abstract: Network traffic analysis by means of Quality of Service (QoS) is a popular research and development area among researchers for a long time. It is becoming even more relevant recently due to ever increasing use of the Internet and other public and private communication networks. Fast and precise QoS analysis is a vital task in mission-critical communication networks (MCCNs), where providing a certain level of QoS is essential for national security, safety or economic vitality. In this thesis, the details of all aspects of a comprehensive computational framework for QoS analysis in MCCNs are provided. There are three main QoS analysis tasks in MCCNs; QoS measurement, QoS visualization and QoS prediction. Definitions of these tasks are provided and for each of those, complete solutions are suggested either by referring to an existing work or providing novel methods. A scalable and accurate passive one-way QoS measurement algorithm is proposed. It is shown that accurate QoS measurements are possible using network flow data. Requirements of a good QoS visualization platform are listed. Implementations of the capabilities of a complete visualization platform are presented. Steps of QoS prediction task in MCCNs are defined. The details of feature selection, class balancing through sampling and assessing classification algorithms for this task are outlined. Moreover, a novel tree based logistic regression method for knowledge discovery is introduced. Developed prediction framework is capable of making very accurate packet level QoS predictions and giving valuable insights to network administrators. / Dissertation/Thesis / Masters Thesis Industrial Engineering 2014

Current complex service systems are usually comprised of many other components which are often external services performing particular tasks. The quality of service (QoS) attributes such as availability, cost, response time are essential to determine usability and eciency of such system. Obviously, the QoS of such compound system is dependent on the QoS of its components. However, the QoS of each component is naturally unstable and di erent each time it is called due to many factors like network bandwidth, workload, hardware resource, etc. This will consequently make the QoS of the whole system be unstable. This uncertainty can be described and represented with probability distributions. This thesis presents an approach to calculate the QoS of the system when the probability distributions of QoS of each component are provided by service provider or derived from historical data, along with the structure of their compositions. In addition, an analyzer tool is implemented in order to predict the QoS of the given compositions and probability distributions following the proposed approach. The output of the analyzer can be used to predict the behavior of the system to be implemented and to make decisions based on the expected performance. The experimental evaluation shows that the estimation is reliable with a minimal and acceptable error measurement.