Today, Prof. Michael Seufert will give a talk on Machine Learning-supported Network Management for User-centric Communication Networks at the IfI Colloquium at the University of Zurich. In his talk, he will discuss how machine learning techniques can be used to optimize and control modern communication networks in order to improve the user experience.

Abstract:

In modern user-centric networks, ensuring a high Quality of Experience (QoE) for Internet applications is becoming increasingly difficult as traditional monitoring and management methods reach their limits. This talk explores how machine learning can serve as a powerful tool to overcome these challenges. Supervised machine learning models can enable highly accurate QoE monitoring, even for encrypted network traffic, while reinforcement learning offers promising strategies for proactive QoE optimization. However, despite these advantages, challenges such as model overfitting and the need for labeled QoE data must also be addressed.

?

?