Network reliability prediction based on support vector machine

摘要：

Network reliability prediction is significant to make up the strategy for network management.In order to solve the local optimum of BP neural network, support vector machine(SVM) is proposed to predict network reliability in the paper. In the study, Grid method is applied to select optimal parameters of support vector machine. Thus, network reliability prediction model by SVM has four input nodes and one output node. The experimental network reliability data are applied to study the superiority of support vector machine. The comparison of network reliability prediction error between support vector machine and BP neural network demonstrates that network reliability prediction ability of support vector machine is better than that of BP neural network.

关键词： support vector machine nonlinear regression network reliability prediction influencing factors

作者: Zhao Ling

作者单位: Northeast Petroleum University Daqing 163318,China

会议类型: 国际会议

会议名称: 2011 3rd International Conference on Computer and Automation Engineering(ICCAE 2011)(2011年第三届IEEE计算机与自动化工程国际会议)

会议地点: 重庆

会议语种:英文

页码: 583-587

在线出版日期: 2011-01-21（万方平台首次上网日期，不代表论文的发表时间）