An Iterative Information-Theoretic approach to estimate traffic matrix

Traffic matrices are very essential for many network engineering tasks: for instance, load balancing, capacity planning, routing protocol configuration. However, measuring these traffic matrices directly is difficult and costly. Hence many methods have been proposed to estimate these traffic matrices based on link load measurements and other more easily available data. This paper presents an iterative algorithm to estimate traffic matrix without differentiating the access links and the peering links and our algorithm get a similar performance with the Minimal Mutual Information method which requires that difference. Experiments on real backbone network data have also demonstrated that our algorithm is accurate and robust to measurement noise.