Abstract
The performance analysis of the mobile ad-hoc network (MANET) is a challenging issue. In this paper, network tomography is studied to analyse the network performance in a dynamic MANET. For such a purpose, a network tomography analytical model is proposed for a dynamic network environment. Expected Maximization (EM) algorithm for network tomography is able to estimate the network performance parameter in accordance to network performance observations. Our study is different than current network tomography approaches where are applied for static wired network. Over the dynamic network, we proposed a new algorithm that is called Stitching algorithm to aggregate the dynamic performance. Specifically, the stitching algorithm concatenates the performance parameter i.e. link delay, from distinguish time periods. Therefore, the network behaviour as well as the corresponding performance in a mobile ad-hoc network can be derived over a continuous period.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
