Comosum: An Extensible, Reconfigurable, and Fault-Tolerant IoT Platform for Digital Agriculture

This work is an experience with a deployed networked system for digital agriculture (or DA). DA is the use of data-driven techniques toward a sustainable increase in farm productivity and efficiency. DA systems are expected to be overlaid on existing rural infrastructures, which are known to be less robust than urban infrastructures. While existing DA approaches partially address several infrastructure issues, challenges related to data aggregation, data analytics, and fault tolerance remain open. In this work, we present the design of Comosum, an extensible, reconfigurable, and fault-tolerant architecture of hardware, software, and distributed cloud abstractions to sense, analyze, and actuate on different farm types. We also present FarmBIOS, an implementation of the Comosum architecture. We analyze FarmBIOS by leveraging various applications, deployment experiences, and network differences between urban and rural farms. This includes, for instance, an edge analytics application achieving 86% accuracy in vineyard disease detection. An eighteen-month deployment of FarmBIOS highlights Comosum's tolerance to intermittent network outages that lasted for several days during many periods of the deployment. We offer practical insights on how FarmBIOS adapts to new DA vendors, reconfigurability challenges in the cloud, persistent failures that are unique to the DA context, and the system's current limitations.