Recent advances in animal tracking technology have ushered in a new era in biologging. However, the considerable size of many sophisticated biologging devices restricts their application to larger animals, whereas older techniques often still represent the state-of-the-art for studying small vertebrates. In industrial applications, low-power wireless sensor networks (WSNs) fulfill requirements similar to those needed to monitor animal behavior at high resolution and at low tag mass. We developed a wireless biologging network (WBN), which enables simultaneous direct proximity sensing, high-resolution tracking, and long-range remote data download at tag masses of 1 to 2 g. Deployments to study wild bats created social networks and flight trajectories of unprecedented quality. Our developments highlight the vast capabilities of WBNs and their potential to close an important gap in biologging: fully automated tracking and proximity sensing of small animals, even in closed habitats, at high spatial and temporal resolution.
In this paper, the BATS project is presented, which aims to track the behavior of bats via an ultra-low power wireless sensor network. An overview about the whole project and its parts like sensor node design, tracking grid and software infrastructure is given and the evaluation of the project is shown. The BATS project includes a lightweight sensor node that is attached to bats and combines multiple features. Communication among sensor nodes allows tracking of bat encounters. Flight trajectories of individual tagged bats can be recorded at high spatial and temporal resolution by a ground node grid. To increase the communication range, the BATS project implemented a long-range telemetry system to still receive sensor data outside the standard ground node network. The whole system is designed with the common goal of ultra-low energy consumption while still maintaining optimal measurement results. To this end, the system is designed in a flexible way and is able to adapt its functionality according to the current situation. In this way, it uses the energy available on the sensor node as efficient as possible.
The worst-case response time (WCRT) - the time span from release to completion of a real-time task - is a crucial property of real-time systems. However, WCRT analysis is complex in practice, as it depends not only on the realistic examination of worst-case execution times (WCET), but also on system-level overheads and blocking/preemption times. While the implicit path enumeration technique (IPET) has greatly improved automated WCET analysis, the resulting values still need to be aggregated manually with the system-level overheads - an errorprone and tedious process that yields overly pessimistic results. With SysWCET, we provide an integrated approach for the automated WCRT analysis across multiple threads of execution, locks, interrupt service routines, and the real-time operating system (RTOS) in particular. Our approach spans a single IPET formulation over the whole system and exploits RTOS and scheduler semantics to derive cross-kernel flow facts in order to significantly reduce pessimism in the WCRT analysis. We evaluate our approach with a fully functional implementation of SysWCET for the automotive OSEK-OS standard (ECC1), including threads, alarms, interrupt-service routines, events, and PCP-based resource management.
The widespread integration of the Internet of Things (IoT) into daily operations has made optimizing energy consumption in low-power edge devices increasingly important. This is especially critical when battery-powered IoT platforms, like sensor networks, are provided to third parties to run custom sensing and perception applications. In such cases, two main requirements emerge: (A) accurate measurement of task energy consumption to fairly distribute maintenance and operations costs among parties and (B) reliable identification of tasks with high power consumption fluctuations to prevent interference with sensitive measurement campaigns. However, the need for compact, cost-effective, and energy-efficient power measurement solutions often compromises dynamic range, resolution, and overall measurement quality in these platforms. To address these challenges, we introduce TinyEP, a system that leverages machine learning on highly constrained microcontrollers (TinyML) to enhance the quality of power traces recorded by limited measurement hardware on highly constrained devices in real-time. Our approach incorporates online learning in the final layer of the model, combined with sparse feedback from an existing battery fuel gauge IC, to automatically adapt to new environments and compensate for concept drift. We evaluated the robustness of TinyEP under extreme conditions, demonstrating its effective operation within a temperature range of –40 °C to 80 °C. Our results show that TinyEP improves the Mean Absolute Percentage Error (MAPE) in recorded power traces and reduces the MAPE in task energy measurements from over 2% to under 0.8% across all tested scenarios. Additionally, it significantly decreases residual variance during task energy measurements.
Reliable and fine-grained cost-models are fundamental for real-time systems to statically predict worst-case execution time (WCET) estimates of program code in order to guarantee timeliness. Analogous considerations hold for energy-constrained systems where worst-case energy consumption (WCEC) values are mandatory to ensure meeting predefined energy budgets. These cost models are generally unavailable for commercial off-the-shelf (COTS) hardware platforms, although static worst-case analysis tools require those models in order to predict the WCET as well as the WCEC of program code. To solve this problem, we present NEO, an end-to-end toolchain to automate cost-model generation for both WCET and WCEC analyses. NEO exploits automatically generated benchmarks, which are input for 1) an instruction-level emulation and 2) automatically conducted execution-time and energy-consumption measurements on the target platform. The gathered values (i.e., occurrences per instruction, execution-time and energyconsumption per benchmark) are combined as mathematical optimization problems. The solutions to the formulated problems, which are designed to reveal the worst-case behavior, yield the respective cost models. To statically determine upper bounds of benchmarks, we integrated the cost models into the stateof-the-art WCET analyzer PLATIN. Our evaluations on COTS hardware reveal that our open-source, end-to-end toolchain NEO yields accurate worst-case bounds.
Embedded systems with intermittent energy supply can revolutionize the Internet of Things, as they are energy self-sufficient due to energy harvesting. Existing intermittent-computing approaches, running directly from non-volatile memory, allow incremental progress of machine-code instructions. However, this progress does not apply to many devices (e.g., transceivers) having transactional (i.e., all-or-nothing) semantics: Power failures during transactions lead to starvation when frequently experiencing failed attempts. We introduce WoCA, an approach that exploits static, whole-system worst-case analysis for device-driven intermittent computing. With the currently available energy, WoCA enables transactional device uses and guarantees forward progress. WoCA's novel static analysis tracks program-path-sensitive device states and transitions to yield energy bounds. With these bounds, WoCA's runtime decides when to safely execute code between checkpoints. Using WoCA's hardware platform, we validate that WoCA makes more efficient use of available energy compared to worst-case-agnostic approaches, while also giving runtime guarantees.