Title

混合平行基因演算法與支持向量機作短期負載預測

Translated Titles

Hybrid Parallel Genetic Algorithm and Support Vector Machines for Short Term Load Forecasting

DOI

10.6841/NTUT.2014.00148

Authors

姜大駿

Key Words

基因演算法 ; 支持向量機 ; 平行化技術 ; 負載預測 ; Genetic Algorithm ; Support Vector Machine ; Parallel Technology ; Load Forecasting

PublicationName

臺北科技大學電機工程系研究所學位論文

Volume or Term/Year and Month of Publication

2014年

Academic Degree Category

碩士

Advisor

曹大鵬

Content Language

繁體中文

Chinese Abstract

精確的負載預測不僅可以適當的做為發電機排程規劃及調度之參考依據,也能降低機組運轉時的成本及改進供電品質可靠度,最重要的是能避免限電危機或是電力資源浪費。 本論文以平行基因演算法(Genetic Algorithm, GA)結合支持向量機(Support Vector Machines, SVM)中的最小平方支持向量機(Least Squares Support Vector Machines, LSSVM)來求解電力負載預測之問題,本論文乃以最小平方支持向量機為主體,接著使用平行基因演算法來求得最小平方支持向量建立負載預測之模型的各項最佳參數值,且加以改進傳統用於求解建立負載預測模型之最佳參數值方法。 在求解過程中,基因演算法是架構簡單且結果準確率較高的最佳化演算法,因為其編碼方式是採用格雷碼編碼使建立負載預測之模型參數能更加精確,接著經由複製、交配、突變則可以有效提高整體最佳解的搜索能力,而其演算法的缺點為資料龐大時運算時間較久,因此,本研究以基因演算法為基礎,結合平行處裡技術來輔助基因演算法處裡資料龐大而運算時間過長之問題。 最後,本論文依據各項數據資料(電力負載、氣象)為基準,作為實際之負載預測,且將本論文結果與量子基因演算法結合倒傳遞類神經網路(Quantum Genetic Algorithm and Artificial Neural Network,QGA-BPNN)做比較,本方法不僅求得小的負載預測誤差值,且在大部分預測中,因為使用平行處裡技術,使得運算時間也較少,因此,本論文提出較優質的可行方法。

English Abstract

The accurate load forecasting can not only be properly considered as the reference of unit commitment and arranging for generation but also lower the operational cost and improve the reliability of supply quality. The most important is that it can avoid the crisis of limit-electricity and the waste of power resource. In this thesis, the Genetic algorithm (GA)is combined with the Least squares support vector mechine(LSSVM)of Support vector mechine(SVM)to solve the problem of power load forecasting. With the main foundation of LSSVM, parallel GA is adopted to obtain the necessary parameters in the model built by LSSVM for load forecasting,which modifies the original optimized parameters contributed by the conventional model (i.e.LSSVM,BPNN)for predicting load. During the period of solving, the GA is an optimized algorithm with simple structures and precise results. Thanks to the Grey code introducing, the accuracy of parameters can be promised in the model for load forecasting. Then, through the duplicatation, matching and mutation, the searching ability can be significantly improved in the whole area for optimized solution. However, the disadvantage of this algorithm is that the long calculation time due to the large amount of data. Therefore, the technique of parallel processing is joined to assist the GA for dealing with a great number of data and long calculation time while the GA is taken as the basis in this research. In the end, several data, including power load and weather parameters utilized in a proposed model, has been viewed as criteria. Compared with QGA-BPNN, the method proposed in this thesis illustrates less prediction error and calculation time than the traditionl existing techniques in most estimation because of parallel process. To sum up, this research indicates a practical and competitive method for predicting load.

