A Survey of Prototyping Platforms for Intermittent Computing Research

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.