Browsing by Author "Williams, Harrison"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Energy-Adaptive Buffering for Efficient, Responsive, and Persistent Batteryless Systems
    Williams, Harrison; Hicks, Matthew (ACM, 2024-04-27)
    Batteryless energy harvesting systems enable a wide array of new sensing, computation, and communication platforms untethered by power delivery or battery maintenance demands. Energy harvesters charge a buffer capacitor from an unreliable environmental source until enough energy is stored to guarantee a burst of operation despite changes in power input. Current platforms use a fixed-size buffer chosen at design time to meet constraints on charge time or application longevity, but static energy buffers are a poor fit for the highly volatile power sources found in real-world deployments: fixed buffers waste energy both as heat when they reach capacity during a power surplus and as leakage when they fail to charge the system during a power deficit. To maximize batteryless system performance in the face of highly dynamic input power, we propose REACT: a responsive buffering circuit which varies total capacitance according to net input power. REACT uses a variable capacitor bank to expand capacitance to capture incoming energy during a power surplus and reconfigures internal capacitors to reclaim additional energy from each capacitor as power input falls. Compared to fixed-capacity systems, REACT captures more energy, maximizes usable energy, and efficiently decouples system voltage from stored charge—enabling low-power and high-performance designs previously limited by ambient power. Our evaluation on real-world platforms shows that REACT eliminates the tradeoff between responsiveness, efficiency, and longevity, increasing the energy available for useful work by an average 25.6% over static buffers optimized for reactivity and capacity, improving event responsiveness by an average 7.7𝑥 without sacrificing capacity, and enabling programmer directed longevity guarantees.
  • Thumbnail Image
    A Survey of Prototyping Platforms for Intermittent Computing Research
    Williams, Harrison; Hicks, Matthew (ACM, 2024-11-04)
    Batteryless energy harvesting platforms are gaining popularity as a way to bring next-generation sensing and edge computing devices to deployments previously limited by their need for batteries. Energy harvesting enables perpetual, maintenance-free operation, but also introduces new challenges associated with unreliable environmental power as systems face common-case, yet unpredictable power failures. Software execution on these devices is an active area of research: intermittently executed software must correctly and efficiently handle arbitrary interruption, frequent state saving/ restoration, and re-execution of certain code segments as part of a normal operation. The wide application range for batteryless systems combined with strict limitations on size and performance means there is little overlap in batteryless system prototypes— platforms are chosen for familiarity or specific features in a given application. Unfortunately, the effectiveness of different intermittent computing approaches varies widely across devices. As a result, intermittent computing research is at best hard to generalize across platforms and at worst contradictory across studies. This work explores several of the device-level differences that substantially affect intermittent system performance across eight low-power prototyping platforms. We examine system-level assumptions made by the major approaches to intermittent computing today and determine how compatible each approach is with each platform. The goal of this paper is to serve as a guide for researchers and practitioners developing intermittent systems to both understand the landscape of devices suitable for batteryless operation and to highlight how interactions between devices and the intermittent software running on them can profoundly affect both performance and high-level conclusions in intermittent systems research.We open source our device bring-up code and instructions to facilitate multi-board experiments for future approaches.