Full Record

New Search | Similar Records

Author
Title Application-aware Traffic Prediction and User-aware Quality-of-Experience Measurement in Smart Network
URL
Publication Date
Degree MS(M.S.)
Discipline/Department Electrical and Computer Engineering
Degree Level masters
University/Publisher University of Dayton
Abstract 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.
Subjects/Keywords Electrical Engineering; network measurement; machine learning; application-aware; quality-of-experience; smart network
Contributors Ye, Feng (Advisor)
Language en
Rights unrestricted ; This thesis or dissertation is protected by copyright: all rights reserved. It may not be copied or redistributed beyond the terms of applicable copyright laws.
Country of Publication us
Format application/pdf
Record ID oai:etd.ohiolink.edu:dayton1532582833701364
Repository ohiolink
Date Indexed 2020-10-19
Grantor University of Dayton

Sample Images | Cited Works

.