Alexander Gräfe

Alexander Gräfe

Auto-generated profile, based on publicly available information

Alexander Gräfe

Institute for Data Science in Mechanical Engineering, RWTH Aachen University, Aachen, Germany

Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
21 January 2026 in ACM Transactions on Cyber-Physical Systems
Verified
Journal Article
Open access
AGAlexander Gräfe
Alexander Gräfe
FMFabian Mager
Fabian Mager
MZMarco Zimmerling
Marco Zimmerling
STSebastian Trimpe
Sebastian Trimpe
As Machine Learning (ML) becomes integral to Cyber-Physical Systems (CPS), there is growing interest in shifting training from traditional cloud-based to on-device processing (TinyML), for example, due to privacy and latency concerns. However, CPS often comprise ultra-low-power microcontrollers, whose limited compute resources make training challenging. This article presents RockNet , a new TinyML method tailored for ultra-low-power hardware that achieves state-of-the-art accuracy in timeseries classification, such as fault or malware detection, without requiring offline pretraining. By leveraging that CPS consist of multiple devices, we design a distributed learning method that integrates ML and wireless communication. RockNet leverages all devices for distributed training of specialized compute efficient classifiers that need minimal communication overhead for parallelization. Combined with tailored and efficient wireless multi-hop communication protocols, our approach overcomes the communication bottleneck that often occurs in distributed learning. Hardware experiments on a testbed with 20 ultra-low-power devices demonstrate RockNet ’s effectiveness. It successfully learns timeseries classification tasks from scratch, surpassing the accuracy of the latest approach for neural network microcontroller training by up to 2x. RockNet ’s distributed ML architecture reduces memory, latency and energy consumption per device by up to 90% when scaling from one central device to 20 devices. Our results show that a tight integration of distributed ML, distributed computing, and communication enables, for the first time, training on ultra-low-power hardware with state-of-the-art accuracy.

2 July 2026
Verified
Book Chapter
Closed access
PDF file
HHHenrik Hose
Henrik Hose
PBPaul Brunzema
Paul Brunzema
ARAlexander von Rohr
Alexander von Rohr
AGAlexander Gräfe
Alexander Gräfe
ASAngela P. Schoellig
Angela P. Schoellig
STSebastian Trimpe
Sebastian Trimpe