WSEAS Transactions on Mathematics
Print ISSN: 1109-2769, E-ISSN: 2224-2880
Volume 19, 2020
An Adaptive Technique for Estimating Traffic Intensities for a Network in Random Markovian Routing
Authors: Debanjan Bhattacharjee, Yan Zhuang
Abstract: We propose an efficient method for estimating a vector of parameters that characterize the node-tonode traffic intensities in a network. The estimation procedure is free from any initial estimate which is often difficult to choose for iterative procedures that occur in maximum likelihood estimation or method of moments. The procedure discussed here updates the information from a continuous chain of data until a stopping variable decides the final sample size and the estimate. More importantly, it considers the cost of logistics in sampling. We discuss important desirable properties of the estimation-procedure under the assumption of Poisson distribution. Data analyses reveal a highly accurate estimation and demonstrate a fast convergence.
Search Articles
Keywords: Markovian-Routing, Network-Tomography, Poisson Thinning, Risk Efficiency, Sequential-Estimation
Pages: 549-554
DOI: 10.37394/23206.2020.19.59
WSEAS Transactions on Mathematics, ISSN / E-ISSN: 1109-2769 / 2224-2880, Volume 19, 2020, Art. #59