Study of Sequential Minimal Optimization Algorithm Type and Kernel Function Selection for Short-Term Load Forecasting

Abstract:

Short-term load forecasting is important for power system operation,including preparing plans for generation and supply, arranging the generator to set start or stop, coordinating thermal power units and hydropower units. Support vector machines have advantage in approximating any nonlinear function with arbitrary precision and modeling by studying history data. Based on SVM, this paper selects the sequential minimal optimization (SMO) algorithm to compute load forecasting, because SMO can avoid iterative, so as to short the running time. If we select different kernel functions and the SMO type in the computing process, we will receive different result. Though the analysis of results,the paper obtains the optimal solution in different accuracy or time requirements for short-term load forecasting. By a power plant data, respectively, it discusses from the weekly load forecasts and daily load forecast to play an empirical analysis. It concludes that the selection of ɛ-SVR type and the linear form kernel function is ideal for short-term load forecasting in a not strictly time limits. Otherwise, it will select others in different terms.

• Periodical: Applied Mechanics and Materials (Volume 329)
• Pages: 472-477
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.329.472
• Online since: June 2013
• Authors: Zhe Zhao, Xiao Yu Li
• Keywords: Kernel Function, Load Forecasting, Sequential Minimal Optimization, Support Vector Regression (SVR)

References

[1] Zhai Yongjie, Wang Zijie, Huang Baohai, Li Haili, "Research and Application of SMO Algorithm Based on PSO Optimization", Journal of North China Electric Power University, vol. 35, no. 1, pp.57-61, 2008.

[2] Xie Chunxin, "A Simple Deduction for SMO Algorithm of Support Vector Machines", Journal of Computer Knowledge and Technology, vol. 5, no. 17, pp.4522-4524, 2009.

[3] IvorW. Tsang, James T. Kwok, Pak-Ming Cheung, "Core Vector Machines: Fast SVM Training on Very Large Data Sets", Journal of Machine Learning Research, vol.12, no. 4, p.363–392, 2005.

[4] Luca Zanni, Thomas Serafini, Gaetano Zanghirati, Parallel Software for Training Large Scale Support Vector Machines on Multiprocessor Systems, Journal of Machine Learning Research, vol.10, no.5, p.1467–1492, 2006.

[5] Hans Peter Graf, Eric Cosatto, L´eon Bottou, Igor Dourdanovic, Vladimir N. Vapnik, "Parallel support vector machines: the Cascade SVM", Journal of Advances in Neural Information Processing Systems, vol.10, no.7, p.291–314, 2005.

[6] Feng KONG, Guo ping SONG. "Middle Long Power Load Forecasting Based on Dynamic Grey Prediction and Support Vector Machine", IJACT: International Journal of Advancements in Computing Technology, vol. 4, no. 5, p.148 ~ 156, 2012.

DOI: 10.4156/ijact.vol4.issue5.18