Research on Comparison and Application of SVM and FNN Algorithm

Author

Yang, Shaomei ; Zhu, Qian

Author_Institution

Econ. & Manage. Dept., North China Electr. Power Univ., Baoding

fYear

2008

fDate

12-14 Oct. 2008

Firstpage

1

Lastpage

4

Abstract

SVM and FNN are the improved algorithms of neural network, which are more popular at present. In this paper, based on the simple introduction of the two algorithms, discuss the basic principle and the learning process respectively; two cities´ short-term power load forecasting in Hebei Province as examples, case 1 delegates large sample, case 2 delegates small sample, use SVM and FNN to forecast the average failure rate, through the comparison and analysis, get a conclusion that SVM is applicable to the fewer data situation, and FNN is applicable to the more data situation.

Keywords

fuzzy neural nets; load forecasting; power engineering computing; support vector machines; FNN algorithm; Hebei Province; SVM; average failure rate; fuzzy neural network; learning process; short-term power load forecasting; support vector machine; Economic forecasting; Fuzzy neural networks; Fuzzy systems; Information processing; Learning systems; Load forecasting; Neural networks; Power generation economics; Support vector machine classification; Support vector machines;

fLanguage

English

Publisher

ieee

Conference_Titel

Wireless Communications, Networking and Mobile Computing, 2008. WiCOM '08. 4th International Conference on

Conference_Location

Dalian

Print_ISBN

978-1-4244-2107-7

Electronic_ISBN

978-1-4244-2108-4

Type

conf

DOI

10.1109/WiCom.2008.1273

Filename

4679181