Waggle: An open sensor platform for edge computing

Many advanced sensors are capable of producing extremely large and continuous data streams. Hyperspectral imagers, microphones, high-resolution cameras, and 3D scanning devices can easily generate gigabytes of data per day, making it impractical for many wireless sensor platforms to stream all collected data to the cloud for analysis. Furthermore, in some sensor deployments, privacy concerns may restrict the resolution or content of data leaving the devices and being routinely stored in the cloud. To address this situation, sensor platforms must reduce or transform the data in situ, sending only the analyzed results to a central server. In designing an open sensor platform capable of leveraging advances in machine learning to support edge computing, several challenges arise, including resilience, performance isolation, and data privacy. This paper describes the architecture of the Waggle platform developed at Argonne National Laboratory. As an open platform, Waggle supports a wide range of sensors, including experimental sensors to measure airborne pollutants such as hydrogen sulfide and ozone, as well as cameras intended to detect urban flooding and automobile traffic. The Waggle platform is used by the Array of Things, a National Science Foundation project to deploy 500 sensor platforms in the city of Chicago, beginning in mid-2016.

I. Introduction

Wireless sensor platforms span a wide range of designs, from lightweight wearable devices powered by battery or energy-harvesting technology to large unmanned remote monitoring stations used in climate research. Lightweight wireless sensors are often vertically integrated to achieve maximum power efficiency and a small, optimized form factor. However, for wireless sensor systems designed to use multiple high-bandwidth sensors, a programmable general-purpose platform is desired. Many advanced sensors can produce extremely large and continuous data streams. Hyperspectral imagers, such as those used to investigate ecosystem fluxes [1], microphones used to measure urban noise [2], and high-resolution cameras capable of counting pedestrians can easily generate multiple gigabytes of data per day, making streaming all collected data to the cloud impractical. Furthermore, in some sensor deployments, privacy concerns may restrict the resolution of data leaving the devices and being routinely stored in the cloud. Ultimately, a new generation of in situ sensing devices is needed with sufficient computational power to support machine learning across the complement of onboard sensors, moving from embedded devices that are “smart” (but inflexible) to those that can learn and discover. To address this situation, sensor platforms must use the computational power of multiple CPU/GPUs to reduce the data in situ, sending only analyzed results to the cloud. An architecture to support edge computing capable of leveraging the latest advances in machine learning to analyze and classify data must overcome several challenges, including resilience, performance isolation, and data privacy. We describe here the architecture of Waggle, an open sensor platform for edge computing developed by Argonne National Laboratory.