Desta Haileselassie Hagos successfully completed his PhD trial lecture and thesis defense at the University of Oslo on Wednesday, the 15th of April 2020 and will be awarded the degree of Doctor of Philosophy.
The title of his thesis is “Discovering the Dynamic Complexity of TCP Using Machine Learning and Deep Learning Techniques” and the given topic for his trial lecture was “MultiPath TCP and RTP / RTCP protocols: motivations, mechanisms, deployment, and performances”.
The doctoral thesis mainly focuses on monitoring of internal TCP conditions in the end nodes, based on analysis of passive traffic measurements carried out in an intermediate node in the network. The research is believed to be industry-relevant, as passive traffic measurement is a method increasingly used by network operators and Internet service providers to analyze the communication performance of network-based applications and services. The work proposes different models and solutions for predicting TCP conditions in the end node, and presents experiments that indicate that the predictions provide relatively good accuracy over different validation scenarios and over the use of different TCP variants.
The work presented in this dissertation aims to obtain detailed knowledge about the end hosts by monitoring information of the packets that pass through the network, and by employing machine learning and deep learning-based techniques on the monitored network traffic. Since machine learning and deep learning methods are good at coping with complex tasks and massive amounts of data, they might play an important role in predicting the TCP per-connection internal states. Understanding the dynamic complexity of the internal states of TCP is a fundamental challenge, and especially demanding due to the dynamics and complexity of modern networks. Even though this is the main objective of the dissertation, our work shows that related techniques can also be used to find other information about the hosts,
The analyzes of this dissertation focus mainly on TCP internal state monitoring from passive traffic measurements. We believe that our work will be useful to the industry as passive measurements are becoming increasingly useful for network operators and Internet Service Providers to evaluate the communication performance of applications and services running on their networks. Our experimental results indicate the effectiveness of the proposed prediction models with reasonably good accuracy across different validation scenarios and multiple TCP variants
The following committee has been appointed to evaluate his thesis, trial lecture and defense:
- First external opponent: Professor Nadjib Aait Saadi, UVSQ Paris-Saclay University, France.
- Second external opponent: Associate Professor Marija Slavkovik, University of Bergen, Norway.
- Internal member and committee administrator: Professor Josef Noll, Department of Technology Systems, University of Oslo.
Desta Haileselassie Hagos carried out his PhD work at the Department of Technology Systems, University of Oslo.
His main supervisor was Professor Paal Einar Engelstad, Department of Technology Systems, University of Oslo and co-supervisors Professor Øivind Kure, Department of Technology Systems, University of Oslo and Professor Anis Yazidi, OsloMet.