Topic Category 電資學院 > 電機工程系研究所
工程學 > 電機工程
Reference
  1. [6] 邱士齊,混和量子基因演算法與類神經網路作短期負載預測,碩士論文,台北科技大學,臺北,2012
    連結:
  2. [7] I. Moghram and S. Rahman, “Analysis and Evaluation of Five Short-term Load ForecastingTechniques,” IEEE Transactions on Power Systems, Vol.4, No.4, October 1989, pp.1484-1491.
    連結:
  3. [8] M. T. Hagan and S. M. Behr, “The Time Series Approach to ShortTerm Load Forecasting,”IEEE Transactions on Power Systems, Vol.PWRS-2, No3, August 1987, pp. 785-791
    連結:
  4. [10] A. D. Papalexopulos and T. C. Hesterberg, “A Regression-Based Approach to Short-term System Load Forecasting,”IEEE Transactions on Power Systems, Vol. 5, No. 4, November 1990, pp. 1535-1547.
    連結:
  5. [11] T. Haida and S. Muto, “Regression Based Peak Load ForecastingUsing a Transformation Technique,”IEEE Transactions on PowerSystems, Vol. 9, No. 4, November 1994, pp. 1788-1794.
    連結:
  6. [12] G.T. Heinemann, D.A. Nordman, and E. C. Plant, “The Relationship BetweenSummer Weather and Summer Loads, ARegression Analysis,”IEEE Transactions on Power Apparatus and Systems, Vol. PAS-85, No.11,November 1996, pp.1144-1154.
    連結:
  7. [14] H. T. Yang, T. C. Liang, K. R. Shih and C. L. Huang, “Power System Yearly Peak Load Forecasting: A Grey System Modeling Approach,”IEEE Proc. Energy Management and Power Delivery, Vol. 1, 1995, pp. 261-266.
    連結:
  8. [15] S. H. Fan, T. Y. Xiao and C. Guo,“A Model of the Expanded Grey Theory,”2004 IEEE International Conference on Networking, Vol. 1, March 2004, pp. 339-342.
    連結:
  9. [16] S. J. Kiartzis, A. G. Bakirtzis, J. B. Theocharis and Gr. Tsagas, “A Fuzzy Expert System for Peak Load Forecasting. Applicaton to the Greek Power System,”IEEE Proc. MEleCon 2000, Vol. 3, 2000, pp. 1097-1100.
    連結:
  10. [17] H. Mori, Y. Sone, D. Moridera and T. Kondo, “Fuzzy Inference Models for Short-term Load Forecasting with Tabu Search,”IEEE Proc. Systems, Man, and Cybernetics, Vol. 6, 1999, pp. 551-556.
    連結:
  11. [19] S. Rahman and O. Hazim, “A Generalized Knowledge-Based Short-term Load-Forecasting Technique,”IEEE Transactions on Power Systems, Vol. 8, No. 2, May 1993, pp. 508-514.
    連結:
  12. [20] A.Khotanzad,A.R.Reza andT.L.Lu,“ANNSTLF-A Neural-Network-BasedElectric Load Forecasting System,”IEEE Transactions on Neural Networks, Vol. 8, No.4, July 1997, pp. 835-846.
    連結:
  13. [21] R. C. Hwang, H. C. Huang and J. G. Hsieh, “Short-term Power Load Forecasting byNeural Network with Stochastic Back-Propagation Learning Algorithm,” IEEE PowerEngineering Society Winter Meeting,Vol. 3, Jan. 2000, pp. 1790-1795.
    連結:
  14. [22] C. Y. Tee, J. B. Cardell and G. W. Ellis, “Short-term Load Forecasting Using Artificial Neural Networks,”IEEE North American Power Symposium, Oct. 2009, pp. 1-6.
