RBF-SVM在电力通信网光纤保护通道风险评估的应用  

RBF-SVM and Its Application in Risk Evaluation of Power System Communication Fiber-optic Relay Protection Channels

作　　者：高会生[1] 郭爱玲[1] 于晓东[1] 靳玮玮 

机构地区：[1]华北电力大学电子与通信工程系,河北保定071003 [2]许继电气直流输电系统部,河南许昌461000

出　　处：《通信技术》2008年第7期83-85,共3页Communications Technology

摘　　要：支持向量机是最近几年发展起来的一种新的智能学习方法,以RBF为核函数的支持向量机在实际应用中表现出良好的学习性能,被广泛的应用到模式识别中,其参数C和σ对SVM的性能起决定性作用。文中阐述了SVM原理,给出了RBF-SVM的性能随参数变化的规律,并得到了参数C和σ对SVM支持向量个数和测试样本错分率的影响曲线图。最后,通过采用不同核函数的SVM对电力通信网光纤保护通道进行风险评估,比较其评估性能,同时验证了RBF-SVM性能的优势。Support Vector Machine has become a novel machine learning method in recent years, the SVM with RBF is widely used in pattern recognition becase of its good learning properities. However, the performance of RBF-SVM is greatly influenced by the parameter of C and G. In this paper, the principle of SVM is presented, how the parameters affect the performance of RBF-SVM discussed, and the curve of the C and G affecting the number of SV and wrong recognition rate is given. Finally, through risk evaluation with SVMs under different kernel funtions, the performaace of RBF-SVM is verified.

关 键 词：RBF核SVM 核函数 电力通信网 光纤保护通道 风险评估 

分 类 号：TN915.853[电子电信—通信与信息系统]