Application-aware Traffic Prediction and User-aware Quality-of-Experience Measurement in Smart Network
Date of Award
M.S. in Electrical Engineering
Department of Electrical and Computer Engineering
Advisor: Feng Ye
In this thesis, we propose to develop a secure and distributed network quality-of-experience (QoE) measurement for smart networks. Network measurement capability has been updated gradually as the network technology progresses. For example, software-defined network will enable efficient monitoring and control of the core network. However, end-to-end network QoE measurement requires distributed approaches from the user side. In our proposed measurement framework, a traffic measurement agent is deployed in the last-hop gateway. The gateway is equipped with new features, i.e., encrypted packet classifier, traffic prediction, and user quality-of-service (QoS) to QoE mappings. Since all measurement processes are done at the gateway, end user devices are separated from the entire process. Thus security can be provided by the proposed measurement framework. In addition to the framework, we demonstrate an efficient learning approach to develop the traffic prediction scheme and the QoS to QoE mapping scheme. Experiments results are provided to demonstrate that the developed schemes are applicable to a distributed network QoS measurement framework for smart networks.
Electrical Engineering, network measurement, machine learning, application-aware, quality-of-experience, smart network
Copyright 2018, author
Zhang, Jielun, "Application-aware Traffic Prediction and User-aware Quality-of-Experience Measurement in Smart Network" (2018). Graduate Theses and Dissertations. 6693.