An Optimal Estimation of Origin-Destination Traffic in Large-Scale Backbone Network

This paper proposes a constrained iterative optimal approach to estimate traffic matrix, namely all origin-destination traffic, in a large-scale backbone network. Based on the modified principal component analysis method, we denote traffic matrix estimation problem into an iterative optimal process under the constraints followed by it. In each iterative step, the covariance matrix of traffic matrix is used to capture its spatio-temporal correlation in order to make the more accurate estimation. Furthermore, we present an iterative adjustment method to find the optimal solution in accordance with link load deviation yielded by traffic matrix estimation. Thus this will gradually overcome the highly ill-posed nature of this problem and obtain the accurate estimation. Finally, we use the real data from a backbone network to validate our method. Simulation results show that our method is effective and practical.