UserNet (ML-based Monitoring and Management of QoE for User-centric Communication Networks, Emmy Noether Junior Research Group funded by German Research Foundation (DFG))

 

In order to allow QoE monitoring for arbitrary Internet applications, the interplays between QoE and user interactions is investigated and modelled based on measurements and subjective studies. In addition, ML methods are adapted to the domain in order to apply them to encrypted network traffic. This allows to quantify the QoE by monitoring interactions and the resulting changes in the encrypted application traffic. Based on this, a data-driven improvement of QoE and QoE fairness is enabled by using reinforcement learning to find optimal network configurations by interacting with the dynamic network environment. By means of powerful, software-defined networking (SDN) technologies like P4, together with available computing resources in the network, such fine-granular models can now be implemented in the network for the first time, such that network management becomes more dynamic. Thus, the implementation of the required ML-based algorithms and components and their integration into network operation is researched.

 

 

 

 

In-network Video Traffic Management (Collaboration with AT&T Research Labs, USA and University of Würzburg, Germany)

The rapid growth of short-form video streaming services like TikTok, Instagram Reels, or YouTube Shorts poses major challenges, for service providers and network operators. High download volumes and application-specific pre-loading strategies cause fluctuations in bandwidth demand that often lead to excessive resource consumption, especially when users quickly swipe past videos. To address these challenges, different network management techniques can be implemented. For this, this project researches, for example, the impact of implementing bandwidth capping on short-form video traffic. To gain a better understanding of its effects, data is collected both from the network and application layers. This research helps to assess the impact on network dynamics, fairness, and users’ Quality of Experience (QoE).
The results will contribute to more efficient video traffic management strategies, optimizing network performance while ensuring a seamless streaming experience.