Informatics, TU Vienna

Performance Analysis

Analyzing hybrid scheduling-cum polling mechanisms multiple classes of self-similar and long-range dependent traffic input.


A polling model resembles a system of multiple queues targeted in cyclic order by a single server. The characteristics of polling models show a noticeable impact with performance investigations of network-related applications. To provide guaranteed QoS to the end-user of multiservice Internet, a variety of scheduling schemes have been introduced in the market. To date, researchers have been analyzing polling models and scheduling schemes separately. Polling models have only been analyzed with Poisson traffic distributions.

In this talk we will survey polling models with realistic self-similar and long-range dependent traffic distributions. Our combination of traditional polling and common scheduling schemes offers a more promising differential treatment in terms of providing the required QoS to the various kinds of applications found in modern 4G wireless networks. The talk will address the results obtained from the analytical framework we have built by considering multiple classes of long-range dependent and self-similar traffic. The framework is based on a G/M/1 queuing system, which has been analyzed under a variety of polling mechanisms. In our study, we have combined different polling mechanism and scheduling schemes. We have built a Markov chain for G/M/1 queuing systems and extracted closed-form expressions for different QoS parameters such as delay and packet loss rate. We performed simulation experiments in C++ to validate our proposed analytical framework for evaluating the QoS parameters.


Mohsin Inftikhar is an Associate Professor in Computer Science at the King Saud University in Riyadh, Saudi Arabia. He received his BSc in Electrical Engineering from the University of Engineering and Technology Lahore, Pakistan in 1999, his MEngSc in Telecommunications from the University of New South Wales in 2001, and his PhD from the University of Sydney in 2009. He has been a consultant for National Information Communication and Technology Australia (NICTA) and Soul Communications Australia during 2007-2009. His research interests include Quality of Service (QoS), Traffic Modeling, Polling Models, 3G/4G Networks, Markov Chains, Stochastic Processes, Network Calculus, Sensor Networks and Wireless Body Area Networks.


This talk is organized by the Automation Systems Group at the Institute of Computer-Aided Automation.