Research on Comparison and Application of SVM and FNN Algorithm

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 I 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.