Title :
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
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;
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
DOI :
10.1109/WiCom.2008.1273
