Authors: Abdel Ejnioui; Carlos E. Otero; Ivica Kostanic
Addresses: Department of Information Technology, University of South Florida, Lakeland, Florida 33803, USA ' Department of Electrical and Computer Engineering, Florida Institute of Technology, Melbourne, Florida 32901, USA ' Department of Electrical and Computer Engineering, Florida Institute of Technology, Melbourne, Florida 32901, USA
Abstract: Recent increases in application and user data over cellular networks requires networks service providers to guarantee a well-defined quality of service for their customers. As such, network service providers must be able to evaluate and assess the quality of service in different types of applications over their networks. This paper presents a method for assessing quality of service in application-specific and user-centric data on cellular networks. To this end, it formulates the evaluation problem as a stochastic multi-attribute decision problem in which measurement parameters are used as probabilistic attributes of the problem collected in drive testing over three different cellular networks. Matrix relational analysis is applied on the decision matrix to solve the problem by reaching a final ranking of the networks based on the collected measured values of the problem parameters. A case study is used to show how this approach can be effective in evaluating quality of service in cellular networks.
Keywords: stochastic decision making; wireless networks; quality of service; QoS evaluation; cellular networks; performance evaluation; matrix relational analysis; network ranking.
International Journal of Wireless and Mobile Computing, 2013 Vol.6 No.3, pp.201 - 208
Received: 24 Jul 2012
Accepted: 24 Oct 2012
Published online: 06 Aug 2013 *