    連結:
  15. [23] W. Charytoniuk and M. S. Chen, “Very Short-term Load Forecasting Using Artificial Neural Networks,”IEEE Transactions on Power Systems, Vol. 15, Feb. 2000, pp. 263-268.
    連結:
  16. [27] Z. L. Gaing and T. C. Ou, “Dynamic Economic Dispatch Solution Using Fast Evolutionary Programming with Swarm Direction,” in Proc. 4th IEEE Conference on Industrial Electronics and Applications, Xi'an, China, May 2009, pp. 1538-1544.
    連結:
  17. [29] 林大仁,運用支撐向量迴歸與倒傳遞類神經網路建構產品造型設計之預測模型,碩士論文,國立成功大學,台南市,2007
    連結:
  18. [30] Johan Suykens ,”Least Squares Support VectorMachines”,Leuven,July 2002
    連結:
  19. [31] J. H. Holland, Adaptation in Natural and Artificial System, Cambridge: the MIT Press, 1992.
    連結:
  20. [33] 劉律伸,應用量子基因演算法求解最佳化短期火力機組排程,碩士論文,國立台北科技大學,臺北,2012。
    連結:
  21. [35] 羅一峰,應用累積元與基因演算法求解配電系統無效電力控制,碩士論文,中原大學,中壢市,2007。
    連結:
  22. [37] 張淯詠,應用二進制粒子群演算法求解最佳化短期火力機組排程,碩士論文,國立臺北科技大學,臺北,2013。
    連結:
  23. [1] 經濟部能源局,http://web3.moeaboe.gov.tw/ECW/populace/home/Home.aspx。
  24. [2] 台灣電力公司,http://www.taipower.com.tw/。
  25. [3] 邴喆,刁友鋒,電力系統短期負荷預測方法綜述,科技資訊,33期,2007
  26. [4] 李卜娟,基於LS-SVM的電力系統短期負荷預測研究,碩士論文,南京理工大學,南京市,2009
  27. [5] 張云云,基於智能優化SVM的短期負載預測及誤差修正模型研究,碩士論文,華北電力大學,北京市,2009
  28. [9] 王嘉鈺,全電力推進船舶短期電力負荷預測研究,碩士論文,哈爾濱工業大學,哈爾濱市,2010
  29. [13] 范興奎,灰色系統理論,青島理工大學,理學院,2012
  30. [18] 林志鈞,應用專家系統及灰關聯分析於葡萄酒之選購及品評,博士論文,大葉大學,彰化縣,2012
  31. [24] G. C. Liao, “An Improved Fuzzy Neural Networks Approach for Short-term Electrical Load Forecasting,”2011 8th Asian Control Conference, Kaohsiung, Taiwan, May 2011, pp. 596-601.
  32. [25] 李家居,混和量子基因演算法於小波神經網路法解短期負載預測,第三十屆電力工程研討會,龍華科技大學電機工程系,2009,181頁
  33. [26] http://baike.baidu.com/view/620928.htm
  34. [28] V. N. Vapnik, “The nature of statistical learning theory”, Springer, New York, USA, 1995.
  35. [32] 蘇木春、張孝德編,類神經網路、模糊系統以及基因演算法則,臺北,全華科技圖書,2004。
  36. [34] K. F. Man, K.S. Tang, and S. Kwong, Genetic Algorithms: Conceptsand Designs. London, U.K.: Springer-Verlag, 1999.
  37. [36] Kennedy , James and Eberhart , Russell “Neural Networks:Particle Swarm Optimization,” in Proceedings of IEEE International Conference, Vol.27, 1995, pp.1942-1948.
  38. [38] 嚴浩哲,平行遺傳演算法以電腦叢集為工具應用於地下水優選問題之探討,碩士論文,國立中興大學,台中,2002。
  39. [39] 謝景惠,非監督式模糊類神經網路推理模式於個人電腦叢集之平行計算,碩士論文,國立交通大學,新竹,2002。
  40. [40] 曾耀寰,「企鵝雄兵:以Linux進行電腦叢集計算」,台北,和碩科技文化有限公司,2002。
  41. [41] Grefenstette, J. J.,1981. Parallel adaptive algorithms for function optimization. Technical Report CS-81-19, Computer Science Department, Vanderbilt University, Nashville, TN.
  42. [42] James, P., Cohoon, Shailesh., U. Hegde, Worthy., Martin, N., and Dana, S., 1987. Punctuated Equilibria: A Parallel Genetic Alogrithm,11:148-154. Richards
  43. [43] 中央氣象局,http://www.cwb.gov.tw/V7/index.htm