精準的負載預測，能夠提供電力公司作系統之正確的規劃和安排，並降低整個運轉成本及提供穩定之電力給用戶端，使得電力設備能夠有效配置與充分利用。短期負載預測主要在提供預測未來一小時至一周之每小時負載需求，如果想要達到預測一小時甚至更短的時間，負載預測的運算時間將成為關鍵。在負載預測中，影響負載預測運算時間最大的因素為建模資料筆數。但是，以往經驗中建模資料筆數越多得到較佳的預測結果機會越大，而相對在建模時所需的時間會越長。因此應用資料探勘(Data Mining, DM)從資料庫中萃取較有意義的資料，以達到減少建模資料筆數縮短運算時間。本文以支撐向量機為主體結合粒子群演算法，由粒子群演算法找出支撐向量機中較佳設定的參數，本文稱此為改良型支撐向量機(Modified Support Vector Machines, MSVM)。支撐向量機具有非常快速與準確的特性，因此非常適合應用於短期負載預測。粒子群演算法是一種新的最佳化演算法，能精確且快速求取整個系統之真正較佳参數解，然後再以支撐向量機來實現預測負載。

The accuracy of load forecast has a significant impact for power companies on executing the plan of power development, reducing operating costs and providing reliable power to the client. Short-term load forecasting is to forecast load demand for the duration of one hour or less. This study presents a new approach to process load forecasting. A Support Vector Machine (SVM) was used for the initial load estimation. Particle Swarm Optimization (PSO) was then adopted to search for optimal parameters for the SVM. In doing the load forecast, training data is the most important factor to affect the calculation time. Using more data for model training should provide a better forecast results, but it needs more computing time and is less efficient. Applications of data mining can provide means to reduce the data requirement and the computing time. The proposed Modified Support Vector Machines approach can be proved to provide a more accurate load forecasting.

目 錄

中文摘要..............................................................................................................I
英文摘要.............................................................................................................II
目錄....................................................................................................................III
圖目錄...............................................................................................................VI
表目錄.............................................................................................................VIII

第一章 緒論
1-1 研究背景與動機..........................................................................................1
1-2 研究方法與步驟..........................................................................................2
1-3 論文架構及概要..........................................................................................3

第二章 資料探勘應用於短期負載預測問題研究
2-1 問題描述......................................................................................................5
2-2 資料探勘......................................................................................................5
2-2.1 資料探勘的功能.................................................................................6
2-2.2 資料探勘的方法.................................................................................7
2-3 資料探勘應用流程......................................................................................8
2-3.1 變數值域正規化.................................................................................9
2-3.2 資料排序及選取...............................................................................10
2-4 研究方法…................................................................................................10
2-4.1 相似天預測法描述...........................................................................11
2-4.2 相似時預測法描述...........................................................................14
2-4.3 負載預測流程圖...............................................................................17

第三章 粒子群演算法結合支撐向量機(改良型支撐向量機)
3-1 支撐向量機.................................................................................................19
3-1.1 分類與回歸.......................................................................................20
3-1.2 核心函數...........................................................................................26
3-2 粒子群演算法............................................................................................28
3-2.1 傳統粒子群演算法...........................................................................28
3-2.2 具時變性質加速係數粒子群演算法...............................................32
3-2.3 收斂型粒子群演算法.......................................................................34
3-2.4 範例測試與效果比較.......................................................................35

第四章 案例測試及結果分析
4-1 前言…........................................................................................................38
4-2 負載預測結果............................................................................................39
4-2.1 平常日負載預測結果…...................................................................40
4-2.2 假日負載預測結果….......................................................................41
4-2.3 一周負載預測結果….......................................................................42
4-3 資料探勘強建性分析................................................................................43
4-3.1 參考資料筆數分析….......................................................................43
4-3.2 相似筆數分析…...............................................................................45
4-3.3 資料庫筆數分析...............................................................................46
4-3.4尖峰負載預測分析............................................................................47
4-4 案例測試延伸探討....................................................................................49

第五章 結論及未來發展方向
5-1 結論............................................................................................................62
5-2 未來發展方向............................................................................................63

參考文獻............................................................................................................64

