Kaan Aykurt’s research while affiliated with Technical University of Munich and other places

What is this page?


This page lists works of an author who doesn't have a ResearchGate profile or hasn't added the works to their profile yet. It is automatically generated from public (personal) data to further our legitimate goal of comprehensive and accurate scientific recordkeeping. If you are this author and want this page removed, please let us know.

Publications (7)


Digital twin opportunities with leveraging graph neural networks on real network data
  • Article

December 2024

·

4 Reads

ITU Journal on Future and Evolving Technologies

Kaan Aykurt

·

Maximilian Stephan

·

Serkut Ayvasik

·

[...]

·

Sixth-generation networks propose integrating multiple networks while ensuring seamless network performance. Hence, networks are becoming increasingly complex while the traditional methods to manage networks are facing significant challenges as the topology sizes, traffic patterns, and network domains are changing. Autonomous network management solutions, which are often built on digital twins, are emerging as possible candidates for addressing these challenges. Machine learning models are widely used for realizing digital twins. Among many neural network structures, graph neural networks are a subclass of promising machine learning methods that perform well in graph-structured data such as network topologies. In this paper, we explore GNN performance on real network data and present our solution to per-flow mean delay prediction which achieves a MAPE of 35.39%, improving the baseline solutions by over 20% together with additional findings and further improved models for Graph Neural Networking Challenge 2023.;





When TCP Meets Reconfigurations: A Comprehensive Measurement Study

January 2023

·

10 Reads

·

5 Citations

IEEE Transactions on Network and Service Management

The diversity of deployed applications in data centers leads to a complex traffic mix in the network. Reconfigurable Data Center Networks (RDCNs) have been designed to fulfill the demanding requirements of ever-changing data center traffic. However, they pose new challenges for network traffic engineering, e.g., interference between reconfigurations, transport layer protocols, and congestion control (CC) algorithms. This raises a fundamental research problem: can the current transport layer protocols handle frequent network updates? This paper focuses on TCP and presents a measurement study of TCP performance in RDCNs. In particular, it evaluates diverse traffic mixes combining TCP variants, UDP, and QUIC transport protocols. The quantitative analysis of the measurements shows that migrated TCP flows suffer from frequent reconfigurations. The effect of reconfigurations on the cost, e.g. increased Flow Completion Time (FCT), depending on the traffic mix is modeled with Machine Learning (ML) methods. The availability of such a model will provide insights into the relationship between the reconfiguration settings and the FCT. Our model explains 88 the variance in the FCT increase under different reconfiguration settings.



Citations (4)


... Another important goal was that the network should withstand the loss of subnetwork hardware without disrupting existing conversations [25]. That is, they wanted to keep the connections intact as long as the source and destination computers worked, even if one of the computers or the lines between them suddenly stopped working. ...

Reference:

Comparative Study Between the OSI Model and the TCP/IP Model: Architecture and Protocols in Computer Networking Systems
When TCP Meets Reconfigurations: A Comprehensive Measurement Study
  • Citing Article
  • January 2023

IEEE Transactions on Network and Service Management

... Despite the fact that NDT is an evolving technology, broad-successful research could be accomplished in various domains, such as Fifth Generation (5G) [54], 6G [17], IIoT [139], network traffic prediction [165], and Software Defined Networking (SDN)-based networks [189], [5]. Moreover, there are many surveys in the field, such as [273], [21], [130], [81], which cover various scenarios and use cases of DT and NDT. ...

Autonomous Network Management in Multi-Domain 6G Networks based on Graph Neural Networks
  • Citing Conference Paper
  • June 2023

... For the purpose of controlling congestion in datacenter networks with high bandwidth and low latency, Datacenter TCP (DCTCP) was created [137]. To identify and address congestion in a proactive manner, DCTCP makes use of feedback from explicit congestion notification (ECN). ...

On the Performance of TCP in Reconfigurable Data Center Networks
  • Citing Conference Paper
  • October 2022

... Aggregation applications typically need to aggregate massive intermediate results from different worker servers to get final results, thus these applications can generate a large amount of traffic consisting of intermediate data. For example, training deep learning model under parameter server architecture may generate hundreds of GBs traffic or even more [4] during its parameter synchronization process. In Facebook's data center, intermediate traffic contributes 46% of the total traffic at most [5]. ...

Network Traffic Characteristics of Machine Learning Frameworks Under the Microscope
  • Citing Conference Paper
  • October 2021