The transition towards 6G networks necessitates a fundamental paradigm shift from reactive network management towards proactive and autonomous optimization strategies. At the center of this evolution lies the “Digital Twin” (DT), which serves as a high-fidelity virtual representation of the physical radio environment. In this talk, we present recent research findings on the construction of differentiable network twins, supported by extensive empirical measurements from real-world datasets in Vienna. In contrast to conventional “black-box” approaches, we propose a framework where network abstractions are rendered fully differentiable. This allows for the direct and scalable optimization of critical network parameters, such as transmit power and load-balancing, utilizing gradient-based Artificial Intelligence.
Furthermore, we discuss the integration of uncertainty-aware Bayesian learning to enhance the prediction reliability of signal parameters (RSRP), particularly within complex urban environments and railway corridors. In the context of 6G, these digital twins evolve beyond simple monitoring tools to become the core engine for Integrated Sensing and Communication (ISAC), facilitating high-precision localization and context-aware connectivity. By addressing the “sim-to-real” gap as a structured AI challenge, this work outlines a practical roadmap for sustainable, zero-touch network management. These insights are intended to provide a solid basis for future communication and collaboration with researchers working on digital-twin-based network evolution and intelligent infrastructure.
Philipp Svoboda is a Senior Researcher with the Institute of Telecommunications at TU Wien. His research focuses on the intersection of mobile network optimization, machine learning, and the digital transformation of infrastructure. He has extensive experience in analyzing large-scale real-world network datasets, particularly the “Vienna traces,” to bridge the gap between theoretical models and practical deployment. Currently, his work centers on the development of differentiable digital twins and AI-driven solutions for 5G-Advanced and 6G systems, with a specific emphasis on smart railway applications and high-mobility scenarios.