[1] I. Moghram and S. Ruhman, “Analysis and Evaluation Five of Load Forecasting Techniques,” IEEE Trans. on Power Systems, vol. 4, no. 4, pp. 1484–1491, 1889.
[2] M. T. Hagan and S. M. Behr, “The Time Series Approach to Short Term Load Forecasting,” IEEE Trans. on Power System, vol. PWRS-2, no. 3, pp. 832–837, 1987.
[3] S. Vemuri, W. L. Huang and D. L. Nelson, “On-Line Algorithms for Forecasting Hourly Loads of an Electrical Utility,” IEEE Trans. Power Apparatus and Systems, PAS-100, vol. 2, no. 8, pp. 3775–3784, Aug. 1981.
[4] H. Akagi, “New trends in active filter for power conditioning,” IEEE Trans. On Power Electronics, vol. 32, pp. 1312-1322, Jun. 1996.
[5] H. Yoo and R. L. Pimmel, “Short-term Load Forecasting Using a Self-Super Vised Adaptive Neural Network,” IEEE Trans. on Power Systems, vol. 14, no. 2, pp. 779-784, May 1999.
[6] J. Vermoak and E. C. Botha, “Recurrent Neural Networks for Short-Term Load Forecasting,” IEEE Trans. on Power Systems, vol. 13, no. 1, pp. 126-132, Feb. 1998.
[7] J. W. Taylor and R. Buizza, “Neural Network Load Forecasting with Weather Ensemble Predictions,” IEEE Trans. On Power Systems, vol. 17, no. 3, pp. 626-632, Aug. 2002.
[8] S. Osowskki and K. Siwek, “Regularisation of Neural Networks for Improved Load Forecasting in the Power System,” IEE Proc.-Gener. Trans. Distrib. , vol. 149, no. 3, pp. 340-344, May 2002.
[9] N. B. Karayiannis, M. Balasurbramanian and H. A. Malki, “Evaluation of Cosine Basis Function Neural Networks on Electric Power Load Forecasting,” Neural Networks, 2003 Proceedings of the International Joint Conference on, vol. 3, pp. 2100-2105, Jul. 20-24, 2003.
[10] L. M. Saini and M. K. Soni, “Artificial Neural Network Based Peak Load Forecasting Using Levenberg-Marquardt and quasi-Newton Methods,” Generation, Trans. And Distri. , IEE Proceedings , vol. 149, Issue 5, pp. 578-584, Sep. 2002.
[11] U. Fayyad, Gregory, Piatetsky-Shapiro and P. Smyth, “The KDD Process for Extracting Useful Knowledge from Volumes of Data,” Communications of the ACM, vol. 39, no. 11, pp. 27-34. Nov. 1996
[12] UniMiner探宇科技股份有限公司：http://www.uniminer.com/center01.htm，2010年6月。
[13] C. Cortes, and V. Vapnik, “Support vector networks,” Machine Learning, 20, pp. 273-297. 1995.
[14] N. Cristianini and J. Shawe-Taylor, An Introduction to Support Vector Machines and Other Kernel-Based Learning Methods. Cambridge, U.K.: Cambridge Univ. Press, 2000.
[15] B. Schölkopf and A. J. Smola, Learning with Kernel. Cambridge, MA: MIT Press, 2001.
[16] B. Schölkopf, A. J. Smola, R. Willianson and P. Bartlett, “New support vector algorithms,” Neural Comput. , vol. 12, no. 5, pp. 207–1245, 2000.
[17] C. J. C. Burges, “A tutorial on support vector machines for pattern recognition,” Data Mining Knowl. Disc. , vol. 2, no. 2, pp. 121–168, 1998.
[18] W. M. Lin, C. H. Wu, C. H. Lin and F. S. Cheng, “Classification of Multiple Power Quality Disturbances Using Support Vector Machine and One-versus-One Approach,” IEEE International Conference on Power System Technology, Chongqing, China, Oct. 2006.
[19] C. W. Hsu and C. J. Lin, “A comparison of methods for multi-class support vector machines,” IEEE Trans. Neural Network, vol. 13, no2, pp. 415–425, Mar. 2002.
[20] 吳建賢， “軟計算於電力品質偵測與電機故障診斷之應用(Applications of Soft Computing for Power-Quality Detection and Electric Machinery Fault Diagnosis)” ，國立中山大學電機工程研究所博士論文，2008年10月。
[21] 林義隆， “基於支撐向量機之細胞神經網路韌性模板設計及Wilcoxon學習機之初步研究(SVM-based Robust Template Design of Cellular Neural Networks and Primary Study of Wilcoxon Learning Machines)” ，國立中山大學電機工程研究所博士論文，2006年12月29日。
[22] B. J. Kruif and T. J. A. Vries, “Pruning Error Minimization in Least Squares Support Vector Machines,” IEEE Trans. On Neural Networks, vol. 14, no. 3, pp. 696-702, May 2003.
[23] T. V. Gestel, Johan A. K. Suykens, Dirk-Emma Baestaens, nnemie Lambrechts, Gert Lanckriet, Bruno Vandaele, Bart De Moor and Joos Vandewalle, “Financial Time Series Prediction Using Least Squares Support Vector Machines Within the Evidence Framework,” IEEE Trans. On Neural Networks, vol. 12, no. 4, pp. 809-821, Jul. 2001.
[24] V. Kecman, Learning and Soft Computing. Cambridge, MA: MIT Press, pp. 11-298, 2001.
[25] H. W. Kuhn and A. W. Tucker, “Nonlinear programming,” Proceedings of 2nd Berkeley Symposium: 481-492, Berkeley: University of California Press, 1951.
[26] M. A. Aizerman, E. M. Braverman and L. I. Rozonoer, “Theoretical Foundations of the Potential Function Method in Pattern Recognition Learning,” Autom. Remote Control, vol. 25, 1964.
[27] J. Kennedy and R. Eberhart, “Particle swarm optimization,” IEEE International Conference Neural Networks, 1995. Proceedings, vol. 4, pp. 1942–1948, 27 Nov.-1 Dec. 1995.
[28] Y. Shi and R. Eberhart, “Empirical study of particle swarm optimization,” Proc. IEEE Evol. Comput. , vol. 3, pp. 69-73, 1999.
[29] F. S. Cheng, J. S. Tu, C. H. Lv and M. T. Tsay, “A Generalized Regression Neural Network for Solving Economic Dispatch Problem,” ICEE for the 21st Century With focus on Sustainability and Reliability, pp. 113, Jul. 2007.
[30] A. Ratnaweera, S. K. Halgamuge and H. C. Watson, “Self-organizing hierarchical particle swarm optimizer with time-varying acceleration coefficients,” IEEE Trans. on Evolutionary Computatio, vol. 8, no. 3, pp. 240-255, Jun. 2004.
[31] K. T. Chaturvedi, M. Pandit and L. Srivastava, “Self-Organizing Hierarchical 102 Particle Swarm Optimization for Nonconvex Economic Dispatch,” IEEE Trans. on Power System, Vol. 23, Issue 3, pp. 1079-1087, Aug. 2008.
[32] M. Clerc and J. Kennedy, “The particle swarm-Explosion, stability, and convergence in a multidimensional complex space,” IEEE Trans. on Evolutionary Computation, vol. 6, no. 1, pp. 58–73, Feb. 2002.