Energy-Aware Adaptive Sampling for Self-Sustainability in Resource-Constrained IoT Devices

In the ever-growing Internet of Things (IoT) landscape, smart power management algorithms combined with energy harvesting solutions are crucial to obtain self-sustainability. This paper presents an energy-aware adaptive sampling rate algorithm designed for embedded deployment in resource-constrained, battery-powered IoT devices. The algorithm, based on a finite state machine (FSM) and inspired by Transmission Control Protocol (TCP) Reno's additive increase and multiplicative decrease, maximizes sensor sampling rates, ensuring power self-sustainability without risking battery depletion. Moreover, we characterized our solar cell with data acquired over 48 days and used the model created to obtain energy data from an open-source world-wide dataset. To validate our approach, we introduce the EcoTrack device, a versatile device with global navigation satellite system (GNSS) capabilities and Long-Term Evolution Machine Type Communication (LTE-M) connectivity, supporting MQTT protocol for cloud data relay. This multi-purpose device can be used, for instance, as a health and safety wearable, remote hazard monitoring system, or as a global asset tracker. The results, validated on data from three different European cities, show that the proposed algorithm enables self-sustainability while maximizing sampled locations per day. In experiments conducted with a 3000 mAh battery capacity, the algorithm consistently maintained a minimum of 24 localizations per day and achieved peaks of up to 3000.

Optimizing IoT-Based Asset and Utilization Tracking: Efficient Activity Classification with MiniRocket on Resource-Constrained Devices

This paper introduces an effective solution for retrofitting construction power tools with low-power IoT to enable accurate activity classification. We address the challenge of distinguishing between when a power tool is being moved and when it is actually being used. To achieve classification accuracy and power consumption preservation a newly released algorithm called MiniRocket was employed. Known for its accuracy, scalability, and fast training for time-series classification, in this paper, it is proposed as a TinyML algorithm for inference on resource-constrained IoT devices. The paper demonstrates the portability and performance of MiniRocket on a resource-constrained, ultra-low power sensor node for floating-point and fixed-point arithmetic, matching up to 1% of the floating-point accuracy. The hyperparameters of the algorithm have been optimized for the task at hand to find a Pareto point that balances memory usage, accuracy and energy consumption. For the classification problem, we rely on an accelerometer as the sole sensor source, and BLE for data transmission. Extensive real-world construction data, using 16 different power tools, were collected, labeled, and used to validate the algorithm's performance directly embedded in the IoT device. Experimental results demonstrate that the proposed solution achieves an accuracy of 96.9% in distinguishing between real usage status and other motion statuses while consuming only 7kB of flash and 3kB of RAM. The final application exhibits an average current consumption of less than 15{\mu}W for the whole system, resulting in battery life performance ranging from 3 to 9 years depending on the battery capacity (250-500mAh) and the number of power tool usage hours (100-1500h).