Marco Zimmerling

Fabian Mager, Dominik Baumann, Romain Jacob et al.

Closing feedback loops fast and over long distances is key to emerging applications; for example, robot motion control and swarm coordination require update intervals of tens of milliseconds. Low-power wireless technology is preferred for its low cost, small form factor, and flexibility, especially if the devices support multi-hop communication. So far, however, feedback control over wireless multi-hop networks has only been shown for update intervals on the order of seconds. This paper presents a wireless embedded system that tames imperfections impairing control performance (e.g., jitter and message loss), and a control design that exploits the essential properties of this system to provably guarantee closed-loop stability for physical processes with linear time-invariant dynamics. Using experiments on a cyber-physical testbed with 20 wireless nodes and multiple cart-pole systems, we are the first to demonstrate and evaluate feedback control and coordination over wireless multi-hop networks for update intervals of 20 to 50 milliseconds.

Dominik Baumann, Fabian Mager, Harsoveet Singh et al.

Simulation tools and testbeds have been proposed to assess the performance of control designs and wireless protocols in isolation. A cyber-physical system (CPS), however, integrates control with network elements, which must be evaluated together under real-world conditions to assess control performance, stability, and associated costs. We present an approach to evaluate CPS relying on embedded devices and low-power wireless technology. Using one or multiple inverted pendulums as physical system, our approach supports a spectrum of realistic CPS scenarios that impose different requirements onto the control and networking elements. Moreover, our approach allows one to flexibly combine simulated and real pendulums, promoting adoption, scalability, repeatability, and integration with existing wireless testbed infrastructures. A case study demonstrates implementation, execution, and measurements using the proposed evaluation approach.

Alexander Gräfe, Ding Huo, Johannes Berger et al.

Transformer models are rapidly becoming a cornerstone of modern Internet of Things (IoT) applications, yet their computational and memory demands far exceed the capabilities of a single typical ultra-low-power IoT device. We present CATS, a framework for distributed transformer inference on ultra-low-power wireless devices, enabling multiple devices to collaboratively execute models far larger than what a single device can sustain. At its core, CATS is a communication-aware distributed transformer inference scheme co-designed across transformer partitioning, wireless communication and training. It employs SomeGather, a new pruned communication primitive that selectively broadcasts activation columns to reduce communication bandwidth and RAM usage without sacrificing model accuracy. Building on SomeGather, we design a partitioning method that exploits this primitive for efficient model parallelism. To cope with unreliable wireless communication, CATS employs message-dropout during training, which mimics packet losses and yields models that are robust to message loss during inference. In real-world experiments, we show that CATS brings distributed transformer inference to ultra-low-power wireless devices for the first time, with deployments on up to 16 devices that collaboratively execute transformer models up to 14 times larger than what a single device can run.

Alexander Gräfe, Fabian Mager, Marco Zimmerling et al.

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 paper 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.