Andreas Weinand

Anjie Qiu, Donglin Wang, Sanket Partani et al.

The emergence of sixth-generation (6G) technologies has introduced new challenges and opportunities for machine learning (ML) applications in Internet of Things (IoT) networks, particularly concerning energy efficiency. As model training and data transmission contribute significantly to energy consumption, optimizing these processes has become critical for sustainable system design. This study first conduct analysis on the energy consumption model for both centralized and decentralized architecture and then presents a testbed deployed within the German railway infrastructure, leveraging sensor data for ML-based predictive maintenance. A comparative analysis of distributed versus Centralized Learning (CL) architectures reveals that distributed models maintain competitive predictive accuracy (~90%) while reducing overall electricity consumption by up to 70%. These findings underscore the potential of distributed ML to improve energy efficiency in real-world IoT deployments, particularly by mitigating transmission-related energy costs.

Weinand Andreas, Andreu G. de la Fuente, Lipps Christoph et al.

Within this the work applicability of Physical LayerSecurity (PHYSEC) based key management within Long RangeWide Area Network (LoRaWAN) is proposed and evaluatedusing an experimental testbed. Since Internet of Things (IoT)technologies have been arising in past years, they have as wellattracted attention for possible cyber attacks. While LoRaWANalready provides many of the features needed in order to ensuresecurity goals such as data confidentiality and integrity, it lacksin measures such as secure key management and distributionschemes. Since conventional solutions are not feasible here, e.g.due to constraints on payload size and power consumption, wepropose the usage of PHYSEC based session key management,which can provide the respective measures in a more lightweightway. The results derived from our testbed show that it can be apromising alternative approach.

Andreas Weinand, Raja Sattiraju, Michael Karrenbauer et al.

PHYSEC based message authentication can, as an alternative to conventional security schemes, be applied within \gls{urllc} scenarios in order to meet the requirement of secure user data transmissions in the sense of authenticity and integrity. In this work, we investigate the performance of supervised learning classifiers for discriminating legitimate transmitters from illegimate ones in such scenarios. We further present our methodology of data collection using \gls{sdr} platforms and the data processing pipeline including e.g. necessary preprocessing steps. Finally, the performance of the considered supervised learning schemes under different side conditions is presented.