Battery-free devices collect the harvested ambient energy in their energy storage capacitors. The size of the storage capacitor is one of the main factors affecting the device’s active time and power failure rate. In fact, a larger capacitor ensures energy autonomy for longer operations, while a smaller capacitor charges faster and shrinks inefficient cold starts. This paper presents CapDYN , a new energy storage architecture that can self-adapt its capacity based on incoming ambient energy. CapDYN automatically reconfigures the size of its capacitor bank to both speed up charging and improve execution rate. CapDYN reduces the startup time by up to 98% and can schedule tasks up to 38% faster, compared to a fixed-size capacitor. CapDYN operates in a fully autonomous manner consuming down to 11.6 µW in its simplest implementation and replaces the power-hungry microcontroller governing the switching operation with a dedicated ultra-low-power circuit built with COTS components. Its power consumption improves the previous state of the art by 73%, all the while featuring uncompromising reactivity. CapDYN can instantly react to sudden power transients without incurring extra power draw by foregoing MCU-driven reconfiguration used in state-of-the-art dynamic energy storages.

Backing up the intermediate results of hardware-accelerated deep inference is crucial to ensure the progress of execution on batteryless computing platforms. However, hardware accelerators in low-power AI platforms only support the one-shot atomic execution of one neural network inference without any backups. This article introduces a new toolchain for MAX78000, which is a brand-new microcontroller with a hardware-based convolutional neural network (CNN) accelerator. Our toolchain converts any MAX78000-compatible neural network into an intermittently executable form. The toolchain enables finer checkpoint granularity on the MAX78000 CNN accelerator, allowing for backups of any intermediate neural network layer output. Based on the layer-by-layer CNN execution, we propose a new backup technique that performs only necessary (urgent) checkpoints. The method involves the batteryless system switching to ultra-low-power mode while charging, saving intermediate results only when input power is lower than ultra-low-power mode energy consumption. By avoiding unnecessary memory transfer, the proposed solution increases the inference throughput by 1.9× for simulation and by 1.2× for real-world setup compared to the coarse-grained baseline execution.

Batteryless image sensors present an opportunity for long-life, long-range sensor deployments that require zero maintenance, and have low cost. Such deployments are critical for enabling remote sensing applications, e.g., instrumenting national highways, where individual devices are deployed far (kms away) from supporting infrastructure. In this work, we develop and characterize Camaroptera, the first batteryless image-sensing platform to combine energy-harvesting with active, long-range (LoRa) communication. We also equip Camaroptera with a Machine Learning-based processing pipeline to mitigate costly, long-distance communication of image data. This processing pipeline filters out uninteresting images and only transmits the images interesting to the application. We show that compared to running a traditional Sense-and-Send workload, Camaroptera’s Local Inference pipeline captures and sends upto \( 12\times \) more images of interest to an application. By performing Local Inference , Camaroptera also sends upto \( 6.5\times \) fewer uninteresting images, instead using that energy to capture upto \( 14.7\times \) more new images, increasing its sensing effectiveness and availability. We fully prototype the Camaroptera hardware platform in a compact, 2 cm \( \times \) 3 cm \( \times \) 5 cm volume. Our evaluation demonstrates the viability of a batteryless, remote, visual-sensing platform in a small package that collects and usefully processes acquired data and transmits it over long distances (kms), while being deployed for multiple decades with zero maintenance.