Abstract:
To reduce the estimation’s complexity, an algorithm which estimates traffic matrix based on Gauss Mixed Model(GMM) is proposed. It decreases the times of clustering computing by fully utilizing the physical meaning of GMM and estimates the model parameter by Expectation- Maximization(EM) algorithm to improve the algorithm stability. Experimental results prove this algorithm is effective.
Key words:
traffic matrix estimation,
Gauss Mixed Model(GMM),
Expectation-Maximization(EM) algorithm
摘要： 针对源-目的流量估计解的不稳定性和求解方法的复杂性，提出一种基于高斯混合模型的流量矩阵估算算法，它充分利用高斯混合模型的物理意义，使数据聚类的次数减少，并利用Expectation-Maximization算法估算出模型的参数，提高求解的稳定性。实验结果证明了该方法的有效性。
关键词:
流量矩阵估算,
混合高斯模型,
EM算法
CLC Number:
XU Xiao-dong; XIONG Wei-bin; ZHU Shi-rui. Research on Traffic Matrix Estimation Based on Gauss Mixed Model[J]. Computer Engineering, 2009, 35(14): 132-134.
许晓东;熊卫斌;朱士瑞. 基于高斯混合模型的流量矩阵估算研究[J]. 计算机工程, 2009, 35(14): 132-134.