基于Bayesian网IP网络拥塞链路定位算法  

IP Network Congested Link Location Algorithm Based on Bayesian Network

作　　者：周欣[1] 周巍[1] 

机构地区：[1]西北工业大学自动化学院,电子信息学院,西安710072

出　　处：《电子科技大学学报》2017年第3期537-542,共6页Journal of University of Electronic Science and Technology of China

基　　金：国家自然科学基金(61602383);中央高校基本科研业务费(3102016ZY024)

摘　　要：在借助E2E路径性能主动探测技术进行内部拥塞链路推理的网络层析成像方法中,传统的利用路径探测计算链路丢包率的方法涉及线性方程组求逆,其计算量过大可能导致算法失效。对此,该文提出一种基于布尔代数的IP网络拥塞链路定位算法,通过对求解先验概率的线性方程组构造满秩系数矩阵,从而计算出各链路拥塞先验概率,再借助贝叶斯最大后验概率算法推理定位当前时刻拥塞链路集合。实验验证了该算法的有效性及准确性。In the method of end-to-end （E2E） path performance active detection （network tomography）, the link loss rate solution methods involve the inverse of linear equations, so its large computation complexity may lead to failure. This paper proposes a new congestion link location algorithm based Boolean model. First the nonsingular coefficient matrix of the linear system for solving prior probability is formed; then the prior probability of link congestion is calculated. Finally, based on Bayesian maximum a posteriori probability （MAP） estimator, the set of congested links can be located. The validity and accuracy of this algorithm is verified by experiments.

关 键 词：贝叶斯最大后验概率 Boolean代数 拥塞链路推理 IPN络 

分 类 号：TP393.09[自动化与计算机技术—计算机应用技术]