Systems, 2002.
[4] C.-C. Chang and C.-J. Lin. Libsvm: A library for support vector machines.
ACM Trans. Intell. Syst. Technol., 2(3):27:1–27:27, May 2011.
[5] R.-S. Chang, C.-Y. Kuo, and Y.-H. Ho. A survival analysis based approach for
mdms missing data treatment. In Wireless and Sensor Networks Conference,
number 61, August 2012.
[6] B.-J. Chen, M.-W. Chang, and C.-J. Lin. Load forecasting using support
vector machines: a study on eunite competition 2001. Power Systems, IEEE
Transactions on, 19(4):1821–1830, 2004.
[7] D. L. Davies and D. W. Bouldin. A cluster separation measure. Pattern
Analysis and Machine Intelligence, IEEE Transactions on, PAMI-1(2):224–
227, 1979.
[8] J. C. Dunn. Well-separated clusters and optimal fuzzy partitions. Journal of
Cybernetics, 4(1):95–104, 1974.
[9] D. Esp. Adaptive logic networks for east slovakian electrical load forecasting.
In Electricity Load Forcast Using Intelligent Technologies, page 55–74. EUNITE:
The European Network on Intelligent Technologies for Smart Adaptive
Systems, 2002.
[10] A. Jain and B. Satish. Clustering based short term load forecasting using
support vector machines. In PowerTech IEEE Bucharest, page 1–8, 2009.
[11] W. Karush. Minima of functions of several variables with inequalities as side
constraints. Master’s thesis, Dept. of Mathematics, Univ. of Chicago, 1939.
[12] L. Kaufman and P. J. Rousseeuw. Finding Groups in Data: An Introduction
to Cluster Analysis (Wiley Series in Probability and Statistics). Wiley-
Interscience, 1st. edition, March 2005.
[13] W. Kowalczyk. Averaging and data enrichment: Two approaches to electricity
load forecasting. In Electricity Load Forcast Using Intelligent Technologies,
page 209–218. EUNITE: The European Network on Intelligent Technologies
for Smart Adaptive Systems, 2002.
[14] H. W. Kuhn and A. W. Tucker. Nonlinear programming. In Second Berkeley
Symposium on Mathematical Statistics and Probability, page 481–492, 1951.
[15] A. Lewandowski, F. Sandner, and P. Protzel. Prediction of electricity load
by modeling the temperature dependencies. In Electricity Load Forcast Using
Intelligent Technologies, page 107–114. EUNITE: The European Network on
Intelligent Technologies for Smart Adaptive Systems, 2002.
[16] T. W. Liao. Clustering of time series data—a survey. Pattern Recognition,
38(11):1857 – 1874, 2005.
[17] A. Lotfi. Application of learning fuzzy inference systems in electricity load
forecast. In Electricity Load Forcast Using Intelligent Technologies, page 123–
130. EUNITE: The European Network on Intelligent Technologies for Smart
Adaptive Systems, 2002.
[18] J. B. MacQueen. Some methods for classification and analysis of multivariate
observations. In Proc. of the fifth Berkeley Symposium on Mathematical
Statistics and Probability, volume 1, page 281–297. University of California
Press, 1967.
[19] R. De Maesschalck, D. Jouan-Rimbaud, and D.L. Massart. The mahalanobis
distance. Chemometrics and Intelligent Laboratory Systems, 50(1):1 – 18,
2000.
[20] J. Mercer. Functions of positive and negative type and their connection with
the theory of integral equations. Philos. Trans. Royal Soc. (A), 83(559):69–
70, November 1909.
[21] M. K. Pakhira, S. Bandyopadhyay, and U. Maulik. Validity index for crisp
and fuzzy clusters. Pattern Recognition, 37(3):487 – 501, 2004.
[22] E. Pelikán. Middle-term electrical load forecasting by time series decomposition.
In Electricity Load Forcast Using Intelligent Technologies, page 167–
176. EUNITE: The European Network on Intelligent Technologies for Smart
Adaptive Systems, 2002.
[23] A. P. Reynolds, G. Richards, and V. J. Rayward-Smith. The application of
k-medoids and pam to the clustering of rules. In Intelligent Data Engineering
and Automated Learning – IDEAL 2004, volume 3177 of Lecture Notes in
Computer Science, page 173–178. Springer Berlin Heidelberg, 2004.
[24] W. Shen, V. Babushkin, Z. Aung, and W. L. Woon. An ensemble model for
day-ahead electricity demand time series forecasting. In Proceedings of the
fourth international conference on Future energy systems, page 51–62, 2013.
[25] A. J. Smola and B. Schölkopf. A tutorial on support vector regression. Statistics
and Computing, 14(3):199–222, 2004.
[26] V. N. Vapnik. Statistical learning theory. Wiley, 1st. edition, September 1998.
[27] R. Xu and D. Wunsch. Survey of clustering algorithms. Neural Networks,
IEEE Transactions on, 16(3):645–678, 2005.