Journal of Computers, Vol 7, No 7 (2012), 1615-1622, Jul 2012
doi:10.4304/jcp.7.7.1615-1622

The Application of Support Vector Machine in Load Forecasting

Wenqing Zhao, Fei Wang, Dongxiao Niu

Abstract


The forecasting to mid-long term load is important because it can provide important evidence to the power planning. Traditional forecast techniques apply a single forecaster to carry out the task. However, this forecaster might not be the best for all situations or databases. A combinational model on the basis of Support Vector Machine (SVM) theory is proposed in this paper. During the process of the forecast, several single forecasting methods such as trend prediction model, exponent model, non-linear regression model, improved grey predictive model and improved grey verhulst predictive model, are used to form a model group, and then the fitted results by different traditional predictive models in time sequence act as the input of the support vector machine regression (SVMR) model, then by relative SVMR approach based on known input and output samples, we can obtain the test model. In the paper, the procedure of the combinational prediction on transformer faults based on SVMR is discussed in details. The example on load data has proven that the proposed model can give good results on both the fitting to the known data in time sequence and the extrapolation to the data to be predicted. Moreover, compared with other predictive approaches, both single model and other combinational model, the proposed combinational forecasting model has higher prediction accuracy.


Keywords


Support Vector Machine; Mid-long term load forecasting; Combinational forecasting

References


 

[1] LI Yumei. The utility combination forecasting method in mid-long term load forecasting [D]. Sichuan University, 2006. (In Chinese)

[2] Zeng M, Liu B H, Xu Z Y, et al. Short term load forecasting based on artificial neural network and fuzzy theory[J].Journal of Hunan University :Natural Sciences, 2008, 35(1):58-61.(In Chinese)

[3] Chen Rouyi, Zhang Yao, Wu Zhigang, et al. Application of improving fuzzy clustering algorithm to power load forecasting [J].Proceedings of the CSU EPSA, 2005,17(3):73- 77. (In Chinese)

[4] Zhong Bo, XIAO Z. A method of combination forecast based on rough set[J]. Statistic Research Journal, 2002(11):37 -39.(In Chinese)

[5] GU X H, XING M, NIU D X. Multifactor influenced combined grey neural network models for power load forecasting[J].East China Electric Power Journal, 2006, 34(7) : 548 - 551.(In Chinese)

[6] Zhao Haiqing. The Application to Power Load Forecasting of Optimization Combinatorial Predication Model[J].OPERATIONS RESEARCH AND MANAGEMENT SCIENCE,2005,14(1):115-118. (In Chinese)

[7] YANG S J, NIU D X. Model of forecasting power load based on optimized combination of model library[J].Journal of North China Electric Power University, 2005, 32 (1) :42 - 44.(In Chinese)

[8] Li Chunsheng, Wang Yaonan,Chen Guanghui. Combination Forecast Model Based on Mutual Information and Its Application to Power Load Prediction[J].Journal of Hunan University(Natural Sciences), 35(9):58-61.(In Chinese)

[9] BATES J M, GRANGER C W J. Combination of forecasts [J] .Operations Research Quarterly, 1969, 20 (4) :451 - 468.

[10] Zhai Yongjie, Wang Jingxian, Zhou Lihui. Power system mid-term load forecasting based on fuzzy support vector machines[J].Journal of North China Electric Power University,35(12):70-73. (In Chinese)

[11] Lu Zhigang, Zhou Ling, Yang Lijun, et al. Power load forecasting based on artificial immune algorithm weighted-SVM model[J]. Relay, 2005, 33(24):42-44. (In Chinese)

[12] Zhu Zhiyong, Lin Mugang, Zhang Shengji.Short-term load forecasting based on wavelet transform and support vector machine[J].Microcomputer Applications,2005, 26(4): 440-42. (In Chinese)

[13] Liu Mengliang, Liu Xiaohua, Gao Rong. Short Term Load Forecasting Using Wavelet Transform and SVM Based on Similar-Days[J]. Transactions Of China Electro technical Society,2006,21(11):59-64. (In Chinese)

[14] Vapnik V N, Statistical learning theory[M]. New York: Wiley, 1998.

[15] Hu Zhengping, Wu Yan, Zhang Ye. A novel fast support vector machine based on support vector geometry analysis[J]. Journal of Image and Graphics, 2007, 12(1):82-86.,(In Chinese).

[16] Jiao Licheng, Bo Liefeng, Wang Ling. Fast sparse approximation for least squares support vector machine. IEEE Transactions on Neural Networks, 2007, 18(3):685-690.
http://dx.doi.org/10.1109/TNN.2006.889500
PMid:17526336

[17] Doumpos Michael, Zopounidis Constantin, Golfinopoulou Vassiliki. Additive support vector machines for pattern classification. IEEE Transactions on Systems, Man, and Cybernetics—Part B: Cybernetics, 2007, 37(3):540-550.
http://dx.doi.org/10.1109/TSMCB.2006.887427

[18] ZHAO Wenqing, ZHU Yongli, ZHANG Xiaoqi. Combinational Forecast for Transformer Faults Based on Support Vector Machine[J]. Proceedings of the CSEE, 2008, 28(25):15-19. (In Chinese).

[19] Lin Maoliu, Chen Chunyu, A performance comparison of SVMs based onfourier kernel and RBF kernel [J], Journal of Chongqing University of Posts and Telecommunication, 2005, 17(6)”647-650(In Chinese).

[20] Tang Xiaowo. Research on error matrix of combination prediction [J]. Journal of University of Electronic Science and Technology of China, 1992, 21(4):448-454. (In Chinese)

[21] Ma Yongkai, Tang Xiaowo, Yang Guiyuan. A study on basic theory of the optimal combination prediction method of non-negative weights [J]. Operations research and management science, 1997, 6(2):1-8. (In Chinese)

[22] Chen Huayou, Hou Dingpi. Research on superior combination forecasting model based on forecasting effective measure[J]. Journal of University of Science and Technology of China, 2002, 32(2):172-180. (In Chinese)

[23] Wang Yingming. Research on the methods of combining forecasts based on correlativity. Forecasting, 2002, 21(2):58-62. (In Chinese)

[24] Wu Lizeng. Assessing approach of transformer condition[D]. Hebei: North China Electric Power University, 2005. (In Chinese)

[25] Niu Dongxiao, Cao Shuhua, et al. Power load forecasting technology and its application[M]. Beijing: China Electric Power Press, 2009. (In Chinese).

[26] Gu Jie. Study On The Varied Weight Synthesis Model of Mid-Long Term Load Forecasting In Power System Proceedings of the CSU-EPSA, 2003,15(16):58-59. (In Chinese)

[27] Zhou Quan,Ren Haijun, et al. Variable Weight Combination Method for Mid-long Term Power Load Forecasting Based on Hierarchical Structure. Proceedings of the CSEE, 2010,30(16):50-51. (In Chinese)


Full Text: PDF


Journal of Computers (JCP, ISSN 1796-203X)

Copyright @ 2006-2013 by ACADEMY PUBLISHER – All rights reserved.